Guardrail·Learning & Documentation·v3.3.1

Academic Paper — Academic Paper Writing Agent Team

Name: Academic Paper — Academic Paper Writing Agent Team
Author: Imbad0202

12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-c…

You say

Install this skill Read the source first Free Written by Imbad0202 · unverified publisher

Context cost: 249.3k tokensestimated from the bundle, loaded when it triggers
Bundle: 62 files · 997.4 kBtext throughout, nothing executable
Licence: Source-availablefree to use
Last change: —v3.3.1
Servers it uses: Noneruns standalone

What it does

12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, audit my rebuttal, check my response draft, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見, 評估回覆, 논문 작성, 초록 작성, 논문 수정, 논문 계획을 도와줘, 심사 의견 반영, 답변서 점검, AI 사용 고지.

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Guardrail

Constrains what the agent is allowed to do.

documentationwritingagent

Filed under

Learning & Documentation

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md48.1 kB · 543 lines

--- name: academic-paper description: "12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, audit my rebuttal, check my response draft, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見, 評估回覆, 논문 작성, 초록 작성, 논문 수정, 논문 계획을 도와줘, 심사 의견 반영, 답변서 점검, AI 사용 고지." metadata: version: "3.3.1" last_updated: "2026-08-15" status: active data_access_level: raw task_type: open-ended related_skills: - deep-research - academic-paper-reviewer - academic-pipeline ---

16# Academic Paper — Academic Paper Writing Agent Team

18A general-purpose academic paper writing tool — 12-agent pipeline covering all disciplines, with higher education domain as the default reference.

20**v2.5** adds two writing quality features:

21- **Style Calibration** (intake Step 10, optional) — Provide 3+ past papers and the pipeline learns your writing voice (sentence rhythm, vocabulary preferences, citation integration style). Applied as a soft guide during drafting; discipline conventions always take priority. See shared/style_calibration_protocol.md.

22- **Writing Quality Check** (references/writing_quality_check.md) — A writing quality checklist applied during the draft self-review step. Catches overused AI-typical terms, em dash overuse, throat-clearing openers, uniform paragraph lengths, and monotonous sentence rhythm. These are good writing rules, not detection evasion.

24> **Routing discipline (v3.9.2):** see .claude/CLAUDE.md "Routing Discipline (v3.9.2)" + shared/references/intent_clarification_protocol.md for cross-skill routing rules. This skill assumes routing has already settled — ambiguous cross-phase materials should have been clarified upstream.

26## Quick Start

28**Minimal command:**

29```

30Write a paper on the impact of AI on higher education quality assurance

31```

33```

34Write a paper on the impact of declining birth rates on private university management strategies

35```

37**Execution flow:**

381. Configuration interview — paper type, discipline, citation format, output format

392. Literature search — systematic search strategy, source screening

403. Architecture design — paper structure, outline, word count allocation

414. Argumentation construction — claim-evidence chains, logical flow

425. Full-text drafting — section-by-section draft, register adjustment

436. Citation compliance + bilingual abstract (parallel)

447. Peer review — five-perspective categorical assessment, revision suggestions

458. Output formatting — LaTeX/DOCX (via Pandoc)/PDF/Markdown

47---

49## Trigger Conditions

51### Trigger Keywords

53**English**: write paper, academic paper, paper outline, write abstract, revise paper, literature review paper, check citations, convert to LaTeX, convert format, format paper, conference paper, journal article, thesis chapter, research paper, guide my paper, help me plan my paper, step by step paper, draft manuscript, write methodology, write discussion, parse reviews, revision roadmap, help me with my revision, I got reviewer comments, convert citations

55**繁體中文**: 寫論文, 學術論文, 論文大綱, 寫摘要, 修改論文, 文獻回顧論文, 檢查引用, 轉 LaTeX, 轉換格式, 研討會論文, 期刊文章, 學位論文, 研究論文, 引導我寫論文, 幫我規劃論文, 逐步寫論文, 寫方法論, 寫討論, 審查意見, 修訂路線圖, 幫我修改, 我收到審查意見, 轉換引用格式

57**한국어**: 논문 작성, 논문 초안, 논문 개요, 초록 작성, 논문 수정, 인용 확인, 인용 형식 검사, LaTeX 변환, 서식 변환, 학위논문 작성, 학술지 논문 작성, 학회 논문 작성, 논문 계획을 도와줘, 단계별로 논문 쓰기, 심사 의견을 받았어, 심사 의견 반영, 답변서 점검, AI 사용 고지

59### Plan Mode Activation

61Activate plan mode when the user wants guidance, step-by-step planning, or expresses uncertainty about paper structure. **Default rule**: when ambiguous between plan and full, prefer plan.

63> See references/plan_mode_protocol.md for full intent signals and activation rules.

65### Does NOT Trigger

67| Scenario | Use Instead |

68|----------|-------------|

69| Deep research / fact-checking (not paper writing) | deep-research |

70| Reviewing a paper (structured review) | academic-paper-reviewer |

71| Full research-to-paper pipeline | academic-pipeline |

73### Distinction from deep-research

75| Feature | academic-paper | deep-research |

76|---------|-------------------|-----------------|

77| Primary output | Publishable paper draft | Research report |

78| Structure | Journal-ready (IMRaD, etc.) | APA 7.0 report |

79| Citation | Multi-format (APA/Chicago/MLA/IEEE/Vancouver) | APA 7.0 only |

80| Abstract | Bilingual (zh-TW + EN) | Single language |

81| Peer review | Simulated 5-dimension review | Editorial review |

82| Output format | LaTeX/DOCX (via Pandoc)/PDF/Markdown | Markdown only |

83| Revision loop | Max 2 rounds with targeted feedback | Max 2 rounds |

85---

87## Agent Team (12 Agents)

90|---|-------|------|-------|

101| 11 | visualization_agent | Parse paper data and generate publication-quality figure code (Python matplotlib / R ggplot2) with APA 7.0 formatting, colorblind-safe palettes, and LaTeX integration | Phase 4 / Phase 7 |

102| 12 | revision_coach_agent | Parse unstructured reviewer comments into a Revision Roadmap, or explicitly identified real-committee comments into the separate #668 source-accounted concern tracker; works standalone | Revision-Coach mode |

103

104---

105

106## Output Formats

107

108### Text Formats

109LaTeX (.tex + .bib), DOCX (via Pandoc), PDF (via LaTeX or Pandoc), Markdown.

