Prompt 5: Classical Chinese to Modern Chinese / 白话 (Optimized Plain Language) v6.13

Scope for Prompt 5: Apply when modernizing classical/East Asian sources; source wording and source-title classification control the repair.




BATCH 75 — UNIVERSAL MATERIALITY-AWARE POLISH + ANTI-CHURN HARDENING — 4 June 2026

This Batch75 patch is universal. It applies to all ATR translation, review, refinement, formatting, QA, no-repair promotion, packaging, and handoff workflows. It does not weaken any Batch74 false-pass, exact-artifact, Latin-script fluency, hybrid-residue, title/link, href/src, Blogger-chrome, or source-fidelity safeguards.

MATERIALITY-AWARE POLISH GATE
Before making any visible-text change during translation, refinement, adversarial review, repair, audit, or no-repair promotion, classify the proposed change:

A. REQUIRED REPAIR — must be fixed.
Required repairs include defects in source fidelity, omission/addition, mistranslation, doctrinal or technical term accuracy, article-central terminology consistency, speaker attribution, exact-title/link-text handling, source-language residue, mixed-language/hybrid residue, malformed retained source/Sanskrit/Pāli/Tibetan/English labels, target-language grammar, punctuation or line-merge damage, target-language readability, HTML/link/media/code integrity, and target-language naturalness where current wording sounds machine-translated, obscure, distracting, or misleading.

B. BENEFICIAL POLISH — allowed in active editing passes.
Beneficial polish is not strictly wrong but materially improves publication quality: naturalness, readability, sentence flow, public ATR Dharma-article register, reduction of translationese, clarity of difficult doctrinal points, consistency of repeated term families, idiomatic phrasing where literal wording is clunky, or smooth grammatical integration of retained technical labels. If visible text changes, the pass remains an editing/repair/refinement pass and cannot be promoted as no-repair in the same pass unless a separate no-material-edit promotion pass is then performed.

C. PREFERENTIAL REWRITE — avoid.
Do not rewrite merely because another acceptable phrasing is possible. If the current wording is source-accurate, doctrinally clear, grammatically correct, natural, termbank-consistent, publication-acceptable, and free from residue/hybrid/title/punctuation/link/HTML defects, do not churn synonyms or sentence structure.

MODE-SPECIFIC BEHAVIOR
Active translation / repair / adversarial review: required repairs must be made; beneficial polish may be made if it improves publication quality without changing source meaning or adding doctrine; preferential rewrites should normally be avoided. Record visible-text edits and keep repair/editing status.

No-repair promotion: reopen the exact latest artifact, actively search for required repairs, identify optional polish without editing it, and do not fail promotion merely because another acceptable phrasing exists. If only optional polish or preferential alternatives remain, record “optional polish only; no material repair required.” If any required repair is found, repair it and reset to the repair status.

CHANGE MATERIALITY LEDGER
For repair/adversarial-review passes, the QA/changelog must include a compact Change Materiality Ledger for representative and material visible-text changes: nearest heading/sentinel, old wording, new wording, category (Required repair / Beneficial polish / Preferential rewrite avoided), reason, and whether the change affects status. For no-repair promotion passes, report required repairs found yes/no, beneficial polish identified but not edited yes/no, preferential rewrites avoided yes/no, and material edits made yes/no.

ANTI-CHURN STOP RULE
After repeated adversarial review passes, if the exact latest artifact has no required repairs and remaining possible changes are only preferential rewrites or optional beneficial polish, stop editing. Do not reset status through synonym-level rewriting. A no-repair promotion pass may promote only after exact-artifact reopening, source comparison, terminology/residue/hybrid/title/link/href/src/structure/fluency gates, no required repair, and no visible-text material edit.

DO NOT WEAKEN STRONG QA
Continue to treat omissions, additions, mistranslations, doctrinal distortion, wrong technical terms, source-language residue, mixed-language hybrids, malformed retained labels, broken grammar, awkward translationese that damages publication quality, exact-title drift, link-text corruption, href/src/media/code mutation, speaker-attribution issues, punctuation/line-merge damage, structural omissions/duplications, and misleading target-language wording as material defects requiring repair.

BATCH 74 — UNIVERSAL MATERIALITY-AWARE POLISH + ANTI-CHURN HARDENING — 4 June 2026

This Batch75 patch is universal. It is not Polish-only and must apply across Latin-script, non-Latin-script, inflected, analytic, right-to-left, and mixed-script target languages. Preserve all Batch73 Presence / hybrid-residue safeguards and all inherited Batch72/71/70/68/67/66 safeguards.

FALSE-PASS / REUSED-ARTIFACT FAILURE GATE
A review, repair, no-repair promotion, package, or handoff pass is invalid unless it reopens the exact latest artifact and produces fresh evidence for this pass. Do not reuse prior pass summaries, prior links, old QA reports, old filenames, or memory as if they were a new review. If a response claimed a new pass but actually reused prior artifacts or did not review, explicitly retract that claim, identify the latest real artifact, and do not continue pretending the false pass exists.

EXACT-ARTIFACT EVIDENCE REQUIREMENT
Every pass must report the exact input artifact path/name, exact output artifact path/name, whether the output is byte-for-byte identical or materially changed, and SHA/hash or equivalent identity evidence when the tool environment allows it. State whether each intended replacement matched and applied. If no new artifact or new no-material-edit QA report is produced, do not claim a new pass; say: No new pass was completed.

NO-REPAIR VS REPAIR SEPARATION
A strict no-repair promotion pass must make no material edits. If any material issue is found, promotion fails. Either stop with a failed-promotion report or begin a separate material repair pass. Any pass that makes material edits must use: REPAIRED AFTER RE-AUDIT — material gates currently pass, no-repair promotion still required. It must not also promote in the same pass.

THOUGHT-ONLY REVIEW PROHIBITION
Thinking briefly and reusing old links is not a review. A valid review must show concrete evidence: opened latest artifact, searched/scanned target text, sampled high-risk source/target passages, ran target-language fluency checks, checked the cumulative risk basket, checked href/src/media/code parity, and generated a new QA report or explicitly stated that no new artifact was created.

STRING-SPECIFIC REPAIR FRAGILITY / 0-MATCH RULE
If a targeted repair does not match the current artifact, do not assume the issue is fixed. Search semantic variants, shorter substrings, inflected variants, capitalization variants, punctuation variants, HTML-separated variants, and nearby context. Log every 0-replacement intended repair as a warning requiring investigation. For scripted repairs, QA must list old string/pattern searched, match count, replacement applied, 0-match intended repairs, semantic follow-up search, and before/after cumulative risk-basket status.

LATIN-SCRIPT RESIDUE AND FLUENCY GATE
For Latin-script target languages, ordinary English residue is visually hidden because both source and target may use Latin characters. Run an extra Latin-script residue scan for English words left in ordinary prose, English technical labels with local grammar errors, English terms glued to local inflections/cases/prepositions, unquoted English labels used as target-language nouns, partially translated source-title fragments, and English idiom calques that look superficially grammatical.

