[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WJWQC0CTFQWQKQ2EZYXVGJ":3,"skill-same:01M6WJWQC0CTFQWQKQ2EZYXVGJ":89},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6WJWQC0CTFQWQKQ2EZYXVGJ","oma-academic-writer",null,"Academic writing specialist for publication-grade English prose. Drafts, revises, and audits essays, reports, analysis sections, executive summaries, conclusions, and literature reviews while enforcing sentence-structure variation, high-frequency academic verbs, calibrated hedging, and anti-AI stylistic compliance. USE for academic writing, essay polish, paragraph rewrite, prose revision against any rubric tier (HD\u002FD\u002FC, A\u002FB\u002FC, top-band\u002Fmid-band, etc.), anti-AI audit, reverse outlining, claim-evidence mapping, and rubric enforcement on assignments.","mrmarbury\u002FPalmSync4Mac","mrmarbury","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F114311?v=4","01M6BYSN920J8AMQ0W6HGSBH60","Stefan Marbury","01M6BYSNDEACDBNBPNRNCVYAPJ",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-academic-writing\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"Academic","academic writer","writer","oma academic writer","polish","reports","ai audit","analysis","claim","structure","writing","Anti-AI","english","literature","essays","essay","reviews","drafts","top","audit","2026-11-10 10:12:30",false,"---\nname: oma-academic-writer\ndescription: >\n  Academic writing specialist for publication-grade English prose. Drafts, revises, and\n  audits essays, reports, analysis sections, executive summaries, conclusions, and\n  literature reviews while enforcing sentence-structure variation, high-frequency\n  academic verbs, calibrated hedging, and anti-AI stylistic compliance. USE for\n  academic writing, essay polish, paragraph rewrite, prose revision against any\n  rubric tier (HD\u002FD\u002FC, A\u002FB\u002FC, top-band\u002Fmid-band, etc.), anti-AI audit, reverse\n  outlining, claim-evidence mapping, and rubric enforcement on assignments.\n---\n\n# Academic Writer: Publication-Grade English Prose Specialist\n\n## Scheduling\n\n### Goal\nProduce, revise, and audit publication-grade academic English prose so that every output simultaneously satisfies the Sentence Structure Protocol, Verb Protocol, Hedging Protocol, and Anti-AI Compliance Checklist, with every claim mapped to verifiable evidence.\n\n### Intent signature\n- \"draft this essay \u002F report \u002F executive summary \u002F conclusion \u002F literature review\"\n- \"rewrite this paragraph in academic English\"\n- \"polish this draft to top-band quality\" \u002F \"revise to match the rubric\"\n- \"run an anti-AI audit on this prose\"\n- \"check sentence structure variety\" \u002F \"fix monotonous rhythm\"\n- \"the prose sounds AI-generated, make it pass\"\n- \"verify claims against evidence\" \u002F \"reverse outline this section\"\n\n### When to use\n- Drafting or revising academic reports, essays, or analysis sections\n- Writing executive summaries, conclusions, or literature reviews\n- Rewriting AI-sounding prose into natural academic English\n- Polishing draft text to achieve top-band rubric quality (HD, A, top-band, etc.)\n- Reviewing prose for sentence variety, verb quality, hedging, and anti-AI compliance\n- Any task requiring formal academic English output bound by a rubric\n\n### When NOT to use\n- Translation tasks → use `oma-translator`\n- Source discovery, citation gathering, or scholarly literature search → use `oma-scholar`\n- Rubric \u002F assignment-spec parsing and task decomposition → use `oma-pm`\n- Code documentation, README, or API reference text → use the relevant domain skill (`oma-frontend`, `oma-backend`, `oma-mobile`, `oma-db`, etc.)