110

111### Figures

112When the paper contains quantitative results, the visualization_agent can generate publication-ready figures in Python (matplotlib/seaborn) or R (ggplot2) with APA 7.0 formatting and colorblind-safe palettes. Figures are delivered as runnable code + LaTeX \includegraphics integration code. See references/statistical_visualization_standards.md for chart type decision trees and code templates.

113

114### Citation Formats

115APA 7.0 (default), Chicago (Author-Date or Notes-Bibliography), MLA 9, IEEE, Vancouver. The formatter_agent supports late-stage citation format conversion between any two supported formats via "Convert citations to [format]".

116

117---

118

119## Orchestration Workflow (8 Phases)

120

121```

122Phase 0: CONFIG -> [intake_agent] -> Paper Configuration Record

123Phase 1: RESEARCH -> [literature_strategist] -> Search Strategy + Source Corpus

124Phase 2: ARCHITECTURE -> [structure_architect] -> Paper Outline + Evidence Map

125Phase 3: ARGUMENTATION -> [argument_builder] -> Argument Blueprint

126Phase 4: DRAFTING -> [draft_writer] -> Complete Draft

127Phase 5a: CITATIONS -> [citation_compliance] ──┐ -> Citation Audit Report

128Phase 5b: ABSTRACT -> [abstract_bilingual] ─┘ -> Bilingual Abstract + Keywords (parallel)

129Phase 6: PEER REVIEW -> [peer_reviewer] -> Review Report (max 2 revision loops)

130Phase 7: FORMAT -> [formatter] -> Final Output Package

131```

132

133> See references/workflow_phase_details.md for detailed per-phase agent behavior and output descriptions.

134

135### Review-target criteria binding (#684)

136

137When Phase 0 has produced an author-confirmed ReviewTargetContext (#683), the

138orchestrator initializes one pointer-only ReviewCriteriaBindingManifest and

139uses it unchanged across the formative, internal-evaluator, and external-panel

140consumers. The normative lifecycle, exact marker, closed roles, and explicit

141degraded path are defined in

142shared/references/review_criteria_consumer_protocol.md.

143

144- Phase 2 owns the FORMATIVE receipt. The Structure Architect maps selected

145 criterion ids to planned sections and evidence needs; later writing phases

146 reuse that receipt and do not re-resolve the target.

147- Phase 6a receives the same pointer authority and Target Criteria Brief while

148 remaining paper-blind; its pre-commitment artifact owns the INTERNAL

149 receipt. Phase 6b receives that unchanged artifact, may assess applicability

150 after it sees the draft, and owns any Critical/Major constructive finding

151 sidecar.

152- Scientific validity, venue fit, and submission readiness remain distinct.

153 Criteria never authorize invented evidence, results, methods, or changes to

154 the author's contribution claim.

155

156Binding validation is a handoff-conformance check only. It never supplies an

157editorial verdict, severity, checkpoint state, or author triage. If the binding

158is unavailable, disclose criteria_binding_unavailable; do not claim venue

159alignment and do not silently reconstruct a target from model memory.

160

161### Checkpoint Rules

162

1631. ⚠️ **IRON RULE**: User must confirm Paper Configuration Record before proceeding to Phase 1

1642. **Phase 2 -> 3**: User must approve outline (can request restructuring)

1653. ⚠️ **IRON RULE**: Max 2 revision loops; unresolved items -> "Acknowledged Limitations"

1664. **Peer Review** Critical-severity issues block progression to Phase 7

1675. User can skip Phase 1 (literature) if providing own sources

168

169---

170

171> **v3.4.0 compliance (applies to full mode):** Before finalization, compliance_agent runs RAISE principles-only check (warn-only; primary research is outside PRISMA-trAIce scope). Warnings are listed in the disclosure statement but never block the pipeline. See shared/raise_framework.md §Scope disclaimer.

172

173## Phase-by-phase Invocation Contract (v3.9.2)

174

175academic-paper pipeline runs in 8 phases (Phase 0 intake → 7 formatting). Two invocation modes:

176

177**Mode A — orchestrator-driven (default):** pipeline_orchestrator_agent (in academic-pipeline skill) runs all phases end-to-end with state tracking via Material Passport.

178

179**Mode B — phase-by-phase (cross-session resume):** User invokes one agent per phase across sessions for long-running projects. Common pattern: write the draft in one session, return next week to citation-check / abstract / peer-review independently.

180

181In Mode B, **single-phase agents (Bucket A per docs/design/2026-05-18-ars-v3.9.2-agent-phase-classification.md) stay strictly within their assigned phase for writes**. The 7 Bucket A agents in academic-paper are: literature_strategist (P1), structure_architect (P2), draft_writer (P4/P6 per invocation), citation_compliance (P5a), abstract_bilingual (P5b), peer_reviewer (P6), formatter (P7). Reads from upstream phases are allowed.

182

183Multi-phase agents (Bucket B: argument_builder P3+Plan, visualization P4+P7) do exactly the work specified by the caller's invocation for that phase — no extension to other phases in the same call. The v3.6.6 generator-evaluator contract below additionally constrains draft_writer and peer_reviewer sub-phase behavior (Phase 4a/4b, Phase 6a/6b).

184

185Routing into Mode B requires explicit user signal — /ars-<mode> slash command or [direct-mode] prefix. Ambiguous cross-phase input defaults to clarification per .claude/CLAUDE.md Routing Discipline + shared/references/intent_clarification_protocol.md.

186

187**Enforcement (v3.9.2):** Phase Boundary blocks on Bucket A agents + advisory verifier (scripts/check_pipeline_integrity.py) + a deterministic PreToolUse write-scope guard in hook-enabled runtimes (#134 rescope, PR #294). Multi-phase envelope remains forward-scope (#134 Slices 3-5).

