By nugkta
Personal academic paper-writing pipeline (brainstorm → outline → draft → review → polish) for ML / computational biology venues. Skill-driven architecture: 9 skills hold the procedures, 5 thin agent wrappers, 5 command shortcuts. Opus-by-default. LaTeX from draft onward; markdown earlier. Web research enabled with citation-verification discipline. Repo write requires per-action user confirmation.
Brainstorm a paper from the current repo — dispatch writing-brainstormer in an isolated subagent.
Build a paper outline from findings — dispatch outline-architect in an isolated subagent.
Orchestrator for the full paper-writing pipeline. Detects current stage from papers/<slug>/working/ and dispatches the right agent. Pauses at each checkpoint for user decisions.
Line-level polish of a draft — dispatch prose-polisher in an isolated subagent.
Hostile peer review of a complete draft — dispatch peer-reviewer in an isolated subagent.
Use after outline-architect has produced a section outline. Writes LaTeX prose for ONE section at a time, following the claim-evidence chain exactly. Does NOT change the outline structure.
Use after writing-brainstormer has produced a findings inventory and the user has chosen a thesis. Designs paper structure with section-level claim-evidence chains and word allocation. Does NOT write prose.
Use after a complete draft is assembled. Simulates a critical peer reviewer for ML / computational biology venues. Produces a 0-100 scored review with hostile devil's-advocate paragraph. READ-ONLY — never modifies any file.
Use after a draft is content-complete. Performs LINE-LEVEL edits only — typos, grammar, forbidden-pattern replacement, sentence tightening. Does NOT rewrite arguments, reorganize, or change emphasis.
Use when the user has a repo of experimental results and needs help deciding what to write. Scans the repo, inventories findings, proposes table/figure designs, surfaces narrative hooks. Read-mostly; writes only to papers/<slug>/working/. Does NOT write paper prose.
Style rules for academic prose in ML / computational biology venues. Loaded by draft-writer and prose-polisher to ensure consistent voice and avoid LLM-typical patterns.
Argumentation template for constructing paper sections. Each claim must be paired with explicit evidence and an explicit narrative function. Loaded by outline-architect and draft-writer.
Established figure and table patterns for ML / computational biology papers. Loaded by writing-brainstormer to ground figure suggestions in conventional patterns rather than improvising. Includes references to type-specific guides.
You are writing or editing LaTeX paper sources. This skill governs the **mechanics** of citations, references, equations, figures, and the `[CITE: ...]` / `[CLAIM-NEEDS-EVIDENCE]` / `[NEEDS-AUTHOR-DECISION]` markers. It does not govern voice, argument structure, or claim verification — those are owned by other skills (see §1 Scope).
Use when designing a paper's argumentative skeleton from a findings inventory and a chosen thesis, before any prose is written. Covers skeleton selection (IMRaD/benchmark/position/bio-applied), section-level claim-evidence chain construction, load-bearing claim identification, word-budget allocation, and conclusion-no-new-claims sanity checks.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Personal Claude Code plugin for academic paper writing in ML / computational biology. 9 skills (procedural + reference) + 5 thin agents + 5 commands, designed so the same procedural knowledge can be invoked in main session or in an isolated subagent.
skills/ holds all procedural knowledge. Skills are reusable: load them in main session OR have an agent load them in isolation.agents/ are thin wrappers (~15 lines each). Each agent declares model, tools, and which skills to load — no procedure embedded.commands/ dispatch a specific agent as a subagent (for cases where you want isolation; the same workflow can run in main session without commands).| Skill | Used by |
|---|---|
repo-scanning-protocol | brainstormer |
outline-construction | outline-architect |
peer-review-protocol | peer-reviewer |
prose-editing-discipline | prose-polisher |
latex-conventions | draft-writer, prose-polisher |
claim-evidence-chain | outline-architect, draft-writer, peer-reviewer |
academic-style | draft-writer, prose-polisher |
reviewer-rubric | peer-reviewer |
figure-design-patterns | brainstormer |
All agents run on opus and have WebSearch + WebFetch.
| Agent | Tools (extra to web) | Skills |
|---|---|---|
writing-brainstormer | Read, Glob, Grep, Bash, Write, Edit | repo-scanning-protocol, figure-design-patterns |
outline-architect | Read, Write | outline-construction, claim-evidence-chain |
draft-writer | Read, Write, Edit, Bash | claim-evidence-chain, academic-style, latex-conventions |
peer-reviewer | Read, Glob, Grep | peer-review-protocol, reviewer-rubric, claim-evidence-chain |
prose-polisher | Read, Edit | prose-editing-discipline, academic-style, latex-conventions |
| Command | Dispatches |
|---|---|
/paper-pipeline [slug] [stage] | orchestrator — detects current stage from working/ and runs the right agent; pauses at each checkpoint |
/brainstorm-paper [slug] | writing-brainstormer |
/outline-paper [slug] | outline-architect |
/write-section [slug] [section-id] | draft-writer |
/review-paper [slug] | peer-reviewer |
/polish-paper [slug] | prose-polisher |
You can also invoke any agent directly in main session without a command — the skills load identically.
The full flow is brainstorm → outline → draft → review → polish. Each stage produces a file in papers/<slug>/working/ that the next stage consumes; the user owns the decisions between stages.
| # | Stage | Agent | Produces | You decide before this stage |
|---|---|---|---|---|
| 1 | brainstorm | writing-brainstormer | findings.md | repo path |
| 2 | outline | outline-architect | outline.md | thesis, target venue, word budget |
| 3 | draft | draft-writer (per section, looped) | draft-sections/<id>.tex | section order; you assemble draft.tex |
| 4 | review | peer-reviewer | review.md | review depth; optional reviewer-persona focus |
| 5 | polish | prose-polisher | polished.tex + polish-changelog.md | which reviewer comments to act on; scope |
Two ways to drive it:
/brainstorm-paper, /outline-paper, …). Most explicit; nothing happens you didn't ask for./paper-pipeline <slug>. It detects which artifacts already exist and starts at the earliest missing stage, or starts at [stage] if you pass one explicitly. After each stage it stops, summarizes, and tells you what's next — it never auto-advances. Re-run later to resume from wherever you left off.papers/<paper-slug>/
├── .bibsources # paths to your master .bib files (one per line)
├── refs.bib # plugin-managed; agents append verified entries here
├── working/
│ ├── findings.md
│ ├── outline.md
│ ├── draft-sections/<id>.tex
│ ├── draft.tex # you assemble from draft-sections/
│ ├── review.md
│ ├── polished.tex
│ └── polish-changelog.md
└── final/ # camera-ready (you maintain)
Markdown for findings/outline/review; LaTeX for draft and polish onward. Markdown→LaTeX handoff happens at the outline.md → draft-sections/*.tex boundary.
Hybrid .bibsources lookup chain:
.bib files listed in papers/<slug>/.bibsources → if found, use it.papers/<slug>/refs.bib → if found, use it.papers/<slug>/refs.bib with key lastname2024firstword. Master .bib files are read-only.[CITE: <description>] marker and report in chat.npx claudepluginhub nugkta/paper-writer --plugin paper-writerUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.