agentsclimarketplace

Pagekit run check

Skill hnshah/pagekit/skills/pagekit-run-check

Validate a PageKit run folder against the logging tiers (fully-logged / summary-logged / artifact-only / incomplete). Wraps scripts/run-check.sh. Use at the end of a run to confirm the fully-logged tier is met before declaring done.From its SKILL.md

Install
npx -y skills add hnshah/pagekit --skill pagekit-run-check

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

  • 10 stars10 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.

SKILL.md

1.1 KB, as published. Nobody here has run it

PageKit — Validate a Run

Wraps scripts/run-check.sh. Reads a run folder and classifies it per ../pagekit/references/run-logging.md. Lists missing files for the next tier up.

Procedure

  1. Run: bash scripts/run-check.sh runs/<run-name>.
  2. If the result is FULLY LOGGED, report success.
  3. If the result is SUMMARY LOGGED or below, list the missing items to the user and propose what to fill in to reach fully-logged.

When to invoke

  • At the end of any run produced via the pagekit orchestrator skill.
  • Before treating a run as validation evidence or as a public example.
  • When picking up an existing run to extend.

Hard rule

Do not declare a run "done" if pagekit-run-check returns anything other than FULLY LOGGED. The whole point of mechanized checks is to stop logging from being the part that gets skipped.

Keep looking

Skills are one crate of 610,677. 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.