188

189## v3.6.6 Generator-Evaluator Contract Protocol

190

191> Authoritative orchestration block for the v3.6.6 contract-gated phase splits inside academic-paper full mode. Schema 13.1 since v3.6.6 (shared/sprint_contract.schema.json). Templates: shared/contracts/writer/full.json + shared/contracts/evaluator/full.json. Design spec: docs/design/2026-04-27-ars-v3.6.6-generator-evaluator-contract-design.md §5.

192>

193> **Applies to academic-paper full mode only.** Nine non-full modes (plan, outline-only, revision, revision-coach, abstract-only, lit-review, format-convert, citation-check, disclosure) are byte-equivalent across v3.6.5 → v3.6.6 and do not invoke this protocol. (The later-added rebuttal-audit mode is likewise non-full and does not invoke this protocol.) Pipeline boundary unchanged: academic-pipeline Stage 2 dispatches academic-paper in plan or full mode (full only invokes this protocol); Stage 3 dispatches the separate academic-paper-reviewer skill (5-panel external editorial review). The in-pair Phase 6 evaluator under this protocol and the Stage 3 reviewer are different review layers — see design doc §5.1 audit conclusion 2.

194

195### Overview

196

197v3.6.6 splits Phase 4 (writer drafting) and Phase 6 (in-pair evaluator review) into paper-blind / paper-visible call pairs gated by the writer_full and evaluator_full contracts. The split mirrors academic-paper-reviewer/references/sprint_contract_protocol.md (the v3.6.2 reviewer pattern) but adapts it for single-agent generator modes that have no panel and (for the writer) no scoring_plan.

198

199The load-bearing mechanism is the **physical separation of calls**: writer Phase 4a never sees the runtime drafting artefacts; evaluator Phase 6a never sees the writer Phase 4b draft. This destroys the "read the paper, then rationalise the standard" drift path on the in-pair self-quality gate.

200

201### Four-call structure

202

203For each academic-paper full invocation, Phase 4 + Phase 6 expand from two single calls into four separate model calls. Each call has its own system prompt and user content per the system-vs-user content discipline below.

204

2051. **Phase 4a — writer paper-blind pre-commitment.**

206 - System prompt: ### Phase 4a — Writer paper-blind pre-commitment sub-section in academic-paper/agents/draft_writer_agent.md § "v3.6.6 Generator-Evaluator Contract Protocol".

207 - User content: writer_full contract JSON + paper metadata only (title, field, word_count).

208 - Output: ## Acceptance Criteria Paraphrase section + terminal [PRE-COMMITMENT-ACKNOWLEDGED] tag.

209 - Lint: 3 structural checks (see § "Phase 4a / 6a output lint" below).

2102. **Phase 4b — writer paper-visible drafting + self-scoring.**

211 - System prompt: ### Phase 4b — Writer paper-visible drafting + self-scoring sub-section in the same agent file.

212 - User content: writer_full contract JSON (re-injected) + Phase 4a output wrapped in <phase4a_output>...</phase4a_output> data delimiter + upstream drafting artefacts (Paper Configuration Record, Paper Outline, Argument Blueprint, Annotated Bibliography incl. its Search Strategy / Schema 2 search_strategy (#548 — the bound the writer fills into search-bounded novelty claims), optional Style Profile, optional Knowledge Isolation Directive).

213 - Output: ## Draft Body → ## Dimension Scores → ## Failure Condition Checks → ## Writer Decision.

214 - Lint: 4 structural checks (see § "Phase 4b / 6b output lint" below).

2153. **Phase 6a — evaluator paper-blind pre-commitment.**

216 - System prompt: ### Phase 6a — Evaluator paper-blind pre-commitment sub-section in academic-paper/agents/peer_reviewer_agent.md § "v3.6.6 Generator-Evaluator Contract Protocol".

217 - User content: evaluator_full contract JSON + paper metadata + the writer's most recent <phase4a_output> (the writer artefact the evaluator must verify per disagreement_handling.pre_commitment_check_protocol.check_writer_artifact) +, when active, the pointer-only #684 manifest/Target Criteria Brief/INTERNAL marker.

218 - Output: ## Contract Paraphrase + ## Scoring Plan (per-dimension dimension_id / what_to_look_for / what_triggers_block / what_triggers_warn) + pointer-only binding commitment (or criteria_binding_unavailable) + terminal [PRE-COMMITMENT-ACKNOWLEDGED] tag. No additional H2 is introduced.

219 - Lint: 5 structural checks.

2204. **Phase 6b — evaluator paper-visible scoring + decision.**

221 - System prompt: ### Phase 6b — Evaluator paper-visible scoring + decision sub-section in the same agent file.

222 - User content: evaluator_full contract JSON (re-injected) + Phase 6a output wrapped in <phase6a_output>...</phase6a_output> + the writer's <phase4a_output> (unconditional per pre_commitment_check_protocol.check_writer_artifact) + the writer Phase 4b draft (the artefact under review) + the unchanged #684 authority when it was supplied in Phase 6a.

223 - Output: ## Dimension Scores → ## Failure Condition Checks → ## Review Body → ## Evaluator Decision, plus the role marker/unavailable disclosure and a separately validated constructive sidecar when applicable.

224 - Lint: 5 structural checks.

225

226### System prompt vs user content discipline

227

228Mirrors sprint_contract_protocol.md §2 reviewer pattern verbatim:

229

230- **System prompt carries invariant policy text only**: the phase sub-section instructions from the agent file's ## v3.6.6 Generator-Evaluator Contract Protocol block, the lint description, and the phase-boundary tag conventions.

231- **User content carries the contract JSON (re-injected per call) plus the runtime inputs allowed at that phase**: paper metadata, <phase4a_output> / <phase6a_output> delimiter blocks, upstream drafting artefacts, the paper draft.

232

233All dynamic LLM output (Phase Na runtime emissions, paper content) lives in user content via data delimiters, never in the system prompt. This prevents accidental elevation of dynamic per-paper content into the invariant policy surface.

