agentsclimarketplace
Sign in

Skill refine

Skill batteryshark/skill-tap/skills/development/skill-development/skill-refine

Audit and improve a portable skill for contract compliance, triggering, progressive disclosure, script correctness, portability, safety, and verification. Use for skill reviews, pre-publication checks, broken-skill diagnosis, quality scoring, or modernizing an older package to the Skill Tap contract.From its SKILL.md

Install
npx -y skills add batteryshark/skill-tap --skill skill-refine

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

  • 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.

SKILL.md

1.0 KB, 145 tokens by cl100k_base, as published. Nobody here has run it

Refine a Portable Skill

  1. Run bin/skill-refine PATH for objective structural findings.
  2. Read references/review-rubric.md and inspect every referenced file and executable path.
  3. Run each script and primary bin/ command against representative and boundary fixtures.
  4. Compare description claims with actual behavior; prioritize misleading triggers and broken execution over style.
  5. Apply fixes without adding filler, vendor-specific metadata, or hidden sibling dependencies.
  6. Re-run the package validator and forward-test consequential workflows in fresh context.

Use agents/skill-reviewer.md for an independent evidence-based pass.

What ships with it: 4 files

4.3 KB alongside SKILL.md, 2 of them executable

agents/

bin/

references/

scripts/

Gives 0 of the 12 instructions most audit compliance skills give in 145 tokens

Counted across 937 of the 1,487 authors here whose files we hold, read 2026-08-07

  • Fetch latest guidelines before each reviewin 43 of 937, across 3 files
  • Group findings by severityin 43 of 937
  • Check files against all fetched rulesin 42 of 937, across 2 files
  • Output findings in terse file:line formatin 41 of 937, across 3 files
  • Ask user which files to review if none specifiedin 41 of 937, across 3 files
  • Read specified files or prompt user for filesin 39 of 937, across 1 file
  • Generate the audit reportin 33 of 937, across 30 files
  • Assign a severity to every findingin 25 of 937
  • Run automated accessibility scansin 23 of 937, across 13 files
  • Output a markdown audit reportin 22 of 937
  • Map findings to WCAG criteriain 20 of 937, across 10 files
  • Confirm audit scopein 19 of 937, across 9 files

Said here and by no other author read

  • run the refine command for objective structural findings
  • run each script against representative and boundary fixtures
  • compare description claims with actual behavior
  • prioritize misleading triggers and broken execution over style
  • apply fixes without adding filler or vendor-specific metadata
  • forward-test consequential workflows in fresh context

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,834. 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.