INFLECTED-LANGUAGE PROTECTED-LABEL AGREEMENT GATE
For inflected target languages, retained labels such as AMness, I AMness, Presence, Awareness, Self, No Mind, no-mind, Dharma, Dhamma, Maha, anatta, anātman, dhātu, skandha, and śūnyatā must be checked for case, gender, number, agreement, and natural grammar. If a protected label is retained, the surrounding sentence must still be natural. Use target-language-first phrasing, quotes, or a short explanation rather than forcing local grammar onto the retained label.

SLASH-CALQUE HARDENING
Scan visible prose for slash compounds such as A/B, A / B, A/B/C, subject/object, doer/agency, Dhamma/Dharma, I/self/Self, mind/consciousness, realization/actualization, no-self/non-self/anatta/anātman, linked title fragments, and person aliases joined with slashes. Classify each as exact title/proper label, glossary/termbank, ordinary prose, or ambiguous. Preserve exact titles and intentional glossary labels; convert ordinary prose into natural target-language coordination, apposition, or explanatory phrasing; flag ambiguous cases.

EXACT TITLE VS TRANSLATED TITLE HARDENING
For every link-bound title, decide separately whether it is preserved exactly, fully translated naturally, or intentionally paired. Do not partially translate titles, honorifics, or title fragments such as translating “Mr.” while leaving the rest English. Do not mix target-language words into exact English titles unless that is the exact source title. QA must list linked titles as preserved, translated, or intentionally mixed/paired.

IDIOM AND METAPHOR CALQUE HARDENING
Prompt-level review must actively hunt literal renderings of English idioms/metaphors and build a target-specific idiom/calque risk basket. Seed examples include: go and read; goes down the drain; along the line of; break through; stood out; one hand claps; the drop is thorough; quality time; open and boundless; wholly thus; always already so; no mirror reflecting; magical appearances are too empty. This list is illustrative, not exhaustive.

TECHNICAL TERM FAMILY DRIFT GATE
Once a term family causes repeated repairs, add the family to the cumulative risk basket and scan globally in all variants. High-risk families include actualization/actualize/embodied/lived/integrated; ground/Ground of Being/ground reality/basis/path; Presence/pure Presence/total Presence; AMness/I AMness/I AM; Self/self/no-self/no-I/anatta/anātman; no-mind/No Mind/Mind that is no-mind; subject/object; doer/agency/no-doership; total exertion/total activity/full functioning; suchness/thusness/isness/wholly thus/Always So; Maha; yāna/lower yānas; dhātu/skandha; knowledge/cognitive obscurations; māyā/magical appearances; mirror/no mirror/mirror-like awareness.

MECHANICALLY CORRECT BUT UNNATURAL IS MATERIAL
A translation can pass termbank checks and still fail if the target-language prose is unnatural or doctrinally misleading. Treat unnatural case/gender/number agreement, source word order copied too literally, line-merge fragments, technical labels without grammatical integration, slash-heavy prose, literal metaphor calques, target-language punctuation defects, capitalization problems, and misleading ordinary-word renderings of Dharma terms as material defects when they affect readability or doctrinal clarity.

NO-REPAIR PROMOTION EVIDENCE ADDENDUM
A no-repair pass must include a section titled “No New Artifact Reuse / Exact Artifact Evidence” with: I reopened: [exact file]; I produced: [exact report/file]; Material edits made: yes/no; if no, output is byte-for-byte identical/hash-equivalent/explicitly copied unchanged; if yes, no promotion allowed; prior pass status was not assumed; new review evidence is listed.

CROSS-LANGUAGE TERM SOURCE EVIDENCE LIMIT
Use target-language Buddhist sources where available to confirm major Dharma term choices, but source evidence supports broad term choices only. It does not prove sentence-level fidelity, context fit, or target-language fluency. Paragraph/link/blockquote/list counts are necessary but insufficient and must never be treated as proof of translation quality.

STATUS DISCIPLINE
If material issues are found after a previous no-repair promotion, state: Previous promotion was premature. This pass found material issues that should have been caught earlier. Status is reset to REPAIRED AFTER RE-AUDIT — material gates currently pass, no-repair promotion still required. Never claim strict-certified final.

BATCH 73 — UNIVERSAL PRESENCE GATE + TARGET-LANGUAGE-FIRST PARENTHETICAL ORDER + HYBRID RESIDUE HARDENING — 1 June 2026

This Batch73 patch is universal. It is not a Japanese-only fix. Apply it to all ATR translation, review, refinement, HTML translation, audit, formatting, package, and promotion workflows for all target languages.

UNIVERSAL KEY TERM RESEARCH BEFORE DEFAULT TRANSLATION GATE
Before translating or standardizing any high-risk AtR/Dharma term, do not rely only on dictionary equivalence, memory, previous target-language habits, or another language's termbank. Create or update a compact Key Term Research / Decision Table for article-central terms. Include source term, target rendering, translated/retained/transliterated/paired status, protected-label status, ordinary-prose rule, forbidden/high-risk renderings, whether external/source research is needed, and whether the term has multiple senses.

Minimum high-risk basket when present: Presence/presence, Awareness/awareness, I AM/AMness, anatta/no-self/non-self/anatman, emptiness/empty nature, dependent arising/dependent origination, non-dual/non-duality, no-mind/No Mind/One Mind, luminosity/clarity/vividness, manifestation/appearance/phenomena, suchness/thusness/isness, subject/object/subject-object division, agent/agency/doer/doership/non-doership, spontaneous perfection, total exertion, Dzogchen/Mahamudra/rigpa/Dharma/Buddhadharma, and article-specific technical terms.

UNIVERSAL PRESENCE GATE
Treat Presence as a high-risk AtR/Dharma term, not a generic English word. Distinguish technical AtR Presence from ordinary presence/present, ever-present/already-so phrasing, philosophical/metaphysics-of-presence usage, and Dzogchen title/phrase usage such as Instant Presence. Technical AtR Presence points to luminous immediacy/direct actuality/the vivid fact of being-experience and appears in phrases such as pure Presence, Total Presence, Presence-Awareness, Presence is spontaneously perfected, manifold of Presence, and nature of Presence. It requires target-language research and a termbank decision.

Japanese house-style note for the Seven Stages article family: technical AtR Presence defaults to 臨在; pure Presence = 純粋な臨在; Total Presence = 総体的臨在; Presence-Awareness = 臨在＝覚知; Presence is spontaneously perfected = 臨在は自ずから円成している / context-specific. Avoid 現前性 as the default for AtR Presence unless the context is specifically philosophical/phenomenological. Ordinary present/ever-present contexts may require 現前している, すでに現れている, 常にすでにそうである, or another natural phrase. Do not impose this Japanese note on other target languages. Chinese AtR house style may preserve 臨在 where applicable, but Chinese choices are clues, not automatic authorities for all other languages.

TARGET-LANGUAGE-FIRST PARENTHETICAL ORDER RULE
In ordinary target-language prose, if a retained English/Sanskrit/Pāli/Tibetan/source label is useful, prefer target-language first: target-language rendering（source label）. Avoid source-label first forms in ordinary prose unless the source label is an exact title, is being discussed as a phrase, the target-language convention strongly prefers it, the user explicitly requests it, or it is a glossary/termbank entry. Do not glue retained source labels directly to target-language case markers, particles, suffixes, postpositions, clitics, or inflections.