234

235### Schema field name vs runtime emission distinction

236

237pre_commitment_artifacts (snake_case, backticks) is the schema field name in shared/sprint_contract.schema.json — a configuration declaration in the frozen contract baseline. The "writer Phase 4a pre-commitment output" is the runtime emission — the actual Markdown text the writer agent emits in Phase 4a. The runtime emission lives inside <phase4a_output> and gets handed off to Phase 4b / Phase 6a / Phase 6b. Same pattern for disagreement_handling (schema field) vs "evaluator Phase 6a pre-commitment output" (runtime emission). Mixing the two leads to confusion between contract baseline configuration and LLM-generated content.

238

239### Phase 4a / 6a output lint

240

241Mode-specific structural check counts, per sprint_contract_protocol.md §4 enumeration convention:

242

243- **Writer Phase 4a (3 checks)**: required sections in order (## Acceptance Criteria Paraphrase, terminal [PRE-COMMITMENT-ACKNOWLEDGED]); paraphrase paragraph count ≥ pre_commitment_artifacts.acceptance_criteria_paraphrase.minimum_dimensions; Phase 4a content references contract JSON + paper metadata only. **No ## Scoring Plan section** — writer_full carries no scoring_plan.

244- **Evaluator Phase 6a (5 checks)**: required sections in order (## Contract Paraphrase, ## Scoring Plan, terminal [PRE-COMMITMENT-ACKNOWLEDGED]); paraphrase paragraph count ≥ disagreement_handling.paraphrase_minimum_dimensions; one ### <Dn>: <name> subsection per acceptance dimension; each scoring_plan subsection contains disagreement_handling.scoring_plan.per_dimension_criteria four-field shape (dimension_id, what_to_look_for, what_triggers_block, what_triggers_warn); Phase 6a content references contract JSON + paper metadata + the writer's <phase4a_output> plus the paper-blind #684 pointer authority only (no full draft / paper content). The binding commitment is unbulleted pointer data after Scoring Plan, not an additional H2.

245

246Retry semantics: lint failure on the first attempt → retry once with the specific lint gap hinted in the system prompt; second failure → mark this role unusable per § "Single-agent generator unusable handling" below.

247

248### Phase 4b / 6b output lint

249

250- **Writer Phase 4b (4 checks)**: required sections in order — ## Draft Body, ## Dimension Scores, ## Failure Condition Checks, ## Writer Decision; Dimension Scores one-to-one across the seven writer dimensions D1–D7 (per shared/contracts/writer/full.json); Failure Condition Checks one-to-one across F1 / F4 / F2 / F3 / F0; Writer Decision derivable from F-condition severity precedence. **No multi-dissent retry** (writer has no scoring_plan to dissent against). **No consistency check** (writer Phase 4a emits no scoring_plan trigger tokens).

251- **Evaluator Phase 6b (5 checks)**: required sections in order — ## Dimension Scores, ## Failure Condition Checks, ## Review Body, ## Evaluator Decision; Dimension Scores one-to-one across the five evaluator dimensions D1–D5 (per shared/contracts/evaluator/full.json); Failure Condition Checks one-to-one across F1 / F2 / F3 / F6 / F4 / F5 / F0; consistency check (Phase 6b score substring-matches Phase 6a disagreement_handling.scoring_plan.per_dimension_criteria trigger tokens); Evaluator Decision derivable from F-condition severity precedence. **No multi-dissent retry** (evaluator's intra-phase disagreement is encoded as F-condition action via disagreement_handling.disagreement_resolution, not as a retry trigger).

252

253Multi-dissent retry remains reviewer-only (academic-paper-reviewer skill); generator modes have no panel and no scoring_plan dissent anchor.

254

255Lint count summary across the three modes:

256

258|---|---|---|---|

259| Phase 1 / 4a / 6a | 5 | 3 | 5 |

260| Phase 2 / 4b / 6b | 6 | 4 | 5 |

261

262### Single-agent generator unusable handling

263

264When a writer or evaluator phase becomes unusable (Phase Na lint twice fail OR Phase Nb lint fail), academic-paper emits a phase-level abort tag and routes to user intervention:

265

266- **Writer Phase 4 unusable** → [GENERATOR-PHASE-ABORTED: role=writer, contract=<id>, reason=<lint_failure_kind>] → abort academic-paper Phase 4 → user intervention decides retry / fallback / regression to Phase 3 (Argument Blueprint).

267- **Evaluator Phase 6 unusable** → [GENERATOR-PHASE-ABORTED: role=evaluator, contract=<id>, reason=<lint_failure_kind>] → abort academic-paper Phase 6 → user intervention decides retry / fallback / regression to Phase 5 (Drafting completion).

268

269[GENERATOR-PHASE-ABORTED] does **not** constitute a valid Phase 6b emission and cannot enter Stage 3 reviewer dispatch. Two valid Stage 3 entry paths exist (per design doc §5.1):

270

271- **Standard path**: evaluator Phase 6b emits F0 evaluator_decision=accept or F4 evaluator_decision=accept_with_dissent_note.

272- **Exceptional path**: evaluator Phase 6b emits F5 evaluator_decision=flag_for_reviewer_stage after the in-pair revision loop exhausts at round 2 with mandatory-dimension block recurring.

273

274academic-paper carries no panel cardinality invariant for writer / evaluator (no panel_size field — Schema 13.1 §3.3.5 reviewer-conditional). There is no [PANEL-SHRUNK] analogue at the generator side; [GENERATOR-PHASE-ABORTED] is phase-level abort.

275

276**Operational monitor**: track [GENERATOR-PHASE-ABORTED] rate over the first three months of v3.6.6 deployment. The denominator is **per academic-paper full run** — one user-perceived top-level invocation. The 5% threshold is (runs_with_any_abort) / (total_runs). If the rate exceeds 5%, v3.6.7 introduces graceful-degradation fallback (see § "Known limitations" below).

277

278### Cross-session resume scope

279

280The v3.6.6 generator-evaluator round (Phase 4a + Phase 4b + Phase 6a + Phase 6b + in-pair revision loop) is an **in-session atomic unit**. Manual session split mid-round → writer Phase 4a output is lost; new session must restart academic-paper full mode from Phase 0.