\n- Informal communication, chat, or marketing copy → no skill needed\n- Non-English academic writing → call `oma-translator` for the target language after drafting in English\n\n### Expected inputs\n- `mode`: one of `draft` | `revise` | `review`\n- `rubric_or_constraint`: assignment brief, rubric file, or word\u002Fstructure limits (path or inline text)\n- `existing_draft`: prior text to revise or audit (path or inline text); required for `revise` and `review`\n- `source_data`: available evidence, figures, citations the writer may use\n- `target_register`: defaults to formal academic English with American spelling (en-US)\n\n### Expected outputs\n- `draft` mode: section heading + drafted prose + Writing Notes (sentence mix, key verbs, anti-AI flags resolved, paragraph lengths) + Claim-Evidence Map\n- `revise` mode: original block, revised block, list of specific changes (verb upgrades, structure variation, anti-AI fixes)\n- `review` mode: PASS\u002FFAIL Compliance Report across Sentence Structure, Verb Quality, Anti-AI, Specificity, Hedging, Paragraph Clarity, Rhythm\u002FBurstiness, Claim-Evidence Alignment, plus recommended fixes\n\n### Dependencies\n- `resources\u002Fanti-ai-checklist.md`: banned vocabulary, banned structural patterns, sentence-level checks\n- `resources\u002Fsentence-structure-reference.md`: four sentence types, length targets, common errors\n- `resources\u002Facademic-verb-tiers.md`: banned generic verbs and tiered academic-corpus replacements\n- `resources\u002Fhedging-guide.md`: calibrated certainty expressions matched to evidence strength\n- `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`: task-relevant resource loading\n- `..\u002F_shared\u002Fcore\u002Fquality-principles.md`: shared quality bar\n\n### Control-flow features\n- Mode branching: `draft` vs `revise` vs `review` produce different output formats and pass sequences\n- Rubric-quote gate: refuses to apply a rule until the literal constraint text is quoted from the source\n- Citation gap branch: when a claim lacks evidence, weaken or remove rather than fabricate; optionally hand off to `oma-scholar`\n- Language branch: non-English target hands off to `oma-translator` after the English pass\n- Iterative AUDIT: every fix loops back through the anti-AI checklist before emit\n\n## Structural Flow\n\n### Entry\n1. Identify the mode (`draft`, `revise`, `review`) and the rubric source.\n2. Quote the exact constraint text (word limits, structural requirements, mandatory sections, rubric rows) before applying any rule.\n3. If revising or reviewing, read the existing draft in full first; if drafting, confirm available source data and citations.\n4. Index `resources\u002F` and pre-select the verb tier and sentence mix targets for the section.\n\n### Scenes\n1. **PREPARE**: load rubric, existing draft, source data; record quoted constraints; pick sentence mix and 2–3 anchor verbs per paragraph.\n2. **ACQUIRE**: read `resources\u002Fsentence-structure-reference.md`, `academic-verb-tiers.md`, and `hedging-guide.md` only for the patterns relevant to the current section.\n3. **ACT**: write or revise prose with the four protocols enforced simultaneously: Sentence Structure (4 types, varied length, varied openers), Verb (no banned generic verbs as main verbs; prefer tier-1\u002F2 academic verbs), Hedging (match strength to evidence), and Topic-Support-Conclude paragraphing.\n4. **VERIFY**: audit against `resources\u002Fanti-ai-checklist.md` (vocabulary clusters, structural patterns, sentence-level checks); apply reverse outlining and build the Claim-Evidence Map; weaken or remove unsupported claims.\n5. **FINALIZE**: read-aloud test, cohesion check, specificity audit, word-count verification, paragraph-length variation, rhythm check; emit per the mode's output format.\n\n### Transitions\n- If a rubric line is ambiguous → quote it back to the user and ask for interpretation; do not infer combined rules.\n- If a claim cannot be supported by available evidence → weaken with hedging or remove; if a citation gap is structural, NOTIFY `oma-scholar`.\n- If the target language is non-English → finish the English pass, then hand off to `oma-translator`.\n- If the same anti-AI flag survives one fix attempt → restructure the surrounding two sentences instead of word-substitution alone.\n- If an output mode mismatch is detected (e.g., user asked for review but supplied a fresh prompt) → confirm the mode before producing output.