agentleFS
imMamdouhaboammarimMamdouhaboammar/riqor/.agents/skills/riqor-verification-gate/SKILL.md

riqor-verification-gate

Skill4 starsChanged 3 months agoMITView on GitHub

Use when completing tasks, making changes, or claiming work is done in any codebase monitored by Riqor to enforce empirical verification before completion.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never claim a task is resolved, fixed, or passing based on code edits alone.

    line 9
  2. Very specific:

    If status is verification-pending, a workspace mutation was performed and MUST be verified before finishing.

    line 17
  3. Very specific:

    Run relevant test suites: bun test, npm test, or specific test files.

    line 20
  4. Very specific:

    Run type checking: tsc --noEmit or build scripts.

    line 21
  5. Distinctive:

    Check status & logs: verify exit code 0.

    line 22
  6. Distinctive:

    Only state completion after all verification steps exit cleanly with zero errors.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Riqor Verification Gate

Core Rule

Never claim a task is resolved, fixed, or passing based on code edits alone. Empirical runtime evidence is required before any completion claim.

Execution Flow

  1. Check Session Status:
    riqor terminal status
    If status is verification-pending, a workspace mutation was performed and MUST be verified before finishing.
  2. Execute Targeted Verification:
    • Run relevant test suites: bun test, npm test, or specific test files.
    • Run type checking: tsc --noEmit or build scripts.
    • Check status & logs: verify exit code 0.
  3. Verify Health:
    riqor doctor --json
  4. Claim Completion: Only state completion after all verification steps exit cleanly with zero errors.

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.