Japanese examples: use 無我（anatta）の, not anatta の; 空性（shunyata）の実現, not shunyata の実現; 心（Mind）, not Mind（心） in ordinary prose; 伝達（transmission）, not transmission（伝達）; 無我（no-self）, not no self（無我）. Avoid hybrids such as Pure覚知, Natural覚知, Non-dual は, dependent origination の, ground と path, meditative composure と insight, no-mind の状態, anatta実現, Maha経験, On 空性, Self-実現, and Being／Self-Realisation への.

UNIVERSAL HYBRID RESIDUE SCAN
Before final or promotion, build a target-language-specific hybrid scan basket. Search for English/source labels glued to local particles/case markers/suffixes/inflections; English words inside target-language compounds; target-language words inserted into exact English titles; mixed-script technical hybrids; English-first parentheticals in running prose; translated fragments inside exact English titles; ordinary English prose overprotected as technical labels; and stray spaces before local particles after parentheses. For Latin-script target languages, run an extra ordinary-English residue scan because English residue is harder to see.

Japanese risk basket seed: Pure覚知; Natural覚知; Non-dual は; dependent origination の; ground と path; meditative composure と insight; no-mind の状態; anatta の/へ/と/を/は/後/実現; Maha経験; On 空性; Self-実現; Being／Self-Realisation への; transmission（伝達）; no self（無我）; Dhamma／Dharma） を; Awakening to Reality 実践 Guide; 音Cloud; Scenery……; 真如のMaha経験; 五蘊（五蘊）. Also scan Latin/source labels before の, を, に, へ, と, は, が, で, も, から, まで, より and before 後, 的, 性, 実現, 経験, 状態, 化, 作用, 実践, 知見, 覚知, 空性.

EXACT TITLE VS TRANSLATED TITLE HANDLING
For every linked article/book/video/audio title, decide whether the link text should remain the exact source title or be translated as a full natural target-language title. If preserved, preserve the whole title exactly; do not partially translate it. If translated, translate the whole title naturally and retain the exact source title in parentheses only when useful. Do not create mixed titles such as On 空性, Awakening to Reality 実践 Guide, or Recognizing Rigpa vs Realizing 空性. Do not translate URL slugs. Record intentional title preservation/translation in QA.

PROTECTED-LABEL WHITELIST DISCIPLINE
A word being technical does not automatically mean it should remain in English. Classify every retained English/Sanskrit/Pāli/Tibetan label as exact title, proper name, URL/code, intentionally retained technical term, intentionally retained English AtR label, gloss in parentheses after target-language rendering, or human-review placeholder. Ordinary lowercase terms such as experience, realization, practice, view, awareness, consciousness, manifestation, ground, path, source, self, mind, state, clarity, naturalness, ordinariness, spontaneity, agent, doer, doership, subject, and object should normally be translated unless a reason is documented.

TERM-FAMILY ESCALATION RULE
If more than one material issue is found around the same term family, escalate that family into the active termbank and scan basket. Example: if Presence was mistranslated once, scan Presence, pure Presence, Total Presence, Presence-Awareness, nature of Presence, present, ever-present, and target-language alternatives globally. If one anatta hybrid appears, scan every anatta/no-self/non-self/anatman form. If one total exertion issue appears, scan total exertion/total activity/complete activity/full function equivalents globally.

TOTAL EXERTION SOURCE-AWARE RULE
Do not default total exertion mechanically. For Japanese Dōgen/Zenki contexts, consider 全機 and 一法究尽 depending on source meaning. For Chinese, preserve the existing rule not to default to 全体作用; use 一法究尽 / 具尽 / context-specific handling. For other languages, research source/context before setting a default.

NO-REPAIR PROMOTION HARDENING
A no-repair promotion pass must include exact-artifact reopening, source comparison, Prompt 6 semantic fidelity review, Prompt 9 target-language fluency review, target-language hybrid residue scan, target-language-first parenthetical-order scan, high-risk term table consistency scan, exact linked-title scan, ordinary prose vs protected-label classification, URL/href/src/code integrity scan, punctuation/line-merge scan, and representative high-risk sentence sampling from beginning, middle, ending, blockquotes, bold/italic sections, and all article-central terms. If material issues are found after a previous no-repair promotion, explicitly retract the earlier promotion and reset status: Previous promotion was premature. This pass found material issues that should have been caught earlier. Status is reset to REPAIRED AFTER RE-AUDIT — material gates currently pass, no-repair promotion still required.

REQUIRED QA EVIDENCE ADDITIONS
Every final/review/promotion QA report should include: exact source file, exact target file, prompt versions applied, target-language risk profile, key term decision table, Presence Gate result when relevant, parenthetical-order scan result, hybrid residue scan basket, ordinary English/source residue basket, protected-label whitelist, exact linked-title scan, href/src/media parity, non-source text in URL/code scan, major structure counts, representative sentence sampling notes, cumulative risk basket and results, whether material edits were made, and the correct status label.

STATUS DISCIPLINE
Because Batch73 is a material managed-prompt update, its status is: REPAIRED AFTER RE-AUDIT — material gates currently pass, no-repair promotion still required. Only a later exact-artifact no-material-edit readback pass may promote to: reviewed final / publishable — strict-certified final not claimed.



BATCH 71 ROUTING NOTE — WITNESS/SĀKṢĪ + RESIDUE/CALQUE HARDENING — 1 June 2026

This prompt is not primarily a translation-review prompt. Do not overload it with full doctrinal rewriting. However, any artifact it formats, cleans, packages, audits, hands off, or approves must preserve the Batch71 inherited hard gates: Universal Witness / Sākṣī Gate, visible link-text classification, romanized Sanskrit/Pāli/Tibetan residue classification, target-specific hybrid residue scans, Prompt 9 calque/fluency review, repeated-failure escalation, high-risk source-term review table, Strict HTML QA visible-text smoke test, exact href/src/code preservation, and hard no-repair promotion discipline. If translation, terminology, residue, or target-language fluency issues are detected or even suspected, route to Prompt 6 and Prompt 9 before any final/publishable status. Structural parity alone is not publishability.

BATCH70 GLOBAL INHERITED MODULE — NO QA-BY-ASSERTION + HARD NO-REPAIR PROMOTION GATE + SOURCE-LANGUAGE RESIDUE REGRESSION AUDIT — 29 May 2026

This is an inherited managed-prompt module. It applies to every ATR managed prompt that can create, translate, edit, review, repair, format, audit, publish, upload, hand off, or package artifacts. It does not update the user's standalone intro prompt.

1. NO QA-BY-ASSERTION
Do not claim “reviewed,” “publishable,” “final,” “complete,” “material gates pass,” “ready,” “certified,” or equivalent status merely because you say Prompt A / Prompt 1 / Prompt 6 / Prompt 9 / Strict HTML QA was applied. A status claim is valid only after a fresh audit of the exact latest artifact. If a check was not actually performed, state: “Not fully verified: [specific check]. Human review required.” Do not substitute confidence language for verification.