\n\n### Failure and recovery\n| Failure | Recovery |\n|---------|----------|\n| Word count over \u002F under target | Cut filler adverbs and redundant qualifiers, or expand with supporting evidence; re-run audit |\n| Prose still sounds AI-generated after one pass | Vary sentence openers (subject, adverbial, participial, prepositional) and insert one short (≤10-word) sentence per paragraph; re-run audit |\n| Rubric requirement unclear | Quote exact rubric text and ask user; do not combine rules |\n| Claim lacks evidence | Add citation, hedge to match weaker evidence, or remove the claim entirely |\n| Hedging miscalibrated | Replace double hedges; align hedge strength with `resources\u002Fhedging-guide.md` evidence-level table |\n| Banned generic verb resists replacement | Restructure the sentence so the banned verb is not the main verb |\n| Paragraph blocks are uniform 4–5 sentences | Insert a 2-sentence emphasis paragraph; re-run rhythm check |\n\n### Exit\n- Success: every protocol PASSes, the Claim-Evidence Map has no unsupported entries, word count complies, and the mode-specific output format is fully populated.\n- Partial success: emit prose with explicit `needs evidence` \u002F `pending citation` markers and report which protocol items remain at risk; flag handoff candidates.\n- Failure: refuse to emit and report the blocking ambiguity (rubric quote missing, source data absent, contradictory constraints).\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Read rubric \u002F constraint and quote literal text | `READ` | Rubric file or assignment brief |\n| Read existing draft (revise\u002Freview modes) | `READ` | Draft file or inline text |\n| Index resources for the current section | `READ` | `resources\u002F{anti-ai-checklist,sentence-structure-reference,academic-verb-tiers,hedging-guide}.md` |\n| Select sentence mix and 2–3 anchor verbs per paragraph | `SELECT` | Sentence-structure & verb-tier tables |\n| Plan paragraph as Topic-Support-Conclude | `INFER` | Outline notes |\n| Draft \u002F revise prose under all four protocols | `WRITE` | Generated prose |\n| Audit prose against anti-AI checklist | `VALIDATE` | `resources\u002Fanti-ai-checklist.md` |\n| Reverse outline + build Claim-Evidence Map | `VALIDATE` | Mapping table |\n| Weaken or remove unsupported claims | `WRITE` | Revised claim line |\n| Compare original vs revised (revise mode) | `COMPARE` | Diff block |\n| Hand off non-English target | `NOTIFY` | `oma-translator` |\n| Hand off citation gap | `NOTIFY` | `oma-scholar` |\n| Hand off ambiguous rubric \u002F spec | `NOTIFY` | `oma-pm` |\n| Emit per mode output format | `WRITE` | Final artifact |\n| Report compliance status | `NOTIFY` | PASS\u002FFAIL summary or Writing Notes block |\n\n### Tools and instruments\n- `Read` \u002F `Edit` \u002F `Write` for draft and rubric files\n- `resources\u002Fanti-ai-checklist.md`, `sentence-structure-reference.md`, `academic-verb-tiers.md`, `hedging-guide.md`\n- Topic-Support-Conclude paragraph template (inline)\n- Claim-Evidence Map (inline 3-column table: Claim \u002F Evidence \u002F Status)\n- Output-format blocks per mode (Draft \u002F Revision \u002F Review)\n\n### Canonical workflow path\n1. **READ** rubric\u002Fdraft and quote the exact literal constraint text; pin word limits, mandatory sections, and rubric rows.\n2. **PLAN** each paragraph as Topic-Support-Conclude; pre-select the sentence-type mix and 2–3 anchor verbs from `academic-verb-tiers.md`.\n3. **DRAFT** prose with Sentence Structure, Verb, Hedging, and Topic-Support-Conclude protocols enforced simultaneously.\n4. **AUDIT** the draft against `resources\u002Fanti-ai-checklist.md` (banned vocabulary clusters, banned structural patterns, sentence-level checks) and fix every flag.\n5. **REVERSE-OUTLINE** the section and build the Claim-Evidence Map; weaken or remove any unsupported claim.\n6. **POLISH** with read-aloud, cohesion, specificity, word-count, rhythm, and paragraph-length-variation checks; emit in the mode's output format.\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `LOCAL_FS` | Rubric, existing draft, generated prose output |\n| `CODEBASE` | `resources\u002F` 4 reference files, `_shared\u002Fcore\u002F{context-loading,quality-principles}.md` |\n| `MEMORY` | Mode, quoted constraints, anchor verbs per paragraph, anti-AI flags resolved, Claim-Evidence Map |\n\n### Preconditions\n- A rubric \u002F constraint or an existing draft (or both) is provided.\n- The target register is academic English. If the final deliverable is non-English, the user has agreed to a downstream `oma-translator` handoff.\n- The source data needed to support claims is available, or unsupported claims are explicitly allowed to be weakened or removed.