agentleFS
IgorBabikovIgorBabikov/Flowcairn/skills/workflow-verification/SKILL.md

workflow-verification

Skill4 starsChanged 54 days agoMITView on GitHub

Link current observable behavior to final source, artifact, environment and scenario evidence.

The file

Files
SKILL.md

Actual result

  • Define the expected observable behavior before implementation. Use relevant existing tests and add meaningful assertions for new behavior; do not mirror implementation details or weaken a failing assertion to obtain green output.
  • Frontend: verify the affected route and interaction in a real browser, including relevant async ordering, failure and keyboard states. Backend: trace request, authorization, handler, real storage/dependency and response; verify retries and denial when affected. Mobile: preserve the existing RN/Expo, Flutter or native stack and verify build plus the scenario on each required available platform.
  • Record the tested artifact/source identity, toolchain, target environment, scenario and completed assertions. A mock is not a real dependency; a simulator is not a physical device; build success is not interaction proof.
  • Zero executed tests, skipped mandatory cases, missing tools/devices, screenshots alone and AI summaries leave the relevant requirement unverified. Use only registered checks through the Executor; instructions grant no additional tools or rights.
  • Classify failures before correcting: implementation, plan, environment, verifier, or process uncertainty. An uncertain write or termination requires reconciliation before repetition. After repair rerun the affected required checks against current artifacts; stale evidence cannot close the requirement.

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.