claude-skill-paper-ecosystem
llms.txt1 starsChanged 3 months agoMITView on GitHub
A Claude Code Agent Skill bundle (MIT, v0.1.0) for writing and reviewing academic papers — position papers, preprints, and journal-style articles for SSRN / arXiv / Zenodo / journal venues. Bundles an orchestrator skill (paper-ecosystem), a draft skill (paper-writing), and five reviewer subagents that must be installed together. The academic counterpart to claude-skill-writing-ecosystem (human-facing) and llms-txt-writer (AI-facing). Status: active; skills/ and agents/ are copied one way from the author's paper workspace (via scripts/sync-from-local.sh), so this copy can trail it between…
In this repository3 other files it gives its agents.
- llms-full.txtllms.txt
- paper-ecosystemSkill
- paper-writingSkill
The file
Files
# claude-skill-paper-ecosystem > A Claude Code Agent Skill bundle (MIT, v0.1.0) for writing and reviewing academic papers — position papers, preprints, and journal-style articles for SSRN / arXiv / Zenodo / journal venues. Bundles an orchestrator skill (`paper-ecosystem`), a draft skill (`paper-writing`), and five reviewer subagents that must be installed together. The academic counterpart to claude-skill-writing-ecosystem (human-facing) and llms-txt-writer (AI-facing). Status: active; `skills/` and `agents/` are copied one way from the author's paper workspace (via `scripts/sync-from-local.sh`), so this copy can trail it between syncs. ## Core documentation - [README.md](README.md): human-facing narrative (components, install, how it works, when to use) - [SKILL.md (paper-ecosystem)](skills/paper-ecosystem/SKILL.md): orchestrator — canonical rules (Source Fidelity, Vocabulary Consistency, Academic Voice, Reader Clarity, Citation Format), role-boundary map - [SKILL.md (paper-writing)](skills/paper-writing/SKILL.md): draft procedure — title, outline, section drafting, abstract, references; claim↔cite 1:1 mapping - [CHANGELOG.md](CHANGELOG.md): release notes (v0.1.0 initial release) ## Bundled agents - [paper-reviewer](agents/paper-reviewer.md): argument flow, claim sharpness, section structure, academic voice; flags missing or misaligned cite pointers (whether the source supports the claim is left to source-fidelity-checker) - [source-fidelity-checker](agents/source-fidelity-checker.md): reads cited primary sources directly; flags drift between paper claim and source - [vocabulary-consistency-checker](agents/vocabulary-consistency-checker.md): term-definition consistency and sub-classification discipline - [clarity-reviewer](agents/clarity-reviewer.md): first-contact reader clarity (coined-term budget, title-axis carry-through) - [citation-formatter](agents/citation-formatter.md): in-text ↔ reference 1:1 mapping, format consistency, DOI/arXiv validity (final gate) ## Install - [install.sh](install.sh): one-command bundler — copies skills/* → ~/.claude/skills/, agents/*.md → ~/.claude/agents/; idempotent, backup-then-overwrite, `--force` / `--dry-run` - SkillsMP `/skills add` installs skills/ only — agents must be copied manually (`cp agents/*.md ~/.claude/agents/`) ## Standard & grounding - [Agent Skills specification](https://agentskills.io/specification): open standard; SKILL.md format. Note: subagents are Claude-Code-specific, so this bundle targets Claude Code - [Authorship Strategy](https://github.com/shimo4228/authorship-strategy): parent project whose papers this bundle serves, concept DOI 10.5281/zenodo.20263316 (the bundle itself has no DOI) ## Sibling skills - [claude-skill-writing-ecosystem](https://github.com/shimo4228/claude-skill-writing-ecosystem): human-facing writing & review (also bundles its six review agents) - [llms-txt-writer](https://github.com/shimo4228/llms-txt-writer): AI-facing documents - [readme-writer](https://github.com/shimo4228/readme-writer): human-facing READMEs - [release-doi](https://github.com/shimo4228/release-doi): repo-level Zenodo deposit, the step after the paper - [shimo4228](https://github.com/shimo4228/shimo4228): the author's hub — the five practice lines, their DOIs, and the author's tools for Claude Code
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.