Use when writing or revising CS/AI/ML papers from research notes, code repositories, local literature libraries, target venue requirements, or section-level drafting requests. Triggers include 写论文, 初稿, paper draft, write introduction, write method, full paper outline, section-by-section drafting, 证据闭环, 论文起草, 从零写论文, 逐节写作.
npx skills add https://github.com/joshua-zyy/academic-paper-writer --skill academic-paper-writer
证据闭环型、分节推进的论文编排代理。协调六个子技能:Step 0→1→2→3→4→5→6→7→8→9→10→11→12。
manifest.yaml. It declares always_load files, axes, and references.on_demand.always_load. These are the skill's binding rules — not reference material.stance.md defines core rules, sub-skill boundary, and scope.red-lines.md defines absolute prohibitions. Do not negotiate these.output-contract.md defines file outputs, deliverables, and completion criteria.anti-patterns.md defines known failure modes and their correct alternatives.workflow.md defines the Step 0-12 sequence summary.../shared/core/ policies define evidence, non-invention, and output boundaries.mode, paper_type, section, and language using manifest axes.references/ only when the manifest's references.on_demand condition is satisfied.| Mode | Purpose |
|---|---|
| full-paper-planning | From-scratch full paper (balanced spectrum) |
| section-drafting | Single section, narrowed evidence scope (balanced) |
| section-revision | Local evidence audit + rewrite (fidelity spectrum) |
| related-work-or-citation-pass | Delegate to academic-citation (fidelity spectrum) |
| experiment-evidence-pass | Delegate to academic-experiments (fidelity spectrum) |
| Task | Sub-Skill | Step |
|---|---|---|
| Venue research | academic-venue-research | Step 4 |
| Evidence audit | Probe agent | Step 5 |
| Citation search | academic-citation | Step 6 |
| Experiment audit | academic-experiments | Step 7 |
| Figure generation | academic-figure | Step 9.4 |
| Prose polishing | academic-polishing | Step 9.6 (internal) |
| Draft review | academic-reviser | Step 9.5 / 9.8 |
| Mode | Behavior |
|---|---|
| auto (default) | Auto-advance after Verification; brief progress summary only |
| step-by-step | Pause after each section for user confirmation |
Switch anytime via user request.
| Gate | Trigger | Condition | Failure |
|---|---|---|---|
| E: Venue | Step 1→5 | 若用户提供本地 PDF 文献库,Step 2 已验证 MD 目录;venue-brief.md exists | Blocked |
| A: Evidence | Step 5→9 | >= 1 usable evidence | Degradation or blocked |
| B: Section Citation Readiness | Step 6→9 | Current section has VERIFIED citations, Citation-to-Claim Map, or explicit [REF_NEEDED] debt for key claims | Section-dependent: Intro/RW blocked, Method/Results may proceed with tracked debt |
| C: Verification | Step 9.8→10 | All hard debts closed + thin_draft=no | passed/failed/blocked |
| D: Full-Paper Citation Count | Step 11→output | Total >= min_citations | Warn, allow retry |
| Section | Probes to Dispatch | Strategy |
|---|---|---|
| Introduction | existing_material + local lit deep search + external lit search | Must parallel (3 Tasks) |
| Related Work | existing_material + local lit deep search + external lit search | Must parallel (3 Tasks) |
| Method | code_structure (Module Cards + tensor shapes + forward) + preprocessing | Must parallel |
| Experimental Setup | experiment_setup (hyperparams, dataset split, demographics) | Single probe |
| Results / Ablation | experiment_results (main results, baselines, ablation) | Single probe |
| Discussion | interpretability (interpretability results, network analysis) | Single probe |
Abstract is post-posed, not in initial queue. Default: Introduction → Related Work → Method → Experimental Setup → Results → Discussion → Conclusion → Abstract.
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.
Take joshua-zyy/academic-paper-writer from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.