Help us improve
Share bugs, ideas, or general feedback.
From superpowers
Writes academic papers via 12-agent pipeline: 10 modes, 6 paper types, 5 citation formats. Outputs LaTeX, DOCX, PDF, Markdown. Includes style calibration, writing quality check, peer review simulation.
npx claudepluginhub lunartech-x/superpowers --plugin superpowersHow this skill is triggered — by the user, by Claude, or both
Slash command
/superpowers:academic-paperThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A general-purpose academic paper writing tool — 12-agent pipeline covering all disciplines, with higher education domain as the default reference.
agents/abstract_bilingual_agent.mdagents/argument_builder_agent.mdagents/citation_compliance_agent.mdagents/draft_writer_agent.mdagents/formatter_agent.mdagents/intake_agent.mdagents/literature_strategist_agent.mdagents/peer_reviewer_agent.mdagents/revision_coach_agent.mdagents/socratic_mentor_agent.mdagents/structure_architect_agent.mdagents/visualization_agent.mdexamples/chinese_paper_example.mdexamples/imrad_hei_example.mdexamples/literature_review_example.mdexamples/plan_mode_guided_writing.mdexamples/revision_mode_example.mdexamples/revision_recovery_example.mdreferences/abstract_writing_guide.mdreferences/academic_writing_style.mdWrites philosophy and interdisciplinary academic papers from optimized outline to submission-ready manuscript with chapter-level and final quality validation.
Drafts publication-ready ML/AI papers for top conferences (NeurIPS, ICML, ICLR, ACL, AAAI, COLM) from research repos. Includes LaTeX templates, citation verification via Semantic Scholar/CrossRef, and claim-evidence gating.
Academic writing multi-agent orchestrator. TRIGGER when: user is editing .tex files, reviewing thesis/paper chapters, drafting academic content, checking writing quality, or analyzing research positioning. Coordinates specialist agents in parallel for review, research, drafting, polishing, figure work, bibliography auditing, and literature surveys.
Share bugs, ideas, or general feedback.
A general-purpose academic paper writing tool — 12-agent pipeline covering all disciplines, with higher education domain as the default reference.
v2.5 adds two writing quality features:
shared/style_calibration_protocol.md.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.Minimal command:
Write a paper on the impact of AI on higher education quality assurance
Write a paper on the impact of declining birth rates on private university management strategies
Execution flow:
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
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
Activate 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.
See
references/plan_mode_protocol.mdfor full intent signals and activation rules.
| Scenario | Use Instead |
|---|---|
| Deep research / fact-checking (not paper writing) | deep-research |
| Reviewing a paper (structured review) | academic-paper-reviewer |
| Full research-to-paper pipeline | academic-pipeline |
deep-research| Feature | academic-paper | deep-research |
|---|---|---|
| Primary output | Publishable paper draft | Research report |
| Structure | Journal-ready (IMRaD, etc.) | APA 7.0 report |
| Citation | Multi-format (APA/Chicago/MLA/IEEE/Vancouver) | APA 7.0 only |
| Abstract | Bilingual (zh-TW + EN) | Single language |
| Peer review | Simulated 5-dimension review | Editorial review |
| Output format | LaTeX/DOCX (via Pandoc)/PDF/Markdown | Markdown only |
| Revision loop | Max 2 rounds with targeted feedback | Max 2 rounds |
| # | Agent | Role | Phase |
|---|---|---|---|
| 1 | intake_agent | Configuration interview: paper type, discipline, journal, citation format, output format, language, word count; Handoff detection; Plan mode simplified interview | Phase 0 |
| 2 | literature_strategist_agent | Search strategy design, source screening, annotated bibliography, literature matrix | Phase 1 |
| 3 | structure_architect_agent | Paper structure selection, detailed outline, word count allocation, evidence mapping | Phase 2 |
| 4 | argument_builder_agent | Argument construction, claim-evidence chains, logical flow, counter-argument handling; Plan mode argument stress test | Phase 3 / Plan Step 3 |
| 5 | draft_writer_agent | Section-by-section full draft writing, discipline register adjustment, word count tracking | Phase 4 |
| 6 | citation_compliance_agent | Citation format verification, reference list completeness, DOI checking | Phase 5a |
| 7 | abstract_bilingual_agent | Bilingual abstract (zh-TW + EN), 5-7 keywords each | Phase 5b |
| 8 | peer_reviewer_agent | Simulated double-blind review, five-dimension scoring, revision suggestions (max 2 rounds) | Phase 6 |
| 9 | formatter_agent | Convert to LaTeX/DOCX (via Pandoc)/PDF/Markdown, journal formatting, cover letter, citation format conversion (APA 7 / Chicago / MLA / IEEE / Vancouver) | Phase 7 |
| 10 | socratic_mentor_agent | Plan mode Socratic mentor: chapter-by-chapter guidance, convergence criteria (4 signals), question taxonomy (4 types), INSIGHT extraction | Plan Step 0-3 |
| 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 |
| 12 | revision_coach_agent | Parse unstructured reviewer comments into structured Revision Roadmap; classify, map, and prioritize comments; works standalone without prior pipeline execution | Revision-Coach mode |
LaTeX (.tex + .bib), DOCX (via Pandoc), PDF (via LaTeX or Pandoc), Markdown.
