agentleFS
Vezryn-LLCVezryn-LLC/graph-community/skills/change-aware-verification/SKILL.md

change-aware-verification

Skill2 starsChanged 4 days agoApache-2.0View on GitHub

Select proportionate tests and empirical evidence for actual changed behavior.

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:

    Read the diff, current behavior and existing coverage before creating more tests.

    line 8
  2. Distinctive:

    Stop when the requested behavior and actual risks are adequately checked.

    line 14
  3. Very specific:

    Only for an affected interface, run its producer boundary against the real consumer request/parser/adapter at exact source revisions.

    line 24

≈ “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

Change-Aware Verification

  • Read the diff, current behavior and existing coverage before creating more tests.
  • Reproduce demonstrated bugs; verify the repair and meaningful affected integrations.
  • Reuse valid evidence and existing tests; don't rerun unchanged broad suites without reason.
  • Parameterize or consolidate overlapping cases; delete obsolete tests when their contract disappears.
  • Separate simulated checks, integration checks and actual live behavior.
  • Preserve required CI and meaningful security/data-integrity coverage even when extensive.
  • Stop when the requested behavior and actual risks are adequately checked. No mandatory additional reviewer.

Consumed interfaces across repositories

  • Inspect the diff and actual call site when a change may affect a consumed contract: paths/requests, response fields/envelopes, enum/status meanings, defaults/bounds/ pagination, authorization, idempotency/retry/transaction semantics or compatibility version declarations. Inspect the actual producer and consumer source; co-enrollment alone is not a dependency. Include the affected contract and pinned source links in the normal assignment packet when the worker cannot read the other repository.
  • Only for an affected interface, run its producer boundary against the real consumer request/parser/adapter at exact source revisions. Reuse focused tests and producer-generated transport fixtures. Check the current supported/deployed consumer when known; record unknown identity rather than assuming it is main. Label synthetic, isolated runtime and hosted evidence accurately.
  • Internal refactors with unchanged contracts, styling/static Website changes and unrelated files need no extra cross-repo check. Inspect uncertain boundary impact before deciding; no universal matrix, lock or reviewer is required.
  • In the existing PR closeout record both SHAs, surface, command, actual pass/fail, supported/deployed-consumer coverage and limits. Before merge/release inspect whether the relevant interface changed on either side; rerun only impacted checks. Unrelated commits do not invalidate applicable evidence.
  • A red pair is not compatible. Coordinate only the affected linked work using normal source ownership. Prefer expand → migrate consumers → retire old behavior with documented supported installed versions; separate repositories cannot merge atomically.

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.