agentleFS
pradyumnasagarpradyumnasagar/open-research-skills/template/SKILL.md

my-new-skill

Skill8 starsChanged 5 months agoMITView on GitHub

One sentence (max 200 chars) — what the skill does and when to use it.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md
<!-- metadata: category: <one of the 18 categories in spec/category-taxonomy.md> version: 1.0.0 author: Pradyumna Jayaram oversight: medium tags: [lowercase, 3-6, tags] difficulty: beginner | intermediate | advanced sources: <upstream source name, e.g. bioSkills/sequence-io/my-skill> -->

My New Skill

One-line tagline. What's the one thing someone should remember about this skill?

When to use

  • Trigger condition 1 (concrete, specific)
  • Trigger condition 2
  • Trigger condition 3

When NOT to use

  • Anti-trigger 1 (where another skill fits better)
  • Anti-trigger 2

Hard rules

  1. No fabricated citations — every cited work must resolve to a verifiable record (DOI, PMID, arXiv ID, ISBN, URL with retrieval date).
  2. No claim without provenance — every quantitative or factual claim must point to a file, line, table, figure, or external source the agent can show.
  3. No silent failure — every script invocation, API call, or tool use must declare its exit status and what to do on non-zero.

Domain extensions (optional):

  • Domain-specific rule 1.
  • Domain-specific rule 2.

Cross-references

  • related-skill-slug-1 — one-line description.
  • related-skill-slug-2 — one-line description.
  • meta/integrity-audit — 7-mode AI failure-mode checklist (cross-cutting).

Workflow

  1. Step one. Short imperative sentence.
  2. Step two.
  3. Step three.

Code patterns

Pattern 1: <Name>

# Short, copy-pasteable snippet. Include imports inline.
def example(input_path: str) -> dict:
    """One-line docstring."""
    ...

Pattern 2: <Name>

# Another snippet.

Pitfalls

  • Don't do X — why it's wrong and what to do instead.
  • Watch out for Y — the failure mode and how to detect it.

Validation

How do you know it worked?

  • Check 1
  • Check 2

References

Changelog

  • 1.0.0 (2026-XX-XX) — Initial release.

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.