\n\n### Effects and side effects\n- Writes drafted, revised, or reviewed prose to the user's working location (file or inline).\n- Does not modify `resources\u002F` reference files.\n- Does not fetch external citations; defers to `oma-scholar` when discovery is required.\n- May NOTIFY adjacent skills but does not auto-spawn them; user or workflow drives the actual handoff.\n\n### Guardrails\n1. Every sentence must be verifiable; never fabricate data, statistics, or citations.\n2. Quote-before-judgment: cite the literal constraint or rubric text before applying any rule.\n3. Never combine distinct rules to invent a new constraint; apply rules exactly as written.\n4. Banned generic verbs (`show`, `have`, `make`, `do`, `get`, `use`, `give`, `say`, `put`, `see`, `come`, `go`, `take`, `find`, `know`, `think`, `want`, `try`, `need`, `seem`, `become`, `keep`, `help`, `start`, `turn`, `bring`, `run`, `hold`, `set`) must not appear as main verbs; replace per `academic-verb-tiers.md`. Exception: natural copular\u002Fpossessive `is`\u002F`are`\u002F`has` are allowed and preferred over inflated substitutes (anti-AI checklist §4).\n5. Never place 3+ sentences of the same structural type consecutively; vary length (short 8–15, medium 16–25, long 26–40 words) and openers.\n6. Match hedge strength to evidence strength per `hedging-guide.md`; never use absolute claim words (`definitely`, `clearly`, `obviously`) outside mathematical facts; never first-person `I think` \u002F `I believe`.\n7. Never cluster 3+ flagged AI-vocabulary items in a single paragraph; never insert promotional or inflated language; never append superficial `-ing` clauses for analysis.\n8. Em dashes ≤ 1 per paragraph; semicolons ≤ 2 per 1000 words; sentence-case headers; no didactic disclaimers (`It is important to note`) or summary phrases (`In summary`, `Overall`).\n9. Every claim must map to evidence in the Claim-Evidence Map; weaken or remove unsupported claims rather than emit them.\n10. Read aloud before emit; if a sentence does not flow naturally, restructure it.\n\n## References\n- Anti-AI checklist: `resources\u002Fanti-ai-checklist.md`\n- Sentence-structure reference: `resources\u002Fsentence-structure-reference.md`\n- Academic verb tiers: `resources\u002Facademic-verb-tiers.md`\n- Hedging guide: `resources\u002Fhedging-guide.md`\n- Shared context loading: `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`\n- Shared quality principles: `..\u002F_shared\u002Fcore\u002Fquality-principles.md`\n","# Academic Writer: Publication-Grade English Prose Specialist\n\n## Scheduling\n\n### Goal\nProduce, revise, and audit publication-grade academic English prose so that every output simultaneously satisfies the Sentence Structure Protocol, Verb Protocol, Hedging Protocol, and Anti-AI Compliance Checklist, with every claim mapped to verifiable evidence.\n\n### Intent signature\n- \"draft this essay \u002F report \u002F executive summary \u002F conclusion \u002F literature review\"\n- \"rewrite this paragraph in academic English\"\n- \"polish this draft to top-band quality\" \u002F \"revise to match the rubric\"\n- \"run an anti-AI audit on this prose\"\n- \"check sentence structure variety\" \u002F \"fix monotonous rhythm\"\n- \"the prose sounds AI-generated, make it pass\"\n- \"verify claims against evidence\" \u002F \"reverse outline this section\"\n\n### When to use\n- Drafting or revising academic reports, essays, or analysis sections\n- Writing executive summaries, conclusions, or literature reviews\n- Rewriting AI-sounding prose into natural academic English\n- Polishing draft text to achieve top-band rubric quality (HD, A, top-band, etc.)\n- Reviewing prose for sentence variety, verb quality, hedging, and anti-AI compliance\n- Any task requiring formal academic English output bound by a rubric\n\n### When NOT to use\n- Translation tasks → use `oma-translator`\n- Source discovery, citation gathering, or scholarly literature search → use `oma-scholar`\n- Rubric \u002F assignment-spec parsing and task decomposition → use `oma-pm`\n- Code documentation, README, or API reference text → use the relevant domain skill (`oma-frontend`, `oma-backend`, `oma-mobile`, `oma-db`, etc.)