agentleFS
Sign inStart free
PurasAIPurasAI/skillpack-template/AGENTS.md

skillpack-template

AGENTS.md0 starsChanged 5 months agoMITView on GitHub

This directory is a Puras skillpack: a bundle of AI skills deployed and run on Puras. Each top-level folder containing a skill.yaml is one skill — the folder name is the skill name. There is no root manifest; puras.yaml (written by puras init / puras deploy) binds the directory to its remote skillpack and carries the pack page's title/description. - skill.yaml declares the contract: title, description, input_schema, output_schema, optional tools:, optional examples:. - The entrypoint suffix decides the kind: entrypoint:…

  • Reads credentials
  • Installs packages
  • 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 31,774 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 repositoryOne other file it gives its agents.

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    Every skill ends by producing exactly the output_schema fields — agentic skills call the auto-injected set_output tool once.

    line 22

≈ “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

Working on a Puras skillpack

This directory is a Puras skillpack: a bundle of AI skills deployed and run on Puras. Each top-level folder containing a skill.yaml is one skill — the folder name is the skill name. There is no root manifest; puras.yaml (written by puras init / puras deploy) binds the directory to its remote skillpack and carries the pack page's title/description.

The contract

  • skill.yaml declares the contract: title, description, input_schema, output_schema, optional tools:, optional examples:.
  • The entrypoint suffix decides the kind: entrypoint: SKILL.md (+ optional text_model: family/variant) = agentic — the markdown is the agent's system prompt. entrypoint: scripts/x.py:func = deterministic — plain Python; the worker calls func(**inputs) and validates the returned dict.
  • Schemas use the Puras dialect (JSON Schema + extras like type: text, image, video). Input schemas keep an explicit required; output schemas declare fields only (the platform auto-requires and prunes).
  • Every skill ends by producing exactly the output_schema fields — agentic skills call the auto-injected set_output tool once; deterministic skills return the dict.
  • Custom tools under tools: are deterministic Python (file.py:func) callable by this skill's agent. run_subagent runs a bundle *.md prompt or a sibling skill as an isolated subagent.

Dev loop

pip install puras
puras login                      # or set PURAS_API_KEY
puras deploy                     # zip this dir + push a deployment
                                 # (creates the skillpack on first push)
puras run <skill> -i key=value   # submit a job and wait
puras logs <job_id>              # stream a job's events

References

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