Use when the user asks to write or draft a PhD / doctoral research proposal, research plan, 研究计划书, or 开题报告 — a forward-looking plan of background, gap, research questions, methodology, timeline, and significance, in English or Chinese. Triggers: "write a research proposal", "PhD proposal", "doctoral

Research Proposal Generator Generate a forward looking academic research proposal — a plan for research not yet done — following flagship academic writing conventions, in English or Chinese. This skill produces the first draft correctly , not a template to be fixed later. Its single most important discipline is citation integrity: a proposal with a fabricated reference is an academic integrity problem, not a style problem. Read [references/CITATION INTEGRITY.md](references/CITATION INTEGRITY.md) before Phase 2. Core Principles Prose first. Proposals read as flowing, connected paragraphs — not bulleted lists. Reserve lists for a focused set of research questions/objectives (2–4 items) and timeline milestones. Never enumerate contributions, methodology, background, or significance as bullets; narrate them. Full rules and examples: [references/WRITING STYLE GUIDE.md](references/WRITING STYLE GUIDE.md). Every citation verified before it is committed. Reference count follows the argument, never a quota — there is no minimum. A PhD proposal typically cites 25–50 sources (humanities often more); a tightly argued 25 beats a padded 45. Every reference must exist (DOI/PMID/arXiv resolves, or Zotero metadata), with author and year matching the source, before it enters the proposal. Unverifiable references are flagged [UNVERIFIED] and disclosed — never fabricated. See [references/CITATION INTEGRITY.md](references/CITATION INTEGRITY.md). Write with verification, not one shot. Draft section by section; verify each section's citations before moving to the next (Phase 4). Do not generate a full multi section proposal with dozens of citations in a single pass — that is the structural cause of hallucinated references. Hedge to the evidence. Use tentative language ("aims to", "may", "is expected to") for proposed work and uncertain claims; state well established facts plainly. Do not over claim ("will prove", "revolutionize"). Avoid the LLM tells. These phrases are AI detector signatures — strip them: "Over the past decade, X has emerged as…", "In recent years,", "It is worth noting that", "plays a crucial/pivotal role", "has garnered significant attention", "delves into", "a testament to". Write specific openings grounded in the actual field instead of generic scene setting. Scenario Routing The default structure below targets PhD/doctoral proposals and academic research plans (Abstract → Introduction → Literature Review → Methodology → Timeline → Significance). Confirm the scenario in Phase 1 and adapt: Request Structure PhD/doctoral proposal, research plan, 研究计划书 Default structure (this skill) 开题报告 (thesis proposal / defense) Default structure, but weight Literature Review and feasibility/existing basis more heavily; keep methodology concrete Humanities dissertation proposal Default + a Chapter Outline section (see [references/DOMAIN TEMPLATES.md](references/DOMAIN TEMPLATES.md)) 基金申请书 / 国自然 / NSF grant Different structure (立项依据 / 研究内容与目标 / 研究方案与可行性 / 研究基础与工作条件 / 经费预算). Tell the user the default 5 section template is not a grant form; adapt headings to the funder's required template and confirm with the user before writing Phase 1: Requirements Gathering Use AskUserQuestion to collect: Research topic / question — core problem to investigate. Scenario — PhD proposal / 开题报告 / research plan / grant (routes structure, see above). Academic domain — STEM (and whether computational/ML — see [references/DOMAIN TEMPLATES.md](references/DOMAIN TEMPLATES.md)), Humanities, or Social Sciences. Output language — English or 中文. Target word count — default ~3,000 words; range 2,000–4,000 (humanities may extend to ~10,000). Optional — target institution/supervisor; existing materials or a Zotero library to draw on. If the topic is too vague to scope a methodology, ask focused clarifying questions before proceeding. Phase 2: Literature Collection (with verification gate) Read [references/LITERATURE WORKFLOW.md](references/LITERATURE WORKFLOW.md) for search strategy and organization. Tool portability. Confirm which tools are available before using tool specific names. Prefer the user's Zotero library (via the mcp zotero tools) for closed access papers; use WebSearch for landscape/trends and WebFetch to open DOI / PubMed / arXiv pages and confirm metadata. If a Zotero/arXiv/PubMed MCP is not connected, fall back to WebSearch + WebFetch . Remind the user to add relevant closed access papers to Zotero. Sources by role: WebSearch for trends, reviews, and terminology; WebFetch on arXiv / PubMed / publisher pages for open access primary sources and metadata; Zotero MCP for the user's own library, annotations, and notes. For journal articles the Crossref REST API ( WebFetch https://api.crossref.org/works/<DOI ) is the highest signal existence+metadata check — it returns clean JSON (title / first author / year / venue), more reliable than parsing a publisher HTML page. Organize candidates by role: background/context, current state of the art, gap identifying, methodology, and related work. Verification gate (do not skip) Before any source is eligible to be cited: 1. Verify each candidate's existence, first author, and year against a first source (DOI/PMID/arXiv page, or Zotero metadata) — Rules 1, 2, 5 of [references/CITATION INTEGRITY.md](references/CITATION INTEGRITY.md). 