agentleFS
imtiazrayhanimtiazrayhan/agentscamp-library/skills/code-example-verifier/SKILL.md

code-example-verifier

Skill1 starsChanged 5 days agoMITView on GitHub

Verify documentation code examples against the current repository and toolchain, then fix snippets, imports, commands, and expected output without changing the documented intent. Use when docs examples may be stale, an SDK or API changed, users report copy-paste failures, or before publishing tutorials, READMEs, migration guides, and release documentation.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check prerequisites: Verify supported runtime and package versions, setup steps, imports, public APIs, file paths, environment variables, …

    line 14
  2. Distinctive:

    Fix the source: Update imports, commands, setup, code, output, and cleanup in the documentation.

    line 18

≈ “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

Make documentation examples copy-pasteable and truthful against the current codebase. Do not silently convert real examples into vague pseudocode to make the audit pass.

Workflow

  1. Inventory examples. Find fenced code, inline shell commands, configuration blocks, request examples, imports, package names, paths, environment variables, and claimed output. Group duplicated snippets by canonical source.
  2. Classify execution. Mark each example runnable, compile-only, requires controlled integration, destructive/manual, or pseudocode. Flag unlabeled pseudocode presented as executable code.
  3. Check prerequisites. Verify supported runtime and package versions, setup steps, imports, public APIs, file paths, environment variables, and permissions against the repository—not memory.
  4. Build minimal harnesses. Extract examples into temporary or existing documentation-test fixtures without altering their semantics. Use sanitized local data and mock only external boundaries that the example is not teaching.
  5. Run safely. Execute format, compile/typecheck, and runtime commands as appropriate. Never run destructive, production, billing, or credentialed examples; validate their syntax and document the manual test boundary.
  6. Verify outputs. Assert exit status, response shape, created artifacts, and documented output. Normalize volatile timestamps, ports, IDs, and paths without weakening meaningful assertions.
  7. Fix the source. Update imports, commands, setup, code, output, and cleanup in the documentation. Prefer linking or generating from tested canonical examples when duplication causes drift.
  8. Add repeatable checks. Integrate deterministic examples into the repository's docs test, typecheck, or CI workflow when within scope.
  9. Report exceptions. List examples not executed, why, the risk, and the exact manual verification needed.

[!WARNING] Never execute a documentation command merely because it is fenced as bash. Inspect for deletion, deployment, migration, credential use, external side effects, and production targets first.

Output

Return:

  • an example inventory with classification and verification status
  • documentation edits for every stale or incomplete example
  • harness or CI changes for deterministic examples
  • exact commands run and observed results
  • unverified examples with reason and manual verification procedure
  • duplicated snippets that should be generated from one tested source

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.