\n- Informal communication, chat, or marketing copy → no skill needed\n- Non-English academic writing → call `oma-translator` for the target language after drafting in English\n\n### Expected inputs\n- `mode`: one of `draft` | `revise` | `review`\n- `rubric_or_constraint`: assignment brief, rubric file, or word\u002Fstructure limits (path or inline text)\n- `existing_draft`: prior text to revise or audit (path or inline text); required for `revise` and `review`\n- `source_data`: available evidence, figures, citations the writer may use\n- `target_register`: defaults to formal academic English with American spelling (en-US)\n\n### Expected outputs\n- `draft` mode: section heading + drafted prose + Writing Notes (sentence mix, key verbs, anti-AI flags resolved, paragraph lengths) + Claim-Evidence Map\n- `revise` mode: original block, revised block, list of specific changes (verb upgrades, structure variation, anti-AI fixes)\n- `review` mode: PASS\u002FFAIL Compliance Report across Sentence Structure, Verb Quality, Anti-AI, Specificity, Hedging, Paragraph Clarity, Rhythm\u002FBurstiness, Claim-Evidence Alignment, plus recommended fixes\n\n### Dependencies\n- `resources\u002Fanti-ai-checklist.md`: banned vocabulary, banned structural patterns, sentence-level checks\n- `resources\u002Fsentence-structure-reference.md`: four sentence types, length targets, common errors\n- `resources\u002Facademic-verb-tiers.md`: banned generic verbs and tiered academic-corpus replacements\n- `resources\u002Fhedging-guide.md`: calibrated certainty expressions matched to evidence strength\n- `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`: task-relevant resource loading\n- `..\u002F_shared\u002Fcore\u002Fquality-principles.md`: shared quality bar\n\n### Control-flow features\n- Mode branching: `draft` vs `revise` vs `review` produce different output formats and pass sequences\n- Rubric-quote gate: refuses to apply a rule until the literal constraint text is quoted from the source\n- Citation gap branch: when a claim lacks evidence, weaken or remove rather than fabricate; optionally hand off to `oma-scholar`\n- Language branch: non-English target hands off to `oma-translator` after the English pass\n- Iterative AUDIT: every fix loops back through the anti-AI checklist before emit\n\n## Structural Flow\n\n### Entry\n1. Identify the mode (`draft`, `revise`, `review`) and the rubric source.\n2. Quote the exact constraint text (word limits, structural requirements, mandatory sections, rubric rows) before applying any rule.\n3. If revising or reviewing, read the existing draft in full first; if drafting, confirm available source data and citations.\n4. Index `resources\u002F` and pre-select the verb tier and sentence mix targets for the section.\n\n### Scenes\n1. **PREPARE**: load rubric, existing draft, source data; record quoted constraints; pick sentence mix and 2–3 anchor verbs per paragraph.\n2. **ACQUIRE**: read `resources\u002Fsentence-structure-reference.md`, `academic-verb-tiers.md`, and `hedging-guide.md` only for the patterns relevant to the current section.\n3. **ACT**: write or revise prose with the four protocols enforced simultaneously: Sentence Structure (4 types, varied length, varied openers), Verb (no banned generic verbs as main verbs; prefer tier-1\u002F2 academic verbs), Hedging (match strength to evidence), and Topic-Support-Conclude paragraphing.\n4. **VERIFY**: audit against `resources\u002Fanti-ai-checklist.md` (vocabulary clusters, structural patterns, sentence-level checks); apply reverse outlining and build the Claim-Evidence Map; weaken or remove unsupported claims.\n5. **FINALIZE**: read-aloud test, cohesion check, specificity audit, word-count verification, paragraph-length variation, rhythm check; emit per the mode's output format.\n\n### Transitions\n- If a rubric line is ambiguous → quote it back to the user and ask for interpretation; do not infer combined rules.\n- If a claim cannot be supported by available evidence → weaken with hedging or remove; if a citation gap is structural, NOTIFY `oma-scholar`.\n- If the target language is non-English → finish the English pass, then hand off to `oma-translator`.\n- If the same anti-AI flag survives one fix attempt → restructure the surrounding two sentences instead of word-substitution alone.