2. Only take specific findings/numbers from sources whose full text or abstract you actually accessed. Do not write internal results for a paper you could not open. 3. Present the verified candidate list (title, author, year, source/DOI) to the user for a quick sanity check before outlining. Anything that cannot be verified does not enter the reference pool; if the user insists on a half remembered source, flag it [UNVERIFIED] . Non interactive / headless runs. If the skill is invoked without an interactive user (a background agent or pipeline), do not deadlock on step 3: record the verified candidate list inline in the deliverable (or a companion citation verification log.md ) and continue. The recorded list is the audit trail in lieu of a live sanity check. Phase 3: Outline Generation Read [references/STRUCTURE GUIDE.md](references/STRUCTURE GUIDE.md) and [references/DOMAIN TEMPLATES.md](references/DOMAIN TEMPLATES.md) for section by section and domain guidance. Standard Outline (default scenario) Add a Chapter Outline section for humanities proposals. Do NOT include appendices — integrate essential content into the body. Approval gate (RED LINE) Present the outline and wait for explicit user approval before Phase 4. Do not start writing content on an unapproved outline. Ask whether the structure, section emphasis, and scope are acceptable, and whether to add/remove/modify sections. If the user says "you decide" / "你看着办" / defers: state the assumptions you are locking in (scenario, domain, section set, target length, language), present the concrete outline once more as the decision, and proceed only after that — treat silence plus deferral as approval of that stated outline, but still surface the assumptions so the user can veto. If there is no interactive user at all (headless/agent run): record the locked assumptions and the outline inline in the deliverable and treat that recorded outline as approved. This keeps the audit trail without deadlocking on an approval that no one can give. Phase 4: Content Writing (write with verify) Load the scaffold as the writing skeleton and fill it section by section: English → [assets/proposal scaffold en.md](assets/proposal scaffold en.md) 中文 → [assets/proposal scaffold zh.md](assets/proposal scaffold zh.md) Read [references/WRITING STYLE GUIDE.md](references/WRITING STYLE GUIDE.md) and apply it. Key hard rules from it: prose over lists; hedge to evidence; PEEL paragraphs (point → evidence+citation → explanation → link); define abbreviations on first use ("coronary CT angiography (CCTA)"); integrate citations into sentences. Write with verify loop — repeat per section: 1. Draft the section as connected prose, placing (Author, Year) citations only from the Phase 2 verified pool. 2. Immediately verify that section's citations: each in text (Author, Year) has a matching References entry (Rule 3), and every directional/quantitative claim matches its source (Rule 4). See [references/CITATION INTEGRITY.md](references/CITATION INTEGRITY.md). 3. Self check against the LLM tells (Core Principles) and the hallucination red flags in CITATION INTEGRITY.md. 4. Fix any failure in place before starting the next section. Do not accumulate unverified citations across sections. Citation style by domain: STEM/Social Sciences → APA (Author, Year); Humanities → MLA or Chicago; 中文 → GB/T 7714. Keep one style consistent throughout. Figures: suggest 3–5 figures at appropriate locations (not in the Abstract), each with a title, content description, and style note. Format and placement guidance is in [references/WRITING STYLE GUIDE.md](references/WRITING STYLE GUIDE.md). 中文 output: 规范学术语体；hedging（"本研究旨在探讨…" 而非 "本研究将证明…"）；参考文献遵循 GB/T 7714。 Phase 5: Output and Review Save as proposal {topic slug} {YYYY MM DD}.md in the user's working directory. Verify against [references/QUALITY CHECKLIST.md](references/QUALITY CHECKLIST.md). Before delivering, the citation gate must pass: grep nE "xxx XXXX \[TBD\] \[UNVERIFIED\] 10\.xxxx \[. 占位. \]" returns 0 hits — or every remaining [UNVERIFIED] has been explicitly disclosed to the user and never presented as confirmed. Every in text (Author, Year) reconciles with the References list (no orphans either direction). At least 20% of references, and every quantitative/directional claim, spot checked against sources. No placeholder [brackets] or "TBD" left in the body — except applicant specific scaffold fields the user must personalize ( [University/Institution Name] , [Your Field] , [Month Year] ) and [Figure N Suggestion] labels, which are intentional and may remain. Offer format conversion: Reference Files File Read when [references/CITATION INTEGRITY.md](references/CITATION INTEGRITY.md) Before Phase 2 and throughout Phase 4/5 — the 5 citation rules; non negotiable [references/STRUCTURE GUIDE.md](references/STRUCTURE GUIDE.md) Phase 3 — section by section writing guide [references/DOMAIN TEMPLATES.md](references/DOMAIN TEMPLATES.md) Phase 1/3 — STEM (incl. computational/ML), humanities, social sciences differences [references/WRITING STYLE GUIDE.md](references/WRITING STYLE GUIDE.md) Phase 4 — academic writing style, hedging, transitions, figures [references/QUALITY CHECKLIST.md](references/QUALITY CHECKLIST.md) Phase 5 — final verification before delivery [references/LITERATURE WORKFLOW.md](references/LITERATURE WORKFLOW.md) Phase 2 — literature collection workflow [assets/proposal scaffold en.md](assets/proposal scaffold en.md) Phase 4 — English writing skeleton [assets/proposal scaffold zh.md](assets/proposal scaffold zh.md) Phase 4 — Chinese writing skeleton Workflow Summary Phase 1 Requirements (interactive) → Phase 2 Literature + verification gate → Phase 3 Outline + approval red line → Phase 4 Content, section by section write with verify → Phase 5 Output + citation gate + checklist. Error Handling No Zotero results / MCP unavailable — inform the user, fall back to WebSearch + WebFetch on open access sources, suggest adding papers to Zotero and retrying. A reference cannot be verified / looks fabricated — do not write it into the References list. Flag [UNVERIFIED] inline and tell the user; never invent a DOI or author list to complete it. Topic too vague — ask clarifying questions; narrow scope; offer well formed research question examples. Ov

research-proposal