281

282The v3.6.3 ARS_PASSPORT_RESET=1 reset_boundary[] mechanism (per academic-pipeline/references/passport_as_reset_boundary.md) operates at academic-pipeline Stage boundaries, not at academic-paper internal phase boundaries. academic-paper internal phases (4a / 4b / 6a / 6b) are **not** boundary points; no kind: boundary ledger entry is emitted between them. v3.6.7+ may introduce pre_commitment_history[] to persist writer Phase 4a artefacts across sessions if operational data warrants — see § "Known limitations" below.

283

284## Known limitations

285

286- **No graceful-degradation fallback in v3.6.6**: when the writer or evaluator phase aborts via [GENERATOR-PHASE-ABORTED], academic-paper full aborts and routes to user intervention. v3.6.7 may introduce a fallback that degrades the affected phase to v3.6.5 single-call behaviour and logs the degradation. v3.6.6 ships with abort-only behaviour. See § "Single-agent generator unusable handling" above for the operational 5% / three-month monitor.

287- **No cross-session resume mid-round**: the four-phase generator-evaluator round is an in-session atomic unit. Manual session split mid-round loses the writer Phase 4a artefact and forces restart from Phase 0. v3.6.7+ may introduce a pre_commitment_history[] ledger entry in Schema 9 to persist the writer Phase 4a artefact across session boundaries; v3.6.6 does not implement.

288- **In-pair Phase 6 evaluator vs academic-paper-reviewer external review**: the in-pair peer_reviewer_agent (Phase 6 evaluator with the v3.6.6 contract gate) and the standalone academic-paper-reviewer skill (Stage 3 5-panel external editorial review) serve different review layers and remain documented as known technical debt per design doc §1 known limitations. Routing / merge decisions are deferred to v3.7.x.

289

290## Operational Modes (11 Modes)

291

292See references/mode_selection_guide.md for details.

293

295|------|---------|--------|--------|

304| revision-coach | "parse reviews" / "revision roadmap" / "I got reviewer comments" / "should we push back" / "conference rebuttal" / "grant panel response" / explicitly identified real committee correspondence | 12 only | Peer-review path: immutable Roadmap core + explicit author sidecar + optional Tracking Template/Response Skeleton. Committee path: separate #668 concern tracker + placeholder response skeleton; no Schema 11, reviewer obligation/severity, or determination. |

305| **disclosure** (v3.2) | **"AI disclosure for Nature" / "generate AI usage statement"** | **9 only** | **Default venue path: REQUIRED / ACTION_ONLY / NOT_REQUIRED / UNKNOWN applicability plus typed halt status; policy-anchor path: anchor-specific render** |

306| **rebuttal-audit** | **"audit my response" / "check my rebuttal" / "did I miss any reviewer comment"** (requires BOTH reviewer comments AND an existing rebuttal draft) | **12 only (parse-only)** | **Rebuttal QA report: per-comment coverage + gaps + risk flags. No new response generated; advisory only. Does NOT emit Schema 11 / Material Passport / verified status.** |

307

308**Disclosure dispatch contract:** when mode=disclosure, agent 9 takes its standalone branch and MUST load references/disclosure_mode_protocol.md before producing text. It does not run normal Phase 7 formatting or substitute the generic full-pipeline AI statement; the protocol selects the venue database or policy-anchor path and owns all halt/render decisions.

309

310### Quick Mode Selection Guide

311

312| Your Situation | Recommended Mode | Spectrum |

313|----------------|-----------------|----------|

314| Starting from scratch with a clear RQ | full | balanced |

315| Need help planning before writing | plan | originality |

316| Just need an outline | outline-only | balanced |

317| Have a draft, received review feedback | revision | fidelity |

318| Have unstructured reviewer comments | revision-coach | balanced |

319| Have comments from a real committee/institutional review office to track | revision-coach committee-correspondence variant | fidelity |

320| Just need an abstract | abstract-only | fidelity |

321| Need to check/fix citations | citation-check | fidelity |

322| Need to convert format (LaTeX, DOCX) or citation style | format-convert | fidelity |

323| Want a systematic literature review paper | lit-review | fidelity |

324| Need a venue-specific AI-usage disclosure bundle for submission | disclosure | fidelity |

325| Have a written rebuttal draft to QA against reviewer comments | rebuttal-audit | fidelity |

326

327**Spectrum** (v3.2): *fidelity* = template-heavy, predictable output; *balanced* = default; *originality* = exploratory, template-light. See shared/mode_spectrum.md for the full cross-skill spectrum table.

328

329Not sure? Start with plan — it will guide you step by step. disclosure is a finishing step — run it after the paper is drafted, targeting the venue you plan to submit to.

330

331**Committee-correspondence routing:** use the revision-coach variant only when the

332user explicitly identifies a real committee/institutional review office. Load

333references/committee_correspondence_protocol.md; do not infer official authority

334from tone. The separate artifact is a source-accounted drafting aid and never enters

335peer-review Schema 11.

336

337### Mode Selection Logic

338

339> See references/mode_selection_guide.md for trigger-to-mode mappings and the full selection flowchart.

340

341---

342

343## Rebuttal-Audit Mode

344

345rebuttal-audit evaluates an author's **existing** rebuttal / response-to-reviewers draft for coverage, tone, and evidence. It is advisory QA — it does **not** write or rewrite the response.

346

347**Input gate (routing):** activate rebuttal-audit only when the user supplies BOTH (a) the reviewer comments / decision letter AND (b) an existing rebuttal/response draft to evaluate. If only (a) is present (no draft yet), route to revision-coach (which *generates* a response skeleton). If intent is ambiguous, clarify rather than guess.

348

349**What it produces:**

350- Per-comment coverage table — every reviewer concern marked addressed / partially / missing in the draft.

351- Gap list — concerns the draft fails to answer.

352- Risk flags — tone too combative, claims made without evidence, or a response that misreads the reviewer's actual point.

353- Improvement suggestions (advisory).

