agentsclimarketplace

Capability witness history

Skill jukrap/ai-agent-playbook/skills/ai-harness/capability-witness-history

Reusable AI agent skills, project templates, and guardrails for safer software maintenance and delivery.

Install
npx -y skills add jukrap/ai-agent-playbook --skill capability-witness-history

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

One thing to look at

  • 2 stars2 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.

What its author says it does

Copied from the file, not written here

Use when capability status needs witnesses, baselines, skipped states, or reliability history.

SKILL.md

1.0 KB, as published. Nobody here has run it

Capability Witness History

Use this as the primary AI harness skill for append-only capability evidence, baseline comparison, and reliability history.

Workflow

  1. Choose the capability id, command or check, environment, expected status, baseline source, and comparable scope.
  2. Record an append-only entry with timestamp, version, runtime, status, duration, artifacts, caveats, and skipped/degraded reasons.
  3. Compare against OS, runtime, and capability baselines only when the run is comparable.
  4. Keep witness output in runtime/ until reviewed; report failed, skipped, degraded, and unknown status explicitly.

Reference

Read references/capability-ledger-schema.md for witness entries, status fields, artifact rules, and privacy boundaries.

Read references/regression-baseline-policy.md for comparable baselines, rolling history, regression thresholds, and stop conditions.

Keep looking

Skills are one crate of 328,083. 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.