\n- If an output mode mismatch is detected (e.g., user asked for review but supplied a fresh prompt) → confirm the mode before producing output.\n\n### Failure and recovery\n| Failure | Recovery |\n|---------|----------|\n| Word count over \u002F under target | Cut filler adverbs and redundant qualifiers, or expand with supporting evidence; re-run audit |\n| Prose still sounds AI-generated after one pass | Vary sentence openers (subject, adverbial, participial, prepositional) and insert one short (≤10-word) sentence per paragraph; re-run audit |\n| Rubric requirement unclear | Quote exact rubric text and ask user; do not combine rules |\n| Claim lacks evidence | Add citation, hedge to match weaker evidence, or remove the claim entirely |\n| Hedging miscalibrated | Replace double hedges; align hedge strength with `resources\u002Fhedging-guide.md` evidence-level table |\n| Banned generic verb resists replacement | Restructure the sentence so the banned verb is not the main verb |\n| Paragraph blocks are uniform 4–5 sentences | Insert a 2-sentence emphasis paragraph; re-run rhythm check |\n\n### Exit\n- Success: every protocol PASSes, the Claim-Evidence Map has no unsupported entries, word count complies, and the mode-specific output format is fully populated.\n- Partial success: emit prose with explicit `needs evidence` \u002F `pending citation` markers and report which protocol items remain at risk; flag handoff candidates.\n- Failure: refuse to emit and report the blocking ambiguity (rubric quote missing, source data absent, contradictory constraints).\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Read rubric \u002F constraint and quote literal text | `READ` | Rubric file or assignment brief |\n| Read existing draft (revise\u002Freview modes) | `READ` | Draft file or inline text |\n| Index resources for the current section | `READ` | `resources\u002F{anti-ai-checklist,sentence-structure-reference,academic-verb-tiers,hedging-guide}.md` |\n| Select sentence mix and 2–3 anchor verbs per paragraph | `SELECT` | Sentence-structure & verb-tier tables |\n| Plan paragraph as Topic-Support-Conclude | `INFER` | Outline notes |\n| Draft \u002F revise prose under all four protocols | `WRITE` | Generated prose |\n| Audit prose against anti-AI checklist | `VALIDATE` | `resources\u002Fanti-ai-checklist.md` |\n| Reverse outline + build Claim-Evidence Map | `VALIDATE` | Mapping table |\n| Weaken or remove unsupported claims | `WRITE` | Revised claim line |\n| Compare original vs revised (revise mode) | `COMPARE` | Diff block |\n| Hand off non-English target | `NOTIFY` | `oma-translator` |\n| Hand off citation gap | `NOTIFY` | `oma-scholar` |\n| Hand off ambiguous rubric \u002F spec | `NOTIFY` | `oma-pm` |\n| Emit per mode output format | `WRITE` | Final artifact |\n| Report compliance status | `NOTIFY` | PASS\u002FFAIL summary or Writing Notes block |\n\n### Tools and instruments\n- `Read` \u002F `Edit` \u002F `Write` for draft and rubric files\n- `resources\u002Fanti-ai-checklist.md`, `sentence-structure-reference.md`, `academic-verb-tiers.md`, `hedging-guide.md`\n- Topic-Support-Conclude paragraph template (inline)\n- Claim-Evidence Map (inline 3-column table: Claim \u002F Evidence \u002F Status)\n- Output-format blocks per mode (Draft \u002F Revision \u002F Review)\n\n### Canonical workflow path\n1. **READ** rubric\u002Fdraft and quote the exact literal constraint text; pin word limits, mandatory sections, and rubric rows.\n2. **PLAN** each paragraph as Topic-Support-Conclude; pre-select the sentence-type mix and 2–3 anchor verbs from `academic-verb-tiers.md`.\n3. **DRAFT** prose with Sentence Structure, Verb, Hedging, and Topic-Support-Conclude protocols enforced simultaneously.\n4. **AUDIT** the draft against `resources\u002Fanti-ai-checklist.md` (banned vocabulary clusters, banned structural patterns, sentence-level checks) and fix every flag.\n5. **REVERSE-OUTLINE** the section and build the Claim-Evidence Map; weaken or remove any unsupported claim.\n6. **POLISH** with read-aloud, cohesion, specificity, word-count, rhythm, and paragraph-length-variation checks; emit in the mode's output format.