agentleFS
Sign inStart free
GitHubKnown publishergithub/squad/.copilot/skills/action-skill-contracts/SKILL.md

action-skill-contracts

Skill3.4k starsChanged 2 months agoMITView on GitHub

Author deterministic skills for operations that change state or invoke external tools

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    Use this skill when authoring or revising a skill that can mutate files, state, repositories, or external systems.

    line 11
  2. Very specific:

    Start with an explicit ## SCOPE: activation conditions, allowed targets, and exclusions.

    line 16
  3. Distinctive:

    Keep one skill focused on one operational boundary.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
SKILL.md

Context

Use this skill when authoring or revising a skill that can mutate files, state, repositories, or external systems. Informational reference skills need not carry operational ceremony.

Patterns

  • Start with an explicit ## SCOPE: activation conditions, allowed targets, and exclusions.
  • Provide an ordered, deterministic workflow. State required inputs, the intended side effect, and the exact validation after each consequential operation.
  • Define STOP conditions for missing prerequisites, ambiguous scope, failed verification, and unavailable tools. A failed precondition must not look like success.
  • Point to a current canonical implementation or workflow when a procedure depends on repository behavior; do not copy volatile values into prose.
  • Keep one skill focused on one operational boundary. Link to related skills rather than combining unrelated governance, release, and documentation procedures.

Examples

archival-integrity defines a verified append-before-trim transaction. gh-aw-enlistment limits mutations through an explicit allowlist and ends with strict compilation.

Anti-Patterns

  • Vague verbs such as “handle,” “ensure,” or “fix” without an observable success condition
  • Side effects that proceed after a failed validation
  • Treating a dated incident workaround as a permanent procedure without reconciling source
  • Adding action ceremony to a purely explanatory skill

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