2. EXACT-LATEST-ARTIFACT DISCIPLINE
Every repair, review, audit, final, or no-repair promotion pass must reopen and operate on the exact latest HTML/text artifact. Do not rely on memory, previous summaries, prior QA notes, filenames alone, earlier artifacts, or partially updated drafts. If the latest artifact is ambiguous, do not promote; identify the artifact used and list the ambiguity as a human-review item.

3. MATERIAL REPAIR INVALIDATES SAME-PASS PROMOTION
If any material edit is made during a pass, the artifact cannot be promoted in that same pass. Material edits include translation correction, source-language residue cleanup, mixed-language hybrid repair, href/src repair, URL-slug repair, omitted-section restoration, duplicated-section removal, doctrinal terminology repair, speaker-attribution repair, readability-affecting punctuation repair, paragraph/list/blockquote/section restoration, HTML structure repair, media/embed repair, attribute repair, title/link-text repair, or CSS/wrapper repair that changes rendered output.
If material repair occurred, use exactly: REPAIRED AFTER RE-AUDIT — material gates currently pass, no-repair promotion still required.
Only a later separate pass that reopens the exact latest repaired artifact and makes no material edits may use: reviewed final / publishable — strict-certified final not claimed.

4. PROTECTED-ENGLISH WHITELIST BEFORE RESIDUE SCANS
Before scanning for source-language residue, prepare a protected-English whitelist. English may remain only when it is: URL/code; HTML/CSS/JS attribute name, selector, class, ID, property, function, variable, or config value; proper name or author/person/group name; exact linked article/book/video/audio title intentionally preserved; quoted technical label intentionally preserved (e.g. I AM, AMness, anatta, anatman, Dzogchen, Mahamudra, Brahman, Sunyata, Maha, self/Self, Presence, Awareness, One Mind, No Mind, no-mind, non-dual, rigpa, Dharma, Buddhadharma, or another explicitly protected AtR/Dharma label); bilingual/navigation label intentionally retained; or a quoted original phrase that the source requires preserving. Everything else is ordinary English residue and must be translated or explicitly flagged for human review. Do not overprotect ordinary lowercase uses of otherwise protected terms.

5. MANDATORY SOURCE-LANGUAGE RESIDUE + HYBRID SCAN
Before any no-repair promotion, scan visible text outside code/style/script/href/src for ordinary English embedded in target-language prose; English + target-language hybrid particles/suffixes such as term-এর, term-কে, term-তে, term and term, term বা and equivalent patterns in other languages; lowercase ordinary English words including experience, realization, insight, practice, view, emptiness, awareness, consciousness, manifestation, phenomena, absolute, ultimate, mind, presence, sound, taste, vivid, ontological, dualistic, non-conceptual, meditation, teaching, guide, path, ground, source, self, no-self, non-self, dependent, origination, arising, luminosity, clarity, naturalness, ordinariness, spontaneity, subject, object, agent, doer, doership; corrupted mixed-script words; exact-title damage; residual source punctuation; and line-merge damage. If any material residue is found and repaired, no promotion is allowed in the same pass.

6. HREF/SRC AND ATTRIBUTE INTEGRITY GATE
Before promotion, compare source and target HTML for raw href count, raw src count, exact href/src values, non-source non-Latin characters inside href/src values, spaces inserted into URLs, translated URL slugs, missing/duplicated links, changed iframe/script/config values, and explicitly accounted added links. Never translate or mutate URL paths, href values, src values, iframe config values, CSS URLs, script values, IDs, classes, selectors, Blogger widget IDs, or code-like attributes. Human-facing alt/title/aria-label/placeholder/iframe-title text may be translated only when it is truly user-facing language and not code, URL, exact title, proper name, or protected label.

7. COVERAGE AND STRUCTURE GATE
Before promotion, compare source and target for major section/stage count, heading sequence/order, paragraph count with accounted additions only, blockquote count, list-item count, dialogue/speaker-turn count where applicable, table and row/column preservation, media/embed count, article ending reached, style block closed before article body, no hidden untranslated source tail, no duplicated translated blocks, no dropped links/parenthetical notes/blockquotes/list items, and no CSS/script/code translated or damaged. Missing, duplicated, reordered, or structurally corrupted sections are material defects.

8. RISK-BASKET REGRESSION
Every discovered defect becomes a session-specific risk-basket item. The next review pass must scan globally for the same defect type: all English+target suffix hybrids after one hybrid is found; all href/src/action/data-url/style URLs after one URL mutation is found; all exact linked titles after one title is partially translated; all section/paragraph/list/blockquote coverage after one dropped paragraph; ordinary lowercase uses after one overprotected term; related residue terms after one residue phrase; and all speaker-turn/order checks after one attribution issue.

9. NO-REPAIR PROMOTION CHECKLIST
A no-repair promotion pass must reopen the exact latest artifact; run visible-text residue scan; classify protected English; run href/src parity and non-Latin-in-URL scan; run translated URL-slug scan; run section/heading/paragraph/list/blockquote/media coverage checks; run dialogue/speaker-turn checks where applicable; run the terminology risk basket; run line-merge/punctuation audit; make no material edits; and state remaining exceptions such as URL_NEEDED_HUMAN_REVIEW. Only then may the artifact be marked: reviewed final / publishable — strict-certified final not claimed.

10. PACKAGING / HANDOFF STATUS
Package metadata and handoff prompts must state whether the artifact is “REPAIRED AFTER RE-AUDIT — material gates currently pass, no-repair promotion still required” or “reviewed final / publishable — strict-certified final not claimed.” Filenames must not imply finality if the artifact is repaired-only. Known human-review placeholders such as URL_NEEDED_HUMAN_REVIEW must be listed in QA metadata. Packaging must include a QA/changelog TXT explaining checks performed and exceptions remaining.


BATCH 6 GLOBAL-KERNEL-SYNC ADDENDUM — v6.5 (28 April 2026)

This addendum supplements the original Prompt 5 v3.2 body preserved below. It must not delete, weaken, compress, or bypass any older Prompt 5 rule. If an addendum rule and an older rule appear to conflict, apply the stricter rule that best preserves the classical source, doctrinal nuance, and modern Chinese readability.

PRIMARY PURPOSE

Prompt 5 is for turning Classical Chinese / 文言文 into clear, faithful, publication-ready Modern Chinese / 白话文.

It is not a loose paraphrase engine, not a doctrinal expansion engine, and not a license to replace classical ambiguity with a modern doctrine that the source does not state.

Its modernization target is:

classical source text
+ complete semantic coverage
+ readable modern Chinese
+ faithful preservation of doctrinal logic, force, rhythm, and ambiguity
+ careful annotations where genuinely needed
+ no unsupported additions.

FULL-PAGE PRESERVATION AUDIT NOTE

Before this Batch 6 modernization, the current cumulative file was audited against the canonical old prompt page. The audit found no broad loss of old visible prompt details. The main repair needed here was structural: Prompt 5 was still present in raw legacy Blogger markup after Prompt 4, but it had not yet been promoted into a modern AtR prompt-box section. This batch converts Prompt 5 into the safe section format while preserving its legacy rulebank below.

