agentleFS
ApicurioApicurio/apicurio-registry/.claude/skills/verify-change/SKILL.md

verify-change

Skill958 starsChanged 14 days agoApache-2.0View on GitHub

Verify an existing change against behavioral criteria using tests, reproductions, and explicit evidence gaps. Use when the user asks to check an implementation or invokes /verify-change; report defects without editing implementation or tests.

24 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Read AGENT-VERIFICATION.md at the repository root.

    line 8
  2. Distinctive:

    Run or provide a minimal public-interface reproduction for behavior changes, marking execution status.

    line 21

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “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

Verify a Change

Read AGENT-VERIFICATION.md at the repository root. Follow its shared workflow contract and section 3's evidence requirements. This is a report-only pass: leave implementation and tests unchanged, including during specialist reviews.

  1. Establish the requested diff and revision, including relevant uncommitted files. Reuse agreed criteria and review level. If criteria are absent, infer a short provisional list, label it unconfirmed, and ask the user to confirm intent while continuing independent checks. Ask before proceeding if the scope itself is unclear.
  2. Map each criterion to actual assertions, existing checks, and relevant specialist evidence. Inspect test content rather than trusting test names or prior summaries.
  3. Execute relevant supported checks where feasible. Verify the user's edge case, affected variants, and concrete resulting state as applicable. For fixes, gather expected failing-before/passing-after evidence using a non-destructive setup.
  4. Run or provide a minimal public-interface reproduction for behavior changes, marking execution status. Report absent regression tests or coverage as gaps; do not write tests or fix the implementation during this pass.

Return the shared evidence summary, actionable defects, and pointers to decisions requiring human inspection. Separate executed evidence from proposed checks and static test-quality scores. Stop after reporting; fixes belong in implement-change with agreed criteria. A deeper blind-spot investigation belongs in challenge-change.

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.