354

355**IRON RULE — integrity boundary (no false certification):** rebuttal-audit reuses revision_coach_agent's comment-parsing capability, but a standalone invocation runs **outside** the pipeline and therefore never passes Stage 4.5 final integrity. It **MUST NOT** emit a Schema 11 commitment_extracted ledger, **MUST NOT** write to the Material Passport, and **MUST NOT** mark the package ready_to_submit or any verified status. Producing a Schema 11 artifact would falsely imply the response entered the pipeline's traceability system. The output is an advisory QA report only.

356

357**Boundary vs re-review:** academic-paper-reviewer's re-review mode verifies the **revised manuscript** (did the author's claimed changes actually appear in the paper) and runs inside the pipeline. rebuttal-audit verifies the **response letter itself** (does the rebuttal cover every comment, is its tone/evidence sound) and runs standalone, advisory. Different artifacts, different layers.

358

359---

360

361## Revision Mode Patch Protocol (#390)

362

363In revision mode, draft_writer_agent does NOT re-emit the complete paper. The round runs **anchorize → patch → deterministic apply → finalizer**, confining the regeneration surface to the blocks the revision explicitly touches (DELEGATE-52 blast-radius containment; spec docs/design/2026-06-10-390-diff-patch-revision-mode-spec.md):

364

3651. **Anchorize** the draft (scripts/ars_anchorize_draft.py — idempotent, content-neutral): every block gets a stable  marker and an exact manifest. Nothing rewrites the draft before apply.

3662. **Bind explicit authority (#670):** validate the immutable revision-roadmap/1.0, exact registered claim surfaces, and complete author-adjudication/1.0. The roadmap keeps severity, obligation, cost scope, and bounded consequence independent; author triage and exact targets live only in the separate explicit sidecar.

3673. **The writer emits current patch 1.1** (shared/contracts/patch/revision_patch.schema.json) as a sidecar — every op cites only will_address items, stays inside exact target/operation scopes, and explicitly declares claim/collateral arrays. Registered claim movement needs an exact author-approved replacement; declined overlap needs exact collateral authority.

3684. **Deterministic apply** (scripts/ars_apply_revision_patch.py) replays every binding before structural analysis or write. Current report format 1.3 carries the mechanically derived authorization witness and the honest unregistered_claim_drift_review_required E6 boundary. If E6 later detects a drift on an unregistered surface, the checkpoint has no default-open route: the author must explicitly choose restore, authorize_with_reason, or pause. Build and replay validation bind each choice to one explicitly named run-local raw session-event artifact; the sidecar retains its recomputed digest but neither path nor message. Untouched blocks remain byte-identical.

3695. **Continuous evidence:** every review write, all-declined no-op, and integrity-correction round enters revision-evidence-bundle/1.0, from an exact integrity-PASS draft to the exact final draft. A scope escalation requires a new explicit sidecar or a narrower patch; legacy full re-emission cannot claim current authorization PASS.

370

371Orchestrated runs follow pipeline_orchestrator_agent.md § Revision-Round Patch Sequencing; Mode B users run the same scripts by hand — exact commands in references/revision_patch_protocol.md. Honest boundary: registered surfaces and exact edit authority are machine-replayed, but unregistered semantic drift still requires E6 review. scripts/claim_strength_drift_disposition.py closes explicit handling of reported rows only; it does not make model-mediated detection deterministic or complete. The academic-paper full in-pair Phase 6→4 loop is outside this standalone/pipeline revision contract.

372

373---

374

375## Plan Mode: Chapter-by-Chapter Guided Planning

376

377Socratic mode that guides users through paper planning one chapter at a time. Builds a complete Paper Blueprint through structured dialogue.

378

379> See references/plan_mode_protocol.md for the full chapter-by-chapter dialogue flow and Paper Blueprint structure.

380

381---

382

383## Handoff Protocol: deep-research -> academic-paper

384

385intake_agent automatically detects deep-research materials (RQ Brief /

386Bibliography / Synthesis / INSIGHT Collection) and skips redundant steps. It

387also requires the exact builder-produced preregistration-artifact/1.0 handoff

388receipt and, when provided, its explicitly named companion. Intake validates and

389carries those bytes unchanged; it does not infer status, repair/rebuild the

390sidecar, follow its display path, or substitute a planning template. A later

391explicit user supply must be represented by a new sidecar from the named

392deterministic builder. See deep-research/SKILL.md Handoff Protocol and

393shared/references/cross_document_consistency_advisory_protocol.md.

394

395---

396

397## Failure Paths

398

399See references/failure_paths.md for details. Quick reference:

400

401| Failure Scenario | Handling Strategy |

402|---------|---------|

403| Insufficient research foundation | Recommend running deep-research first |

404| Wrong paper structure selected | Return to Phase 2, suggest alternative structure |

405| Word count significantly over/under target | Identify problematic chapters, suggest trimming/expansion |

406| Citation format entirely wrong | Re-run the entire citation phase |

407| Peer review rejection | Analyze rejection reasons, suggest major revision or restructuring |

408| Plan mode not converging | Suggest switching to outline-only mode |

409| Incomplete handoff materials | List missing items, suggest supplementing or re-running |

410| User abandons midway | Save completed Chapter Plan |

411

412---

413

414## Full Academic Pipeline

415

416See academic-pipeline/SKILL.md for the complete workflow.

417

418---

419

420## Phase 0: Configuration Interview

421

422See agents/intake_agent.md for the complete field definitions of the Phase 0 configuration interview. The interview covers 9 core items: paper type, discipline, target journal, citation format, output format, language, abstract, word count, and existing materials — plus co-authors, funding, optional style calibration, the domain evidence profile (Step 12), the citation-verification level (Step 13, #392), and the independent retraction policy (Step 14, #651). Both citation policies are mark-only by default with explicit strict opt-in, seeding terminal_policies.citation_existence and terminal_policies.retraction respectively. When an author confirms a venue/track/type target, Phase 0 also resolves the #683 ReviewTargetContext and initializes the #684 pointer-only binding manifest before any criteria-aware consumer runs; absence uses the explicit field-general criteria_binding_unavailable path. Outputs a Paper Configuration Record, awaiting user confirmation.

