agentleFS
clarknova99clarknova99/multi-provider-harness/.agents/skills/verify/SKILL.md

verify

Skill1 starsChanged 4 months agoMITView on GitHub

How to prove a change is good — the project's build+test gate and the honesty rule for reporting results. Use whenever you've made a code change and need to validate it, before claiming any work is done, or when deciding what to run to confirm a fix.

189 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use instinct-export, instinct-import and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TheKREATORSSkill

    instinct-export

    Export instincts from project/global scope to a file

    Also in 3 projects that use this

  • TheKREATORSSkill

    instinct-import

    Import instincts from file or URL into project/global scope

    Also in 3 projects that use this

  • AviadPSkill

    risk-assess

    Assess the risk and blast radius of a proposed code change before implementing it. Evaluates CI impact, framework-wide vs localized scope, rollback path, and identifies blindspots. Use when user says "what's the risk", "is this safe", "assess the impact", "risk assess", "blast radius", or before applying framework-wide or CI-affecting changes. Do NOT use for code quality review (use code-quality) or plan validation (use design-validator).

    Also in 3 projects that use this

  • diego-tobalinaSkill

    build-fix

    Fix build and compilation errors systematically. Run when build fails.

    Also in 6 projects that use this

  • AaravChadhaSkill

    secure

    Security review with a confidence gate - a finding exists only with a concrete exploit scenario and a high/medium/low confidence rating; everything else goes to a worth-hardening list, never inflated. Sweeps five surfaces: auth gates, secrets hygiene, injection and unsafe sinks, unsafe deserialization/crypto/transport, and LLM tool-use trust boundaries. Reports only, never fixes. Use when the user asks for a security review or to check vulnerabilities, secrets, or auth.

    Also in 3 projects that use this

  • ArvorCoSkill

    specify

    Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.

    Also in 10 projects that use this

  • +1 more from TheKREATORS

The file

Files
SKILL.md

Skill: Verify your change

One gate answers "is my change good?" Define it once for the project and run it before every commit. Fill in the real command(s) when you set up the harness:

<verify command>        # e.g. `make check`, `npm test`, `./check.sh`, `cargo test` — build + all tests

Make the gate exit non-zero on the first failure, so it's safe to gate commits on it. If the project has a single wrapper script (recommended), point everything at it so every provider runs the identical gate.

What the gate should cover

  1. Build — compiles/typechecks all targets.
  2. Tests — the full automated suite (unit + whatever integration/UI coverage the project has).
  3. Any project-specific proof — a change to a performance- or correctness-critical path may need an extra check a normal test can't express (a benchmark, a memory/latency self-test, a golden-file diff). Name those here as you add them.

When to run which

  • Any code change: the full gate above is the minimum.
  • Touched a hot/critical path with its own proof: also run that specific check (record the command in the relevant skill).
  • Touched the UI: also confirm the surface actually works (integration/UI test, or a launch-and-confirm if the environment can't drive the UI headlessly).

Honesty rule

Report what actually ran. If you skipped a check, say so. If a test failed, show the output — don't mark work done on a red suite. "It should pass" is not "it passed." This rule is what makes a green claim trustworthy across a provider handoff.

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.