agentleFS
oeveryoevery/rsp/.agents/skills/release-acceptance/SKILL.md

release-acceptance

Skill1 starsChanged 8 days agoMITView on GitHub

Plan and interpret local code checks and proportionate Skill matrix evidence for an exact RSP release candidate. Do not publish, tag, push, approve, or infer model acceptance from offline readiness.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. enix/kube-image-keeper★ 759same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository10 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Read local checks when planning or executing deterministic release validation.

    line 14
  2. Distinctive:

    Read Skill behavior when planning or interpreting evidence for relevant behavior changes.

    line 15
  3. Distinctive:

    Read comparison only for an explicitly requested comparative experiment.

    line 16
  4. Distinctive:

    Read exact candidate when version and release surfaces are final.

    line 17
  5. Very specific:

    Run shared build/package/terminal resources serially.

    line 21
  6. Distinctive:

    After a tool-only failure, diagnose the cause and inspect actual effects before read-only or proven repeat-safe continuation.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Release Acceptance

Select evidence for the current release decision using existing local checks and the Skill runner. Plan checks and interpret results; add no release test engine. Tool observations establish evidence, not approval.

Select the decision and evidence

Establish the exact source/version and composition identity, requested claim, available records and execution authority. A read-only interpretation request authorizes no checks or model calls. Keep simulated records labelled as simulations and historical results attached to their original identities.

  • Read local checks when planning or executing deterministic release validation.
  • Read Skill behavior when planning or interpreting evidence for relevant behavior changes. Actual model execution requires separate cost and execution authority.
  • Read comparison only for an explicitly requested comparative experiment.
  • Read exact candidate when version and release surfaces are final.

Execute only the authorized plan

Run shared build/package/terminal resources serially. Keep named release checks and the shared runner's execution/judge operations exact. Inspection methods may vary only within unchanged goal, scope, authority, baseline and required evidence.

After a tool-only failure, diagnose the cause and inspect actual effects before read-only or proven repeat-safe continuation. Unknown mutation, unsafe one-shot replay, changed authority or missing required evidence stops the affected operation; failure authorizes no automatic retry or rerun.

Preserve original reports and observed failures; do not replace unknowns with nearby evidence. Missing execution authority, authentication, realistic cases, provider capability or required independent review is an explicit gap, not acceptance from prose or static checks. Updates to execution, inputs or composition require fresh execution before behavioral claims.

Return the bounded conclusion

Return selected checks, source and composition identity, results, omissions and the smallest useful next evidence request. That recommendation grants no authority. Local success grants no model acceptance, archive, commit, tag, push, publication, approval or human acceptance. Stop before a separately unauthorized action.

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.