When 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.
APA 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]".
Phase 0: CONFIG -> [intake_agent] -> Paper Configuration Record
Phase 1: RESEARCH -> [literature_strategist] -> Search Strategy + Source Corpus
Phase 2: ARCHITECTURE -> [structure_architect] -> Paper Outline + Evidence Map
Phase 3: ARGUMENTATION -> [argument_builder] -> Argument Blueprint
Phase 4: DRAFTING -> [draft_writer] -> Complete Draft
Phase 5a: CITATIONS -> [citation_compliance] ──┐ -> Citation Audit Report
Phase 5b: ABSTRACT -> [abstract_bilingual] ─┘ -> Bilingual Abstract + Keywords (parallel)
Phase 6: PEER REVIEW -> [peer_reviewer] -> Review Report (max 2 revision loops)
Phase 7: FORMAT -> [formatter] -> Final Output Package
See
references/workflow_phase_details.mdfor detailed per-phase agent behavior and output descriptions.
v3.4.0 compliance (applies to
fullmode): Before finalization,compliance_agentruns 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. Seeshared/raise_framework.md §Scope disclaimer.
Authoritative orchestration block for the v3.6.6 contract-gated phase splits inside
academic-paper fullmode. 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.Applies to
academic-paper fullmode 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. Pipeline boundary unchanged:academic-pipelineStage 2 dispatchesacademic-paperin plan or full mode (full only invokes this protocol); Stage 3 dispatches the separateacademic-paper-reviewerskill (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.
v3.6.6 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.
The 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.
For 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.
### Phase 4a — Writer paper-blind pre-commitment sub-section in academic-paper/agents/draft_writer_agent.md § "v3.6.6 Generator-Evaluator Contract Protocol".writer_full contract JSON + paper metadata only (title, field, word_count).## Acceptance Criteria Paraphrase section + terminal [PRE-COMMITMENT-ACKNOWLEDGED] tag.### Phase 4b — Writer paper-visible drafting + self-scoring sub-section in the same agent file.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, optional Style Profile, optional Knowledge Isolation Directive).## Draft Body → ## Dimension Scores → ## Failure Condition Checks → ## Writer Decision.### Phase 6a — Evaluator paper-blind pre-commitment sub-section in academic-paper/agents/peer_reviewer_agent.md § "v3.6.6 Generator-Evaluator Contract Protocol".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).## Contract Paraphrase + ## Scoring Plan (per-dimension dimension_id / what_to_look_for / what_triggers_block / what_triggers_warn) + terminal [PRE-COMMITMENT-ACKNOWLEDGED] tag.### Phase 6b — Evaluator paper-visible scoring + decision sub-section in the same agent file.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).## Dimension Scores → ## Failure Condition Checks → ## Review Body → ## Evaluator Decision.Mirrors sprint_contract_protocol.md §2 reviewer pattern verbatim:
## v3.6.6 Generator-Evaluator Contract Protocol block, the lint description, and the phase-boundary tag conventions.<phase4a_output> / <phase6a_output> delimiter blocks, upstream drafting artefacts, the paper draft.All 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.
pre_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.
