agentleFS
ji-hun-gitji-hun-git/how-to-use-ai/skills/coverage-check/SKILL.md

coverage-check

Skill0 starsChanged 7 days agoMITView on GitHub

Prevents omissions when a task has many requirements or long inputs/outputs. Use when the user gives a list of requirements or constraints, asks to process a long document, transcript or dataset, asks for a long report or translation, or asks to confirm nothing was missed. Numbers the requirements, works section by section, and ends with a coverage table.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Long input: before answering, extract the passages relevant to each requirement (quote them word for word, with location).

    line 14
  2. Distinctive:

    Don't mark a requirement ✅ unless the output actually satisfies it.

    line 25
  3. Distinctive:

    Don't silently drop a requirement because it conflicts with another.

    line 26

≈ “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

Coverage check

The more requirements a task has, the less likely all of them are met, and the longer the input, the less reliably all of it is used. Make coverage explicit instead of hoping for it.

Steps

  1. Number the requirements. Rewrite the user's requirements as R1, R2, R3 … (keep their wording). If there are more than about five hard constraints, propose splitting the work into stages.
  2. Long input: before answering, extract the passages relevant to each requirement (quote them word for word, with location). Go through the whole input, start to end, including the middle.
  3. Long output: produce an outline first, then write one section at a time. Don't compress the end of a long output into "…and so on".
  4. Finish with a coverage table:

    ReqStatus (✅ done / ⚠️ partial / ❌ not done)WhereNote
  5. Report gaps honestly. List anything skipped, shortened or uncertain, and anything you added that wasn't asked for.

Don't

  • Don't mark a requirement ✅ unless the output actually satisfies it.
  • Don't silently drop a requirement because it conflicts with another; flag the conflict and ask which wins.

Evidence

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.