Skills DirectorySearch all skills ↗AI agent skill · by @luwill
Research Paper
Use when the user asks to write or draft an ORIGINAL RESEARCH ARTICLE — IMRaD paper, conference paper, short/workshop paper, 研究论文/期刊论文/会议论文 — reporting their own completed experiments, in English or Chinese. Triggers: "write the paper", "draft our manuscript", "把我们这篇工作写成论文", "论文写作". Results-first: the user's actual results (tables, metrics, figures) are the raw material; this skill never invents an experiment or a number. NOT for literature reviews/surveys (use medical-imaging-review), NOT for proposals (use research-proposal), NOT for grant applications.
Archived 2026-10-23 · Source updated 2026-10-10. Check the original repository for the latest version.
SKILL.md instructions
# Research Paper Writer Draft an original research article from the user's **actual completed work**: their experiments, data, figures, and references. Two disciplines govern everything: 1. **Results-first.** Methods and Results are written from materials the user supplied (result tables, metrics dumps, figures, code notebooks). Anything not supplied is flagged `[PENDING: …]` — never filled with a plausible number. A fabricated result is worse than a fabricated citation: it is data fraud, not a style slip. 2. **Citation integrity** (this repository's shared five-rule core, instantiated for author-year/numeric journal styles — see [references/CITATION_INTEGRITY.md](references/CITATION_INTEGRITY.md)): every reference verified to exist before it enters the bibliography; `[UNVERIFIED]` flags for the rest; no invented DOIs, authors, or numbers. ## Scenario routing | Study type | Structure | Binding checklist (Phase 1) | |---|---|---| | Imaging-AI method / model paper | IMRaD, methods-forward | CLAIM 2024 | | Prediction / risk model | IMRaD + model development emphasis | TRIPOD+AI | | Diagnostic accuracy study | IMRaD, test-vs-reference emphasis | **STARD 2015** (可与 CLAIM 并行声明) | | Observational / cohort study | IMRaD, methods after hypotheses | STROBE | | (Rare here) trial, systematic review | **Out of scope** — say so and stop | CONSORT / PRISMA via the right skill | | CS/eng venue paper (CVPR/NeurIPS style) | Abstract → Intro → Related Work → Method → Experiments → Discussion → Conclusion | venue's own checklist/reproducibility statement | Read [references/STRUCTURE_GUIDE.md](references/STRUCTURE_GUIDE.md) for section-by-section construction and [references/REPORTING_CHECKLISTS.md](references/REPORTING_CHECKLISTS.md) for what the binding checklist actually requires. ## Phase 1: Intake (record, don't improvise) Use `AskUserQuestion` to collect: 1. **Study type + target venue/journal** — routes structure and checklist (above). 2. **Materials in hand** — result tables/CSVs, metric numbers, figures, prior drafts/notes, code notebook. If the user has *no results yet*, stop: this skill writes papers about completed work, not imagined work (that is research-proposal territory). 3. **References pool** — user's Zotero/bib, or run the **lit-search** skill for a defensible related-work corpus (its `references.bib` drops straight in). 4. **Language and length** — en/zh; word limit from the venue's guide. Record the intake as a short `paper_plan.md` (study type, venue, checklist, materials list, citation style). Headless runs: record inline and continue. ## Phase 2: Materials audit (before any prose) Inventory every number that will appear in Results: - Each metric → its source artifact (file, table, cell). Untraceable numbers are `[PENDING]`, and the user is told before drafting starts. - Each figure → real file or a `[PENDING: figure]` placeholder with a content description. Redrawing/schematics follow the same honesty rules as scholar-slides (label what is not data). - This inventory becomes `results_ledger.csv` (see [references/QUALITY_CHECKLIST.md](references/QUALITY_CHECKLIST.md)) — the paper-side sibling