423

424---

425

426## File Structure

427

428**Agent definitions**: agents/{agent_name}.md — one file per agent (12 total, matching Agent Team table above).

429

430**References** (28 files in references/):

431- Citation: apa7_extended_guide, apa7_chinese_citation_guide, citation_format_switcher

432- Writing: academic_writing_style, writing_quality_check, writing_judgment_framework

433- Structure: paper_structure_patterns (6 types), abstract_writing_guide, intro_title_rhetoric_guide (CARS moves + title checklist)

434- Domain: hei_domain_glossary (bilingual), journal_submission_guide, latex_template_reference, domain_evidence_profiles (advisory screening profiles)

435- Process: failure_paths (12 scenarios), mode_selection_guide (11 modes), plan_mode_protocol, workflow_phase_details, revision_patch_protocol (#390 Mode B commands + marker lifecycle)

436- Ethics: credit_authorship_guide (CRediT 14 roles), funding_statement_guide, statistical_visualization_standards

437- Disclosure (v3.2): disclosure_mode_protocol (default venue applicability/status bundle: REQUIRED, ACTION_ONLY, NOT_REQUIRED, UNKNOWN, plus typed halts; separate policy-anchor rendering), venue_disclosure_policies (v2 database: ICLR, NeurIPS, Nature, Science, ACL, EMNLP, plus medical-publishing policy targets — ICMJE, NEJM, The Lancet, JAMA, BMJ, PLOS, Frontiers, publisher-wide Chinese Nursing Journals Publishing House 中华护理杂志社, journal-level International Eye Science 国际眼科杂志)

438- Integrity (v3.3): anti_leakage_protocol (knowledge isolation), vlm_figure_verification (optional VLM figure check)

439- Policy anchors (#108): policy_anchor_table, policy_anchor_disclosure_protocol

440- Meta: changelog (version history)

441- Also: deep-research/references/apa7_style_guide.md (base reference, extended here)

442

443**Templates** (11 files in templates/): imrad, literature_review, case_study, theoretical_paper, policy_brief, conference_paper, latex_article_template.tex, bilingual_abstract, credit_statement, funding_statement, revision_tracking (4 status types).

444

445**Examples** (9 files in examples/): imrad_hei_example, literature_review_example, plan_mode_guided_writing, chinese_paper_example, revision_mode_example, revision_recovery_example, clinical_citation_verification_checklist, clinical_epistemic_status_example, version_family_reconciliation_example.

446

447---

448

449## Anti-Patterns

450

451Explicit prohibitions to prevent common failure modes:

452

454|---|-------------|-------------|-----------------|

459| 5 | **⚠️ IRON RULE: Fabricated citations** | Inventing plausible-sounding references that don't exist | Every citation must be verified via DOI or WebSearch; see academic-pipeline/agents/integrity_verification_agent.md |

463

464---

465

466## Quality Standards

467

468### Writing Quality

4691. **Every claim must have a citation** or be supported by the paper's own data — or, for #548 absence/novelty claims, carry documented-search provenance plus the named nearest prior work where one exists (the explicit absence-of-adjacent-work statement suffices otherwise; no source can cite an absence)

4702. **Zero citation orphans** — in-text citations <-> reference list must perfectly match

4713. **Consistent register** — academic tone appropriate for the discipline

4724. **Logical flow** — clear transitions between paragraphs and sections

4735. **Word count compliance** — within +/-10% of target

474

475### Bilingual Abstract Quality

4766. **Independent writing** — zh-TW and EN abstracts are independently composed, NOT mechanical translations

4777. **Structural alignment** — both abstracts cover the same key points in the same order

4788. **Keywords** — 5-7 per language, reflecting the paper's core concepts

4799. **Word count** — EN: 150-300 words; zh-TW: 300-500 characters

480

481### Citation Quality

48210. **Format compliance** — 100% adherence to selected citation style

48311. ⚠️ IRON RULE: **DOI inclusion** — every source with a DOI must include it; every citation must be verified via DOI or WebSearch

48412. **Currency** — flag sources older than 10 years (unless seminal works)

48513. **Self-citation ratio** — flag if >15%

486

487### Peer Review

48814. **Five criterion-bound dimensions** — Originality, Methodological Rigor, Evidence Sufficiency, Argument Coherence, and Writing Quality; report categorical judgements with evidence and no numerical aggregation

48915. **Actionable feedback** — every criticism must include a specific suggestion

49016. **Max 2 revision rounds** — unresolved items become Acknowledged Limitations

491

492### Mandatory Inclusions

493⚠️ **IRON RULE**: Every paper MUST include: Data Availability Statement, Ethics Declaration, Author Contributions (CRediT), Conflict of Interest Statement, Funding Acknowledgment.

49417. **AI-use reporting** — normal full / format-convert flows include the existing generic AI tool-usage statement; standalone disclosure mode instead follows the selected venue applicability/status or policy-anchor rendering contract

49518. **Limitations section** — explicitly discuss study limitations

49619. **Ethics statement** — when applicable (human subjects, sensitive data)

497

498---

499

500## Output Language

501

502Follows the user's language. Academic terminology is kept in English. Bilingual abstracts are always provided regardless of the main text language.

503

504---

505

506## Integration with Other Skills

507

508```

509academic-paper + tw-hei-intelligence -> Evidence-based HEI paper with real MOE data

510academic-paper + deep-research -> Deep research phase -> paper writing phase (auto-handoff)

511academic-paper + report-to-website -> Interactive web version of the paper

512academic-paper + notebooklm-slides-generator -> Presentation slides from paper

513academic-paper + academic-paper-reviewer -> Peer review -> revision loop

514```

515

516---

517

518## Model Tiering (#517, optional)

519

520When ARS_MODEL_TIERING is set, the dispatching session routes this skill's agents per shared/model_tiering.md (canonical: the full 39-agent judgment/execution table + rules). Compact rule:

521

522- **Unset (default):** every agent inherits the session model — byte-equivalent pre-#517 behavior.