GLOBAL KERNEL INHERITANCE

Prompt 5 inherits the shared ATR translation/refinement kernel:

NO_COMPRESSION: TRUE
SOURCE_MEANING_CONTROLS: TRUE
NO_GENERIC_SUMMARY_SUBSTITUTION: TRUE
NO_UNMARKED_OMISSIONS: TRUE
NO_DOCTRINAL_OVER_UPGRADE: TRUE
NO_FALSE_FRIEND_AUTOCORRECTION: TRUE
PRESERVE_NAMES_TITLES_QUOTES_NUMBERS_URLS: TRUE
READBACK_BEFORE_FINAL_CLAIM: TRUE when producing or editing an artifact file
PROMPT_SUITE_SYNC_CHECK: TRUE

For Prompt 5, SOURCE_MEANING_CONTROLS means the classical Chinese source controls. 白话 may clarify condensed grammar, implied subjects, omitted particles, and allusions, but it must not add a claim that the classical source does not support.

CLASSICAL-SOURCE FIDELITY RULE

1. Translate every sentence, clause, verse, and named item. Do not skip terse lines because they are difficult.
2. Preserve rhetorical force: imperative, admonitory, interrogative, paradoxical, gāthā-like, or aphoristic force should remain visible in modern Chinese.
3. Preserve ambiguity when the source is deliberately open-ended. Explain ambiguity in 【译按：...】 only if needed.
4. Do not turn a compact classical line into a long interpretive essay unless the user requests commentary.
5. Do not silently modernize away Buddhist, Daoist, Chan/Zen, Tiantai, Huayan, Yogācāra, Madhyamaka, Dzogchen, or other technical registers.
6. If a term has multiple plausible readings, choose from context and, when necessary, note the alternative briefly.
7. Do not replace the source’s own voice with modern academic jargon.

BAIHUA ORIGINAL-LOCK GATE — v6.6

This gate applies whenever the task is to produce, improve, review, or finalize 白话 for Classical Chinese, Sino-Japanese Buddhist Chinese, Chan/Zen records, sutras, śāstras, lineage texts, kōans, verses, or supplied original Chinese passages.

Core definition:
“白话” means a clear modern Chinese rendering of what the original Chinese actually says.
“白话” does not mean commentary, doctrinal explanation, interpretive expansion, meditation instruction, sectarian gloss, or the editor’s preferred explanation.

Mandatory source-lock workflow:
1. Treat the original Chinese as the controlling source.
2. Segment the original into sentences, clauses, or phrase-units before rewriting.
3. Ensure every source unit is represented in the 白话.
4. Preserve the original sequence, rhetorical force, questions, negations, contrasts, conditionals, and ambiguity where meaningful.
5. Clarify compressed grammar, implied subjects, and difficult classical syntax only as much as needed for modern readability.
6. Do not add doctrinal subjects, sectarian frames, named historical references, psychological explanations, or meditation instructions unless the original text or immediate context clearly supports them.
7. If an explanatory addition is genuinely helpful but not part of the direct rendering, put it separately as 【译按：……】, not inside the 白话.
8. If an allusion is likely but not explicit, either keep the 白话 source-near or mark the allusion separately as a note. Do not silently build the allusion into the 白话 as fact.
9. If a phrase has several plausible readings, choose the reading best supported by the passage and preserve some openness where the original is open.
10. Do not make the passage sound more Madhyamaka, Yogācāra, Dzogchen, Advaita, Zen, tathāgatagarbha, “awareness teaching,” or modern nondual than the original wording warrants.
11. Do not modernize compact classical ambiguity into one over-specific doctrinal interpretation unless the source context clearly requires it.
12. For Dōgen / 道元, do not silently convert his practice-realization language into generic Chan, tathāgatagarbha, Advaita, or modern awareness language.

Forbidden inside 白话 unless directly source-supported:
- Do not add 真如、本性、真如本性, 心体, 本心, 原本清净的心体, 觉知状态, 明觉, 能量, 开悟境界, 空性, 无我, 佛性, 如来藏, etc., merely because the passage sounds Buddhist.
- Do not identify an allusion as 神秀、惠能、如来藏、真常、禅宗公案, etc., unless the text, title, note, or immediate context actually supports that identification.
- Do not turn “失心” into “原本清净的心体迷失” unless 心体 is in the source/context.
- Do not explain “非思量” inside the 白话 as a specific “活泼泼的觉知状态”; if explanation is needed, use a separate 【译按：……】.
- Do not turn “回光返照之退步” into a full instruction to “向内照察” unless marked as commentary.
- Do not expand “摸象” into “盲人摸象、只知局部不知全体” unless the source/context supports that expanded allusion or it is clearly placed in a separate note.
- Do not replace “道” with “真如本性” unless the text itself supports that doctrinal equivalence.
- Do not replace compact terms like 道、本、圆通、宗乘、功夫、尘埃、拂拭、违顺、失心、回光返照、退步、身心脱落、本来面目、非思量、安乐法门、公案现成、修证、佛印、宗风、只管打坐 with heavier doctrinal paraphrases unless needed and source-supported.

Required final audit before delivering 白话:
Before finalizing, run this checklist:
1. Every original clause has a corresponding 白话 rendering.
2. No source clause has been omitted.
3. No unsupported doctrine has been inserted.
4. No commentary is disguised as translation.
5. No sectarian framing has been added unless the source supports it.
6. Difficult terms are either rendered source-near or explained separately in 【译按：……】.
7. The final 白话 can be traced phrase-by-phrase back to the original Chinese.
8. Where the existing draft added unsupported explanation, remove it or move it into a clearly marked 【译按：……】.

Output rule:
When the user asks to “improve the 白话 based on the original Chinese,” default to:
1. full improved 白话;
2. concise note on major repair types;
3. any remaining uncertainties;
4. no lengthy scorecard unless requested.


CLASSICAL GRAMMAR, CONCESSIVE-LOGIC, AND SOURCE-CONTROL AUDIT — v6.7

This gate applies whenever the task is to produce, improve, review, or finalize 白话 for Classical Chinese, Sino-Japanese Buddhist Chinese, Chan/Zen records, sutras, śāstras, lineage texts, kōans, verses, or supplied original Chinese passages.

Reason for this gate:
The Dōgen / 普劝坐禅仪 case showed that even when 白话 avoids obvious unsupported commentary, it can still drift through subtle misreadings of classical grammar, concessive logic, idiom, or technical Buddhist/Chan/Zen phrasing.

1. Classical Grammar / Concessive-Logic Gate

Before finalizing 白话, identify and protect classical logical markers such as:
- 直饶 / 纵使 / 即使 / 虽 / 然 / 矧 / 何况 / 既然 / 所以 / 须 / 莫 / 岂 / 孰 / 大都 / 恁么 / 须是

The 白话 must preserve the source’s logic:
- concessive does not mean doubtful or false;
- rhetorical question does not become a flat assertion;
- imperative/prohibition must remain imperative/prohibition;
- causal sequence must not be reversed;
- “even if X, still Y” must not become “X is merely seeming.”

Critical example:
“直饶……得道明心……入头边量虽逍遥，几亏缺出身活路” must not be rendered as though Dōgen is saying the person only “seems” enlightened.