Mode-specific structural check counts, per sprint_contract_protocol.md §4 enumeration convention:
## 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.## 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> only (no full draft / paper content).Retry 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.
## 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).## 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).Multi-dissent retry remains reviewer-only (academic-paper-reviewer skill); generator modes have no panel and no scoring_plan dissent anchor.
Lint count summary across the three modes:
| Phase | Reviewer (zero-touch) | Writer | Evaluator |
|---|---|---|---|
| Phase 1 / 4a / 6a | 5 | 3 | 5 |
| Phase 2 / 4b / 6b | 6 | 4 | 5 |
When 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:
[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).[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).[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):
evaluator_decision=accept or F4 evaluator_decision=accept_with_dissent_note.evaluator_decision=flag_for_reviewer_stage after the in-pair revision loop exhausts at round 2 with mandatory-dimension block recurring.academic-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.
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).
The 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.
The 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.
[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.pre_commitment_history[] ledger entry in Schema 9 to persist the writer Phase 4a artefact across session boundaries; v3.6.6 does not implement.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.See references/mode_selection_guide.md for details.
| Mode | Trigger | Agents | Output |
|---|---|---|---|
full | "Write a paper" | All 9 (+ 11 if quantitative) | Complete paper draft (with figures if applicable) |
outline-only | "Paper outline" | 1->2->3 | Detailed outline + evidence map |
revision | "Revise paper" | 8->5->6 | Revised draft with tracked changes (uses templates/revision_tracking_template.md) |
abstract-only | "Write abstract" | 1->7 | Bilingual abstract + keywords |
lit-review | "Literature review" | 1->2 | Annotated bibliography + synthesis |
format-convert | "Convert to LaTeX" / "Convert citations to [format]" | 9 only | Formatted document; includes citation format conversion (APA 7 / Chicago / MLA / IEEE / Vancouver) |
citation-check | "Check citations" | 6 only | Citation error report |
plan | "guide my paper" / "help me plan my paper" | 1->10->3->4 | Chapter Plan + INSIGHT Collection |
revision-coach | "parse reviews" / "revision roadmap" / "I got reviewer comments" | 12 only | Revision Roadmap + optional Tracking Template + Response Letter Skeleton |
disclosure (v3.2) | "AI disclosure for Nature" / "generate AI usage statement" | 9 only | Venue-specific AI-usage disclosure paragraph(s) + placement instructions |
| Your Situation | Recommended Mode | Spectrum |
|---|---|---|
| Starting from scratch with a clear RQ | full | balanced |
| Need help planning before writing | plan | originality |
| Just need an outline | outline-only | balanced |
| Have a draft, received review feedback | revision | fidelity |
| Have unstructured reviewer comments | revision-coach | balanced |
| Just need an abstract | abstract-only | fidelity |
| Need to check/fix citations | citation-check | fidelity |
| Need to convert format (LaTeX, DOCX) or citation style | format-convert | fidelity |
| Want a systematic literature review paper | lit-review | fidelity |
| Need a venue-specific AI-usage disclosure statement for submission | disclosure | fidelity |
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.
Not 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.
See
references/mode_selection_guide.mdfor trigger-to-mode mappings and the full selection flowchart.
Socratic mode that guides users through paper planning one chapter at a time. Builds a complete Paper Blueprint through structured dialogue.
See
references/plan_mode_protocol.mdfor the full chapter-by-chapter dialogue flow and Paper Blueprint structure.
intake_agent automatically detects deep-research materials (RQ Brief / Bibliography / Synthesis / INSIGHT Collection) and skips redundant steps. See deep-research/SKILL.md Handoff Protocol for the complete handoff material format.