of the review skill's claim ledger: one row per load-bearing number, `claim_id → section → claim_text → value`（列名以 [references/QUALITY_CHECKLIST.md](references/QUALITY_CHECKLIST.md) 的 schema 表头为准）. ## Phase 3: Outline + approval (red line) Section skeleton per [references/STRUCTURE_GUIDE.md](references/STRUCTURE_GUIDE.md), with per-section bullet content mapped to Phase 2 materials. **Present the outline and wait for explicit approval** (same rules as research-proposal: "你看着办" → state assumptions, re-present, proceed). ## Phase 4: Write-with-verify (per section) Draft section by section **into a single working file `paper_draft.md`** (the Phase 5 gates grep exactly that filename — a renamed draft makes them scan an empty file and report a false zero-hit); after each section, before starting the next: 1. Every citation in the section is from the verified pool (rules: [references/CITATION_INTEGRITY.md](references/CITATION_INTEGRITY.md)). 2. Every number in the section reconciles against `results_ledger.csv`. 3. Self-check against the AI-tell list and style rules ([references/WRITING_STYLE.md](references/WRITING_STYLE.md)) — the Phase 5 grep gates make these checkable, not aspirational. 4. Tense/register per section (Methods: past, what was done; Results: past, what was found — no interpretation; Discussion: present, what it means). ## Phase 5: Gates + reporting checklist + submission pack Mechanical gates (paste command output as evidence): ```bash # 1) Placeholder gate — zero hits (or disclosed [UNVERIFIED]/[PENDING]) grep -nE "xxx|XXXX|\[TBD\]|\[PENDING|\[UNVERIFIED[^]]*\]|10\.xxxx|doi:10\.[a-z]+/x" paper_draft.md # 2) AI-tell gate — zero hits grep -nEi "over the past ((few|several|two|three) )?(decades?|years)|in recent years,|it is worth noting|plays a (crucial|pivotal) role|has garnered significant attention|delves into|a testament to|众所周知|近年来，?随着|日益受到(广泛)?关注" paper_draft.md ``` Then: work through the binding reporting checklist item by item ([references/REPORTING_CHECKLISTS.md](references/REPORTING_CHECKLISTS.md)); assemble the submission pack — title page, abstract in the venue's format, keywords, cover letter, author contributions (CRediT) / conflicts ([references/SUBMISSION_PACK.md](references/SUBMISSION_PACK.md)). ## Reference Files Read **only** the file for the phase you are in. | File | Read when | |------|-----------| | [references/STRUCTURE_GUIDE.md](references/STRUCTURE_GUIDE.md) | Phase 3 — IMRaD construction per study type | | [references/CITATION_INTEGRITY.md](references/CITATION_INTEGRITY.md) | Phase 2/4/5 — the five rules + Phase 5 reconciliation gate | | [references/REPORTING_CHECKLISTS.md](references/REPORTING_CHECKLISTS.md) | Phase 1/5 — checklist selection + item-by-item pass | | [references/WRITING_STYLE.md](references/WRITING_STYLE.md) | Phase 4 — register, tense, cohesion, AI-tells | | [references/SUBMISSION_PACK.md](references/SUBMISSION_PACK.md) | Phase 5 — abstract/cover letter/reproducibility statement | | [references/QUALITY_CHECKLIST.md](references/QUALITY_CHECKLIST.md) | Phase 2/5 — Phase 2 reads the ledger schema; Phase 5 runs the gates | | [assets/paper_scaffold_en.md](assets/paper_scaffold_en.md) | Phase 4 — English skeleton | | [assets/paper_scaffold_zh.md](assets/paper_scaffold_zh.md) | Phase 4 — 中文骨架 | ## learnings：复盘先于重写 修改 references 或 scaffold 之前先扫 [`learnings/`](learnings/)；返工或发现 自相矛盾后追加一篇，日期命名（格式见 lit-search/learnings/）。 ## Error handling - **No results materials** — stop and say so; suggest research-proposal if the work is still planned. - **A claimed number can't be traced** — `[PENDING]` + explicit disclosure, never a placeholder that looks real. - **Reference can't be verified** — `[UNVERIFIED]` + disclosure (never dropped silently, never fabricated). - **Venue requires a checklist this skill doesn't carry** — say so, point to the official source, and record it as a manual gate in `paper_plan.md`.