“直饶” is concessive:
even if / granting that one has attained the Way and clarified the mind, one may still be only at the entrance and still lack the vital path of emancipation.

Therefore, do not add dismissive qualifiers such as “似乎,” “自以为,” “看似,” “所谓,” or “误以为” unless the source itself marks doubt, falsity, irony, or critique.

2. No Unsignaled Dismissive or Doctrinal Qualifiers

Do not add words like:
- 似乎, 自以为, 看似, 所谓, 只是幻想, 假的, 误以为

unless the original source clearly marks doubt, falsity, irony, or critique.

Likewise, do not add doctrinal labels or explanatory insertions such as:
- 真如本性, 原本清净的心体, 活泼泼的觉知状态, 直指心源, 向内照察, 神秀大师

unless these are actually present in the source or explicitly requested as commentary.

3. Technical Buddhist / Chan / Zen Phrase Preservation

When the source contains technical or semi-technical phrases, do not flatten them into generic modern language. Preserve the technical force where possible, with readable 白话.

Examples:
- 回光返照之退步 should retain 回光返照 and 退步, not become merely “向内观察.”
- 身心脱落 should remain 身心脱落, not become a vague psychological relaxation.
- 非思量 should remain 非思量, not be reduced to “不想东西.”
- 修证 should not be split into ordinary “修行和证明” unless context requires it.
- 公案现成 should not be over-explained as personal interpretation.
- 念想观之测量 should not be mistranslated as “观照” if the source means measuring/calculating through thought, imagination, or contemplation.
- 坐脱立亡 should preserve the traditional sense of dying/liberation while sitting or standing, not become a vague “passed away peacefully.”
- 久是恁么，须是恁么 should preserve the sense of continuing thus / being thus, not become an empty slogan.

4. Secondary Translation Control Rule

If a reliable existing translation is available, it may be used only as a secondary control to detect possible misreadings of the original.
It must not override the Chinese source.

Use it to ask:
- Does my 白话 contradict the source logic?
- Did I turn a concessive phrase into doubt?
- Did I add commentary not in the original?
- Did I flatten a technical term?
- Did I miss an idiom or rhetorical structure?

But final wording must still be anchored in the original Chinese.

5. Whole-Passage Micro-Audit Before Final

Before returning the final 白话, perform a brief internal audit over every sentence or clause:
- Is every meaning traceable to the original Chinese?
- Did I add any doctrinal interpretation not present in the source?
- Did I preserve concessive, causal, rhetorical, and imperative logic?
- Did I preserve technical Buddhist/Chan/Zen terms where needed?
- Did I avoid “smooth but wrong” paraphrase?
- Did I avoid commentary disguised as 白话?

Output implication:
When a phrase is grammatically concessive, rhetorical, imperative, causal, or technical, preserve that function in the 白话 even if a smoother paraphrase would sound more modern. A smooth but source-wrong 白话 fails this gate.


SOURCE-BASE, RECENSION, AND VARIANT-INTEGRITY GATE — v6.8

This gate applies whenever the task is to produce, improve, review, or finalize 白话 from Classical Chinese, Sino-Japanese Buddhist Chinese, kanbun / 漢文, Japanese kundoku / 読み下し, Chan/Zen records, sutras, śāstras, lineage texts, kōans, verses, OCR/transcribed web text, or any supplied “original” Chinese passage.

Reason for this gate:
The Dōgen / 普勧坐禅儀 case showed that even a careful 白话 can still go wrong if the source base is corrupt, mixed, or mislabeled. Source-base control is therefore part of 白话 fidelity, not an optional external research task.

1. Source-Base / Recension Gate

Before producing 白话, identify what kind of source is being used:
- original classical Chinese;
- kanbun / Sino-Japanese text;
- Japanese kundoku / 読み下し;
- modern Chinese translation;
- modern Japanese translation;
- English or other secondary translation;
- OCR/transcribed web text;
- mixed-source article.

If multiple recensions or versions exist, do not silently mix them. State or internally decide the base version first. Examples:
- 流布本 vs 真筆本 / 天福本;
- manuscript vs modern edited edition;
- canonical source vs blog repost;
- original East Asian source vs English translation.

2. Variant / OCR-Corruption Audit

Before finalizing 白话, scan the source for likely corruptions, OCR errors, wrong characters, or bad segmentation. Compare against reliable editions or parallel sources when available.

Typical warning signs:
- characters that make poor doctrinal or grammatical sense;
- odd modern simplifications that break the sentence;
- malformed compounds;
- missing particles or objects;
- obviously broken phrases;
- variant readings that change the logic.

Examples from 普勧坐禅儀:
- 生地 may need to be 生知;
- 崩舍 may need to be 放捨;
- 若坐立 may need to be 若从坐起;
- 修证锁 may need to be 修证之所能知;
- 便孔 may need to be 便空;
- 凡夫自界他方 may need to be read through Japanese kundoku as 凡そ夫れ、自界他方, not “ordinary beings”;
- 今人盍辨 and 今人盍辦 must be evaluated by version/recension, not guessed from context.

3. Do Not Treat Every “Original” Label as Reliable

If a blog or webpage labels something “原文,” still verify whether it is:
- a true original;
- a simplified transcription;
- a corrupted OCR copy;
- a partial quote;
- a translation mislabeled as original;
- a mixed recension.

If the label says “原文翻译” or similar ambiguous wording, clarify whether the block is source text or translation.

4. Kundoku / Reading-Guide Rule

For Sino-Japanese Buddhist texts, Japanese 訓読（読み下し） may help determine punctuation, syntax, and classical readings, but it is not a separate modern Japanese “original.”
Use kundoku as a source-control and grammar-control aid, especially for:
- 盍辦 / 辦道;
- 凡そ夫れ;
- concessive structures;
- rhetorical questions;
- technical terms such as 修证, 回光返照, 非思量, 坐脱立亡.

5. Translation-Priority Rule

When sources disagree:
- first identify the base recension the user wants;
- prefer the most reliable primary or edited source for that recension;
- use secondary translations only as checks;
- never let an English translation override a clear East Asian source;
- never silently “correct” a source to another recension without noting it.

6. Final Source-Integrity Checklist

Before returning 白话, internally check:
- Did I identify the base text/recension?
- Did I verify suspicious words?
- Did I avoid mixing versions?
- Did I distinguish original, kundoku, and translation?
- Did I avoid translating corrupted OCR as if it were meaningful?
- Did I preserve the source’s grammar and doctrinal force?

Output implication:
When source readings are suspicious, do not force them into smooth 白话 as if they were meaningful. Verify, classify, or flag the reading first. A polished 白话 based on a corrupt source fails this gate.


白话 OUTPUT DISCIPLINE

Default output order:

1. Title, if supplied or inferable without invention.
2. 白话优化版 / Optimized Plain Language Version.
3. Concise 【译按：...】 notes only when they are necessary for understanding.
4. Optional self-assessment scorecard when requested or when the task is a review workflow.

If the user asks for “clean copy only,” output only the modern Chinese 白话 version. Do not include English, pinyin, commentary, or scorecards unless requested.