See references/failure_paths.md for details. Quick reference:
| Failure Scenario | Handling Strategy |
|---|---|
| Insufficient research foundation | Recommend running deep-research first |
| Wrong paper structure selected | Return to Phase 2, suggest alternative structure |
| Word count significantly over/under target | Identify problematic chapters, suggest trimming/expansion |
| Citation format entirely wrong | Re-run the entire citation phase |
| Peer review rejection | Analyze rejection reasons, suggest major revision or restructuring |
| Plan mode not converging | Suggest switching to outline-only mode |
| Incomplete handoff materials | List missing items, suggest supplementing or re-running |
| User abandons midway | Save completed Chapter Plan |
See academic-pipeline/SKILL.md for the complete workflow.
See agents/intake_agent.md for the complete field definitions of the Phase 0 configuration interview. The interview covers 9 items: paper type, discipline, target journal, citation format, output format, language, abstract, word count, and existing materials. Outputs a Paper Configuration Record, awaiting user confirmation.
Agent definitions: agents/{agent_name}.md — one file per agent (12 total, matching Agent Team table above).
References (19 files in references/):
apa7_extended_guide, apa7_chinese_citation_guide, citation_format_switcheracademic_writing_style, writing_quality_check, writing_judgment_frameworkpaper_structure_patterns (6 types), abstract_writing_guidehei_domain_glossary (bilingual), journal_submission_guide, latex_template_referencefailure_paths (12 scenarios), mode_selection_guide (10 modes), plan_mode_protocol, workflow_phase_detailscredit_authorship_guide (CRediT 14 roles), funding_statement_guide, statistical_visualization_standardsdisclosure_mode_protocol (venue-specific AI-usage statement generation), venue_disclosure_policies (v1 database: ICLR, NeurIPS, Nature, Science, ACL, EMNLP)deep-research/references/apa7_style_guide.md (base reference, extended here)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).
Examples (5 files in examples/): imrad_hei_example, literature_review_example, plan_mode_guided_writing, chinese_paper_example, revision_mode_example.
Explicit prohibitions to prevent common failure modes:
| # | Anti-Pattern | Why It Fails | Correct Behavior |
|---|---|---|---|
| 1 | AI-typical overused terms | "delve into", "crucial", "it is important to note" = instant AI detection | Use discipline-specific vocabulary; see references/writing_quality_check.md |
| 2 | Em dash abuse | More than 2 em dashes per page signals AI writing | Use parentheses, commas, or restructure the sentence |
| 3 | Throat-clearing openers | "In this section, we will discuss..." adds no information | Start with the claim or finding directly |
| 4 | Uniform paragraph lengths | Every paragraph is 4-5 sentences = monotonous AI rhythm | Vary paragraph length naturally (2-8 sentences) |
| 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 |
| 6 | Sycophantic revision | Accepting all reviewer feedback without critical evaluation | Use REVIEWER_DISAGREE status when reviewer is wrong; justify with evidence |
| 7 | Scope creep during revision | Adding unrequested sections/analyses to "improve" the paper | Revision addresses reviewer concerns only; new content requires explicit user approval |
| 8 | Ignoring failure paths | Continuing despite desk-reject signals or fatal methodology flaws | Check references/failure_paths.md; invoke F11 Desk-Reject Recovery when triggered |
⚠️ IRON RULE: Every paper MUST include: Data Availability Statement, Ethics Declaration, Author Contributions (CRediT), Conflict of Interest Statement, Funding Acknowledgment. 17. AI disclosure statement — every paper must include a statement on AI tool usage 18. Limitations section — explicitly discuss study limitations 19. Ethics statement — when applicable (human subjects, sensitive data)
Follows the user's language. Academic terminology is kept in English. Bilingual abstracts are always provided regardless of the main text language.
academic-paper + tw-hei-intelligence -> Evidence-based HEI paper with real MOE data
academic-paper + deep-research -> Deep research phase -> paper writing phase (auto-handoff)
academic-paper + report-to-website -> Interactive web version of the paper
academic-paper + notebooklm-slides-generator -> Presentation slides from paper
academic-paper + academic-paper-reviewer -> Peer review -> revision loop
| Item | Content |
|---|---|
| Skill Version | 3.1.1 |
| Last Updated | 2026-04-27 |
| Maintainer | Cheng-I Wu |
| Dependent Skills | deep-research v1.0+ (upstream), academic-paper-reviewer v1.0+ (downstream) |
See
references/changelog.mdfor full version history.