523- **economy** (frontier-tier session): execution-type agents dispatch ONE tier below the session model — floor Opus-class, never lower; judgment-type agents stay on the session model. No-op at or below the floor (announce once).

524- **quality-boost** (below-frontier session): judgment-type agents at the checkpoint surfaces (Stage 2.5/4.5 gates; the opt-in Stage 4→5 claim–ref audit; final review) jump UP to the frontier tier (however many tiers away — not a single increment); nothing is ever downgraded. No-op at the frontier (announce once).

525- Unknown values → warn once, behave as unset. Tiers are relative positions, never hard-pinned model ids. When a direction is active, route repeated same-stage calls to the SAME worker so its prompt cache accumulates; unset means dispatch shapes stay byte-equivalent too.

526

527---

528

529## Version Info

530

531| Item | Content |

532|------|---------|

533| Skill Version | 3.3.1 |

534| Last Updated | 2026-08-15 |

535| Maintainer | Cheng-I Wu |

536| Dependent Skills | deep-research v1.0+ (upstream), academic-paper-reviewer v1.0+ (downstream) |

537

538---

539

540## Version History

541

542> See references/changelog.md for full version history.

543

In the file

SKILL.md6,152 words

Files62

LicenceSource-available

Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈210

always loaded

The name and description, so the model knows the skill exists and when to reach for it.

249,140

on trigger

The instruction body and 61 supporting files, read only when the skill fires.

124.7%

of a 200k window

Ten skills this size would take about 1247% of the window before you open a file.

050k100k150k200k context window

249.3k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption

Installsnone yet

Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for

Writes filesno

Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

If this is not it

45 other skills in Learning & Documentation

What is in the bundle

62 files, 997.4 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

SKILL.md48.1 kB
agents/abstract_bilingual_agent.md7.9 kB
agents/argument_builder_agent.md11.2 kB
agents/citation_compliance_agent.md19.6 kB
agents/draft_writer_agent.md52.4 kB
agents/formatter_agent.md63.0 kB
agents/intake_agent.md24.2 kB
agents/literature_strategist_agent.md44.0 kB
agents/peer_reviewer_agent.md30.0 kB
agents/revision_coach_agent.md18.7 kB
agents/socratic_mentor_agent.md28.6 kB
agents/structure_architect_agent.md18.4 kB
agents/visualization_agent.md17.6 kB
examples/chinese_paper_example.md21.6 kB
examples/clinical_citation_verification_checklist.md4.5 kB
examples/clinical_epistemic_status_example.md6.7 kB
examples/commitment_ledger_example.md8.3 kB
examples/imrad_hei_example.md23.9 kB
examples/literature_review_example.md31.5 kB
examples/plan_mode_guided_writing.md35.2 kB
examples/revision_mode_example.md20.6 kB
examples/revision_recovery_example.md42.2 kB
examples/version_family_reconciliation_example.md3.9 kB
references/abstract_writing_guide.md8.0 kB
references/academic_writing_style.md7.7 kB
references/anti_leakage_protocol.md4.5 kB
references/apa7_chinese_citation_guide.md12.5 kB
references/apa7_extended_guide.md6.7 kB
references/changelog.md2.8 kB
references/citation_format_switcher.md7.5 kB
references/committee_correspondence_protocol.md6.3 kB
references/credit_authorship_guide.md14.0 kB
references/disclosure_mode_protocol.md55.2 kB
references/domain_evidence_profiles.md4.3 kB
references/failure_paths.md14.6 kB
references/funding_statement_guide.md12.2 kB
references/hei_domain_glossary.md7.0 kB
references/intro_title_rhetoric_guide.md8.9 kB
references/journal_submission_guide.md8.9 kB
references/latex_template_reference.md9.9 kB
references/mode_selection_guide.md17.8 kB
references/paper_structure_patterns.md8.4 kB
references/plan_mode_protocol.md6.8 kB
references/policy_anchor_disclosure_protocol.md21.5 kB
references/policy_anchor_table.md21.7 kB
references/revision_patch_protocol.md12.9 kB
references/statistical_visualization_standards.md24.2 kB
references/venue_disclosure_policies.md39.3 kB
references/vlm_figure_verification.md9.3 kB
references/workflow_phase_details.md3.8 kB
references/writing_judgment_framework.md3.3 kB
references/writing_quality_check.md9.2 kB
templates/bilingual_abstract_template.md2.9 kB
templates/case_study_template.md2.9 kB
templates/conference_paper_template.md2.4 kB
templates/credit_statement_template.md4.5 kB
templates/funding_statement_template.md9.1 kB
templates/imrad_template.md4.5 kB
templates/literature_review_template.md2.9 kB
templates/policy_brief_template.md3.6 kB
templates/revision_tracking_template.md10.4 kB
templates/theoretical_paper_template.md2.9 kB

What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 62 files you can review in full before installing. The Source-available licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Academic Paper — Academic Paper Writing Agent Team · 249.3k tokens when loaded
npx mcprush@latest skill add imbad0202/academic-paper-academic-paper-writing-agent-team

Writes to .claude/skills/academic-paper-academic-paper-writing-agent-team/ in the current project. Add --global to put it in your home directory instead, for every project.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/

Claude Desktop

ChatGPT

Cursor.cursor/skills/

VS Code.github/skills/

Codex CLI.agents/skills/

Gemini CLI.gemini/skills/

Grok.grok/skills/

Zed.agents/skills/

Windsurf.windsurf/skills/

Agent SDK.claude/skills/

HTTP / API

This release

Version3.3.1

Publishedno release date on file

PriceFree

Referenceimbad0202/academic-paper-academic-paper-writing-agent-team

Versions

v3.3.1 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v3.3.1

No earlier releases have been published to the marketplace.

Pinning

Put imbad0202/academic-paper-academic-paper-writing-agent-team@3.3.1 in the install command to hold this exact version. Without the suffix you get whatever is current the day you install, and nothing moves under you afterwards.

Reviews

—no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Who wrote it

Imbad0202

Publishes on mcprush.

0 servers listed2 skills listednot claimed

Profile

Publisher

Servers0

Claim this skill