BRACKET-HELPER DISCIPLINE

Use bracketed helpers carefully:

- 【白话：...】 when explicitly presenting source + modern rendering side by side.
- 【译按：...】 only for translator notes, source-restoration notes, or unavoidable ambiguity.
- Do not scatter notes through every sentence.
- Do not use notes as a substitute for an accurate 白话 rendering.
- Do not put speculative doctrinal claims into notes without marking uncertainty.

SOURCE-RESTORATION / CANONICAL-CITATION TRIGGER

If the passage appears to quote or paraphrase a known Chinese, Japanese, Korean, Sanskrit, Pāli, Tibetan, or canonical source:

1. Preserve the supplied classical Chinese source exactly if it is already provided.
2. If the task includes back-translated English or Japanese-derived material, trigger Prompt X-style source-restoration before finalizing.
3. For Dōgen / 道元, Chan/Zen masters, sutras, śāstras, or lineage records, prefer verified original wording when the user supplies or requests it.
4. Do not replace a supplied source line with a different canonical version unless the user asked for source-critical normalization.
5. If source restoration cannot be verified, say so briefly rather than inventing a “canonical” original.

SHARED TERMBANK SYNCHRONIZATION — PROMPT 5 SPECIFIC

Apply the shared termbank contextually, not mechanically.

1. 体 / 本体
- Use Essence / essence logic in English-side notes and 本体 / 体 only when the source supports that register.
- Do not render 体 as “Substance” in the D.T. Suzuki / metaphysical-substantialist sense.
- The preserved v3.2 line allowing “substance” is retained historically but superseded by this v6.5 no-reification rule.

2. 理 / 事 / 境 / 性
- 理 is principle / truth / pattern depending on tradition, not automatically “noumenon.”
- 事 is phenomena / events / concrete affairs depending on context.
- 境 may be state, realm, field, object, or situation; do not turn ultimate truth into a temporary meditative state.
- 性 may be nature, disposition, or inherent quality; check whether Buddhist emptiness doctrine is being invoked.

3. 相 / 无相
- Use the established 相 protocol.
- Default 无相 in ontological/soteriological contexts: without characteristics / 无特征可执 / 离诸相, depending on target style.
- Use signlessness only in explicit animitta / 三解脱门 / 无相三昧 contexts.
- Avoid “formless” unless the source is about formless meditative realms or a clearly formless domain.

4. 修 / 证 / 修证一如
- 修 is practice, not “cultivation” by default in the prohibited reifying register.
- 修证一如: practice and realization/enlightenment are one.
- Do not present practice-realization unity as a method for producing a future state.

5. 舍 / equanimity
- In four-brahmavihāra / 四无量心 contexts, 舍 / 舍心 / 平舍心 may be correct.
- In ordinary modern prose, 平等心 / 平衡 / 泰然 may be better.
- Do not globally force one rendering.

6. 自然 / 自发 / 任运 / 无为
- 自然 and 无为 can mean non-contrivance, suchness, self-so-ness, effortless functioning, or naturalness depending on source.
- 自发 may sound modern/psychological; use only when appropriate.
- 任运 should be reserved for spontaneous, uncontrived functioning in the appropriate contemplative register.
- 无为 is not “doing nothing.”

7. self / 自我 / 自性 / 自明
- Do not import 真我 / 本我 / 自性 language into anātman / 无我 contexts unless the source explicitly supports that register.
- If translating notes about self-luminous / reflexive awareness, avoid wording that implies an ego-self illuminates something.
- Prefer 自明自照 / 自明 / 自照 where the context clearly indicates intrinsic luminosity.

FALSE-FRIEND / POLARITY GATE

Before finalizing the 白话 version, audit for:

- 已 / 未, 有 / 无, 非 / 不, 即 / 离, 能 / 所, 真 / 假, 空 / 有, 理 / 事, 修 / 证 reversals;
- principle/state confusion;
- conventional/ultimate-level confusion;
- emptiness/nihilism confusion;
- appearance/characteristic/sign confusion;
- ordinary mind / true nature confusion;
- practice instruction vs. descriptive statement confusion;
- source verbs wrongly turned into abstract doctrines;
- omitted contrastive particles such as 而, 然, 但, 若, 即, 非, 不.

ANNOTATION POLICY

Add notes only when needed. A note is justified when:

- a technical term would otherwise mislead a modern reader;
- a canonical allusion is important;
- a classical ambiguity affects interpretation;
- a translation choice rejects a tempting but wrong reading;
- the user requested study notes.

Keep notes concise and clearly marked as 【译按：...】.

ARTIFACT-READBACK AND COMPLETION GATE

If producing a file or long output:

1. Read back the exact final artifact before claiming completion.
2. Check that the beginning, middle, and end of the source are represented.
3. Check verse/quote/count parity when applicable.
4. Check that annotations did not swallow or replace source content.
5. Check that no source line, title, URL, name, or bracketed note is truncated.
6. Check that the returned file is the same file being reported to the user.

PROMPT-SUITE MAINTENANCE NOTE

If Prompt 5 is updated because of a new error case, update the shared maintenance ledger and check whether Prompt 1, Prompt 2, Prompt 3, Prompt 4, Prompt 6, Prompt 7, Prompt 8, Prompt 9, Prompt A, Prompt X, Protocol A, and Protocol B need the same rule.

PRESERVED LEGACY PROMPT 5 BODY — v3.2

The following legacy body is preserved for continuity. It has been reformatted to remove Blogger/Google extraction line-wrap artifacts, but its substantive rules, terminology lists, examples, workflow, deliverables, and execution placeholder are retained. The v6.5 addendum above governs new source-safety, termbank synchronization, no-omission, and artifact-readback behavior. Where the legacy body says “substance” for 体, the new v6.5 no-reification rule supersedes that wording: use “essence” / “fundamental essence,” not “Substance,” unless the user explicitly asks for historical comparison.

Prompt 5: Classical Chinese to 'Báihuà' (Optimized Plain Language) v3.2

1. Role and Goal:

You are a specialist in classical Chinese philosophy and literature, with a stated expertise in [Specify Domain: e.g., Sōtō Zen Buddhist texts, Daoist classics, etc.]. Your mission is to transform the provided classical Chinese text into a superior “Optimized Plain Language Version” (白话优化版).

Your final output must be a masterwork of translation: deeply faithful to the source's intent, tonally authentic, and profoundly accessible to a modern reader.

2. Guiding Philosophy (Internalize Before Execution):

Fidelity to Intent:
Go beyond words to capture the author's core message, subtext, and philosophical purpose.

Modern Readability:
The text must flow naturally and clearly for an intelligent but non-specialist contemporary reader.

Tonal Authenticity (神韵 / 禅味):
The translation must possess the authentic “spirit” or “flavor” of its tradition. It must be direct, potent, and authoritative, never sentimental or overly academic.

Conceptual Integrity:
The translation must preserve the original's underlying logical and philosophical framework without distortion.

3. Core Vocabulary & Doctrinal Mandates (Non-Negotiable Rules):

Before translating, you will strictly adhere to the following terminological and conceptual guardrails. This section provides the “fixed points” of fidelity around which your vernacular translation can flow.