\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `LOCAL_FS` | Rubric, existing draft, generated prose output |\n| `CODEBASE` | `resources\u002F` 4 reference files, `_shared\u002Fcore\u002F{context-loading,quality-principles}.md` |\n| `MEMORY` | Mode, quoted constraints, anchor verbs per paragraph, anti-AI flags resolved, Claim-Evidence Map |\n\n### Preconditions\n- A rubric \u002F constraint or an existing draft (or both) is provided.\n- The target register is academic English. If the final deliverable is non-English, the user has agreed to a downstream `oma-translator` handoff.\n- The source data needed to support claims is available, or unsupported claims are explicitly allowed to be weakened or removed.\n\n### Effects and side effects\n- Writes drafted, revised, or reviewed prose to the user's working location (file or inline).\n- Does not modify `resources\u002F` reference files.\n- Does not fetch external citations; defers to `oma-scholar` when discovery is required.\n- May NOTIFY adjacent skills but does not auto-spawn them; user or workflow drives the actual handoff.\n\n### Guardrails\n1. Every sentence must be verifiable; never fabricate data, statistics, or citations.\n2. Quote-before-judgment: cite the literal constraint or rubric text before applying any rule.\n3. Never combine distinct rules to invent a new constraint; apply rules exactly as written.\n4. Banned generic verbs (`show`, `have`, `make`, `do`, `get`, `use`, `give`, `say`, `put`, `see`, `come`, `go`, `take`, `find`, `know`, `think`, `want`, `try`, `need`, `seem`, `become`, `keep`, `help`, `start`, `turn`, `bring`, `run`, `hold`, `set`) must not appear as main verbs; replace per `academic-verb-tiers.md`. Exception: natural copular\u002Fpossessive `is`\u002F`are`\u002F`has` are allowed and preferred over inflated substitutes (anti-AI checklist §4).\n5. Never place 3+ sentences of the same structural type consecutively; vary length (short 8–15, medium 16–25, long 26–40 words) and openers.\n6. Match hedge strength to evidence strength per `hedging-guide.md`; never use absolute claim words (`definitely`, `clearly`, `obviously`) outside mathematical facts; never first-person `I think` \u002F `I believe`.\n7. Never cluster 3+ flagged AI-vocabulary items in a single paragraph; never insert promotional or inflated language; never append superficial `-ing` clauses for analysis.\n8. Em dashes ≤ 1 per paragraph; semicolons ≤ 2 per 1000 words; sentence-case headers; no didactic disclaimers (`It is important to note`) or summary phrases (`In summary`, `Overall`).\n9. Every claim must map to evidence in the Claim-Evidence Map; weaken or remove unsupported claims rather than emit them.\n10. Read aloud before emit; if a sentence does not flow naturally, restructure it.\n\n## References\n- Anti-AI checklist: `resources\u002Fanti-ai-checklist.md`\n- Sentence-structure reference: `resources\u002Fsentence-structure-reference.md`\n- Academic verb tiers: `resources\u002Facademic-verb-tiers.md`\n- Hedging guide: `resources\u002Fhedging-guide.md`\n- Shared context loading: `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`\n- Shared quality principles: `..\u002F_shared\u002Fcore\u002Fquality-principles.md`\n",{"name":5,"description":7},"main","6725f57d555e82c2be2d17e092ad1291b20f56f0",".agents\u002Fskills\u002Foma-academic-writing",0,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac","https:\u002F\u002Fgithub.com\u002Fmrmarbury","FreeBSD admin, Elixir & Erlang Dev, Rubyist, Skateboarder, Musician","2026-11-07 06:23:43",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add mrmarbury\u002FPalmSync4Mac --skill oma-academic-writer",{"tool":63,"command":64},"bunx","bunx skills add mrmarbury\u002FPalmSync4Mac --skill oma-academic-writer",{"tool":66,"command":67},"pnpm","pnpm dlx skills add mrmarbury\u002FPalmSync4Mac --skill oma-academic-writer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-academic-writing\u002FSKILL.md",true,[71,77,81,85],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"resources\u002Facademic-verb-tiers.md","REFERENCE","参考文档",9990,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-academic-writing\u002Fresources\u002Facademic-verb-tiers.md",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"resources\u002Fanti-ai-checklist.md",9422,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-academic-writing\u002Fresources\u002Fanti-ai-checklist.md",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"resources\u002Fhedging-guide.md",5612,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-academic-writing\u002Fresources\u002Fhedging-guide.md",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"resources\u002Fsentence-structure-reference.md",7876,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-academic-writing\u002Fresources\u002Fsentence-structure-reference.md",[90,117,144,170,198,204],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":44},"01M6WJZMN4HV76T0Y2PYDAAD7Q","oma-translator","Context-aware