agentsclimarketplace
Sign in

Capture evidence pack

Skill workingclassbuddha/codexmaxxing/skills/capture-evidence-pack

Gather proof that work was done and works: test outputs, screenshots, videos, logs, commands, git diff summaries, environment notes, and known risks. Use after code changes, demos, UI work, experiments, bug fixes, repo packaging, or before handing off a branch or pull request.From its SKILL.md

Install
npx -y skills add workingclassbuddha/codexmaxxing --skill capture-evidence-pack

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 1 command, including `scripts/evidence_manifest.py --root <repo> --out output/evidence/manifest.json`.

SKILL.md

1.4 KB, 235 tokens by cl100k_base, as published. Nobody here has run it

Capture Evidence Pack

Use this skill when the user needs confidence, not just a summary. Evidence should be small, reproducible, and easy to inspect.

Workflow

  1. Decide the proof target: tests, browser flow, CLI command, render, screenshot, endpoint, or file output.
  2. Run the narrowest meaningful automated check first.
  3. Add one product-level smoke test when the work is user-facing.
  4. Save artifacts under the repo's existing output folder, or output/evidence/.
  5. Create a short manifest with commands, files, git commit, and known gaps.
  6. Handoff with pass/fail status and artifact paths.

Good Evidence

  • command output from tests or linters
  • screenshot of the changed UI
  • rendered image/video for visual artifacts
  • endpoint response for API/runtime work
  • generated file with timestamp and command
  • short risk note for anything not tested

Resources

  • Read references/evidence-pack.md for handoff format.
  • Run scripts/evidence_manifest.py --root <repo> --out output/evidence/manifest.json to create a starter manifest.

What ships with it: 3 files

2.3 KB alongside SKILL.md, 1 of them executable

agents/

references/

scripts/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.