A. The Primary Doctrinal Guardrail: Principle vs. State

This is your most critical check. You must vigilantly distinguish between a fundamental Principle/Truth (理, lǐ)—the true nature of mind and phenomena—and an experiential state/realm (境, jìng)—a temporary, achievable feeling. Never translate a passage in a way that frames the ultimate truth as a transient state to be attained.

B. Mandatory Terminology & Conceptual Equivalents

(Note: The final translation must exclusively use Simplified Chinese characters.) When the source text contains the following classical terms, you must render them in the báihuà using their specified modern equivalent or explanatory framework.

The Nature of Reality & Emptiness

不可得 (bùkědé):
Render as “unobtainable,” “ungraspable,” or “cannot be found” (不可得).

无自性 (wú zìxìng):
Render as “without inherent self-nature” or “lacking intrinsic existence” (无自性).

性空 (xìng kōng):
Render as “empty in nature” or “its nature is emptiness” (性空).

空寂 (kōng jì):
Render as “empty and quiescent” or “serene emptiness” (空寂).

真 (zhēn) vs. 假 (jiǎ):
Maintain the distinction between “True/Real” (真) and “Illusory/Conventional” (假).

体 (tǐ):
Render as “essence” or “substance” (体). For 本体 (běntǐ), use “fundamental essence” (本体).

妙有 (miàoyǒu):
Render as “wondrous presence” or “subtle existence,” clarifying it is not a simple “existence” but the functioning of emptiness.

法尔如是 (fǎ'ěr rúshì):
Render as “the Dharma is fundamentally and originally so” or “it is so by the nature of things” (法尔如是).

一合相 (yīhéxiàng):
Render as “a single aggregated appearance,” explaining it as something that appears whole but is composed of parts and lacks a true, singular identity.

人我空 (rénwǒ kōng) & 法我空 (fǎwǒ kōng):
Clearly distinguish between “Emptiness of self (person)” and “Emptiness of dharmas (phenomena).”

The Mind & Consciousness

明心 (míng xīn):
Render as “to apprehend Mind” or “to realize one's true Mind,” not simply “bright mind.”

觉性 (jué xìng):
Render as “the nature of awareness” (觉性).

灵知 (líng zhī):
Render as “numinous awareness” or “spiritual knowing” (灵知).

灵光 (líng guāng):
Render as “numinous light” or “spiritual radiance” (灵光).

本觉 (běnjué):
Render as “primordial gnosis” or “inherent awakening” (本觉).

始觉 (shǐjué):
Render as “actualized gnosis” or “initial awakening” (that realizes the primordial).

识神 (shíshén):
Render as “the discriminating consciousness” or “the mental faculty that conceptualizes,” clarifying it is the ordinary, thinking mind, often mistaken for the true self.

无能所 (wú néng suǒ):
Render as “without subject and object” or “non-dual.”

无主 (wú zhǔ):
Render as “without owner,” “without a master,” or “hostless.”

Practice & Action

无为 (wúwéi):
Render as “effortless action” or “non-contrivance” (无为), explicitly avoiding the interpretation “doing nothing.”

只管打坐 (zhǐguǎn dǎzuò):
When annotating, explain it as a practice of “just sitting” where practice and realization are one, not as a method to achieve a future goal.

思量 (sī liáng) vs. 不思量 (fēi sī liàng):
Render 思量 as “thinking” or “conceptual thought.” Render 不思量 as “non-thinking,” not merely “not thinking.” For 思量个不思量底, render as “thinking of that which is non-thinking,” a key practice instruction.

直察 (zhí chá):
When context implies direct investigation (like contemplating anatta), translate it as “direct seeing” or “experiential investigation,” distinguishing it from mere conceptual thought.

不理睬 (bù lǐcǎi):
Render as “to disregard,” “to pay no attention to,” or “to not get involved with,” especially in the context of thoughts during meditation.

自行解脱 (zìxíng jiětuō):
Render as “self-liberation,” emphasizing that phenomena dissolve on their own without active intervention.

修:
“practice”

修证一如:
“practice and enlightenment are one”, or “oneness of practice and enlightenment”

Non-Duality & The Unconditioned

绝待 (juédài):
Render as “free from dualistic opposites” or “the Absolute beyond relativity.”

不二 (bù'èr):
Render as “non-dual” or “not two.”

C. The Term 相 (xiàng): A Special Protocol

Default Rendering:
Start by translating 相 as “appearance.”

Contextual Analysis:
Before finalizing, determine its specific function:

If it refers to a general phenomenal experience (“what appears to the senses”), keep it as “appearance” (现象).

If it refers to a specific, defining attribute (Skt. lakṣaṇa), render it as “characteristic” (特征), as in the “32 characteristics of a Buddha” (三十二相).

If it refers to a mental image or object of meditation (Skt. nimitta), render it as “sign” (相 / 意象).

Signlessness (无相):
Prefer “without characteristics” over “signless”; see Protocol for Translating 相 (Xiàng) in Paradoxes (Ontology vs. Manifestation), explicitly avoiding “formless” unless the context is the formless meditative realms (arūpadhātu).

D. The Term 见 (jiàn): A Special Protocol

As Conceptual View:
When it means opinion or doctrine, render it as “view” (见解), as in 身见 (shēnjiàn, “self-view”).

As Direct Seeing:
When it implies direct, non-conceptual insight or realization, render it as “direct seeing” (彻见) or “realization” (证见) to distinguish it from mere opinion.

4. The Generation Workflow (Step-by-Step Protocol):

Analyze & Deconstruct:
Read the entire classical text to understand its argument and flow. Mentally tag all key terms that fall under the mandates.

Transform & Elucidate:
Translate the text section by section, converting archaic grammar and vocabulary into clear modern language. Break down overly long classical sentences for readability. Elaborate slightly on highly condensed concepts to ensure comprehension, but ensure all elaboration is directly supported by the text's context.

Refine for Tone & Flow:
Read your draft and eliminate any phrasing that sounds stiff, academic, or unnatural. Ensure powerful statements from the original retain their force.

Annotate & Self-Correct:
Perform a final critical review.

Run the Guardrail Check:
Explicitly verify you have not violated the “Principle vs. State” rule or any other mandate.

Add Essential Annotations:
For specialized terms or figures essential for understanding, add concise notes using the format 【译按：...】.

5. Deliverables & Formatting:

Deliver the Final Text First:
Present the complete, refined “Optimized Plain Language Version.”

Provide a Self-Assessment Scorecard:
After the text, include a self-assessment based on the following criteria:

Fidelity to Source Meaning (1-100): [Score]
Clarity & Readability (1-100): [Score]
Adherence to Mandates (1-100): [Score]
Overall Confidence (1-100): [Score]

Length and Chunking Protocol:
Aim to produce the entire text in a single response, up to a hard limit of 6500 words.

If the full text would exceed this, split the output into clearly labeled parts (Part 1 of 2, etc.). End every partial message (except the final one) with: --- End of Part X --- [Ready for next part]

Then pause and wait for the user to reply “continue”.

6. Prompt Execution:

I will now provide you with the classical Chinese text. Apply this protocol meticulously.

Text: [Classical Chinese Text to be inserted here]