translation that preserves tone, style, and natural word order. Use when translating UI strings, documentation, marketing copy, or any multilingual content. Infers register, domain, and style from the source text and surrounding codebase context.","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-translation\u002FSKILL.md",[],[97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116],"translator","oma translator","when","multilingual","codebase","source","strings","copy","register","style","tone","domain","translation","use","context","text","Word","marketing","ui","documentation",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":126,"publishedAt":44},"01M6WJZ5W60XSDDE72AW5E85GT","oma-skill-creator","Create or update OMA skills in the SSL-lite human-readable format. Use when adding a new `.agents\u002Fskills\u002F{skill-name}\u002FSKILL.md`, converting an existing skill to the standardized Scheduling \u002F Structural Flow \u002F Logical Operations \u002F References structure, or validating whether a skill has enough routing, execution, resource, and safety detail.","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-skill-creation\u002FSKILL.md",[123],{"categoryNo":124,"categoryName":125,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[127,128,129,130,131,132,110,133,134,135,33,136,137,138,139,140,141,99,142,143],"creator","oma skill creator","skill creator","Safety","execution","flow","scheduling","references","existing skill","ssl","human","structural","detail","routing","Existing","create","update",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":151,"publishedAt":44},"01M6WJYHKKTDG9RT9A6ZWCT29A","oma-orchestrator","Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress. Use for orchestration, parallel execution, and automated multi-agent workflows.","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-orchestration\u002FSKILL.md",[150],{"categoryNo":124,"categoryName":125,"taxonomyType":21,"taxonomyTypeDesc":22},[152,153,154,110,155,156,157,158,159,160,161,162,163,164,165,131,166,167,168,169],"oma orchestrator","orchestrator","MCP","for","multi","via","progress","agent workflows","coordinates","parallel execution","agent orchestrator","subagents","parallel","multi-agent","workflows","orchestration","memory","cli",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":179,"publishedAt":44},"01M6WJXXDQ99RCQ3S4GW5D42Q4","oma-explainer","Turn a code change (diff, PR, branch, commit range) into a rich, self-contained interactive HTML explainer with Background \u002F Intuition \u002F Code \u002F Quiz sections. Use for explain, walkthrough, code-change explanation, diff\u002FPR\u002Fbranch explainer requests — 설명서, 해설, コード解説, 代码讲解. Produces a single offline-capable HTML file with diagrams, callouts, and an accessible quiz.","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-explanation\u002FSKILL.md",[176],{"categoryNo":177,"categoryName":178,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[180,181,182,183,184,155,185,186,187,188,189,110,190,191,192,193,194,195,196,197],"oma explainer","explainer","interactive","single","rich","quiz","self","diagrams","diff","html","branch","walkthrough","file","offline","code","pr","commit","change",{"skillNo":199,"name":200,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":203,"publishedAt":44},"01M6BYY6K38NQSE2BXHWM0ZGRC","work","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fwork\u002FSKILL.md",[],[200],{"skillNo":205,"name":206,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":212,"publishedAt":44},"01M6BYY56BEPGHJ0VAZADCYBC1","video","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fvideo\u002FSKILL.md",[209],{"categoryNo":210,"categoryName":211,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[213],"Video"]