agentleFS
Sign inStart free
ray5273ray5273/kr-research-kit/skills/kr-sector-audit/SKILL.md

kr-sector-audit

Skill2 starsChanged 8 days agoMITView on GitHub

Audit an existing Korea sector memo or report for source quality, date consistency, missing sections, number conflicts, overreach, and unsupported claims. Use when the user wants a review of a Korean sector document rather than a rewrite. Output should be findings-first.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Use this skill to review an existing Korea sector document.

    line 8
  2. Distinctive:

    Start from the actual memo or report.

    line 12
  3. Distinctive:

    Do not silently rewrite the document.

    line 15
  4. Distinctive:

    Look for missing citations, stale dates, mixed-date metrics, and unsupported claims.

    line 22
  5. Distinctive:

    Look for missing critical sections, especially sector definition, risks, listed exposure mapping, and source disclosure.

    line 24
  6. Distinctive:

    Read references/workflow.md for the audit checklist.

    line 28
  7. Distinctive:

    Read references/output-format.md for the review format.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Korean Sector Audit

Use this skill to review an existing Korea sector document.

Quick Start

  • Start from the actual memo or report.
  • Focus on factual support, internal consistency, date discipline, and unsupported inference.
  • Lead with findings, ordered by severity.
  • Do not silently rewrite the document. Explain what is wrong and why.

Workflow

  1. Read the document. Identify the intended scope, the claimed numbers, and the source style.
  2. Check support. Look for missing citations, stale dates, mixed-date metrics, and unsupported claims.
  3. Check structure. Look for missing critical sections, especially sector definition, risks, listed exposure mapping, and source disclosure.
  4. Write findings-first. Prioritize bugs in reasoning and factual integrity over style comments.

Read references/workflow.md for the audit checklist. Read references/output-format.md for the review format.

Operating Rules

  • Findings come first.
  • Acknowledge when no material issues are found.
  • Residual risks and testing gaps still belong in the audit even when findings are light.

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.

Check your setup, free