agentleFS
Sign inStart free
youyu-codeyouyu-code/research-pipeline-skills/AGENTS.md

research-pipeline-skills

AGENTS.md1 starsChanged 11 days agoApache-2.0View on GitHub

Repository of open-source Agent Skills (Anthropic Agent Skills format) implementing a research pipeline: literature radar → paper cards → synthesis matrix → proposal forging → evidence audit.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository7 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No private data: No credentials, personal absolute paths, usernames, private library names, or session/timestamp directory names …

    line 23
  2. Distinctive:

    Scripts run standalone: No dependency on a local absolute path.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md

Repository of open-source Agent Skills (Anthropic Agent Skills format) implementing a research pipeline: literature radar → paper cards → synthesis matrix → proposal forging → evidence audit.

Layout

skills/<skill-name>/
  SKILL.md          # frontmatter: name + description (≤1024 chars)
  references/       # progressive-disclosure detail layer
  scripts/          # runnable helpers
  assets/           # templates, icons, static resources
  • name matches the folder name: ≤64 chars, lowercase letters / digits / hyphens only.
  • SKILL.md stays lean: trigger conditions, inputs, outputs, routing into references/.
  • Long tables, examples, edge cases live in references/.
  • One cross-skill reference is allowed: proposal-forge → evidence-audit. Everything else is self-contained; do not add routing chains.

Quality gate (before commit)

  • No private data. No credentials, personal absolute paths, usernames, private library names, or session/timestamp directory names (YYYY-MM-DD-HH-MM-SS session folders, _scanMMDD run folders).
  • Scripts run standalone. No dependency on a local absolute path; inputs via arguments.
  • Graceful degradation. Without a Zotero MCP server, the manual path must still work end to end.
  • Judgment rules carry a counter-example. Any rule that tells the agent how to judge (what counts as a defect, a reversal, a valid objection) must ship with at least one worked counter-example showing a plausible-but-wrong application. Definitions alone are not accepted — they get read as courtesy prose.
  • Case library ships in three tiers. Fully generalizable cases go inline (currently ~30). Cases that only carry a generalizable kernel go to references/case-studies.md with private specifics stripped. Cases tied to one paper's numbers are not published at all.

License

Apache-2.0.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free