agentleFS
lowtidebuildlowtidebuild/second-review-agent/.claude/skills/structure-checker/SKILL.md

structure-checker

Skill1 starsChanged 7 months agoApache-2.0View on GitHub

Evaluate structural integrity (Dimension 5) of the reviewed document. This skill runs as part of Step 4 alongside substance-reviewer and writing-quality-reviewer. The main agent updates checkpoint.json only after ALL Step 4 skills complete — see substance-reviewer/SKILL.md for details.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Run in parallel with substance-reviewer and writing-quality-reviewer

    line 28

≈ “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

structure-checker Skill

Evaluate structural integrity (Dimension 5) of the reviewed document.

Capabilities

  1. Numbering Validation (scripts/numbering-validator.py)
    • Checks heading/numbering hierarchy for gaps, duplicates, and violations
    • Korean: 조/항/호/목 hierarchy consistency
    • English: Section/subsection numbering continuity
    • Usage: python3 numbering-validator.py <parsed_structure_json> <output_path>
  2. Cross-Reference Validation (scripts/cross-reference-checker.py)
    • Verifies all internal references point to existing sections
    • Flags orphaned references (target does not exist)
    • Flags unreferenced sections (informational)
    • Usage: python3 cross-reference-checker.py <parsed_structure_json> <output_path>
  3. LLM-Based Structural Review (no script — LLM judgment)
    • Defined-term audit: all defined terms used, all used terms defined
    • Section completeness per document type (uses checklist from library)
    • Heading hierarchy consistency (no Heading3 under Heading1 without Heading2)
    • Cross-references defined-terms.json from document-parser

When to Use

  • WF1 Step 4: Multi-Dimension Substantive Review (Dimension 5 only)
  • Run in parallel with substance-reviewer and writing-quality-reviewer
  • Input: parsed-structure.json, defined-terms.json, document-type checklist from library/checklists/

Output Format

{
  "dimension": 5,
  "severity": "Minor",
  "location": {"section": "제5조", "paragraph_index": 30},
  "description": "번호 갭: 제3조에서 제5조로 건너뜀 (제4조 누락)",
  "recommendation": "제4조가 삭제된 것이라면 번호를 재정렬하거나, 의도적 누락이면 주석 추가",
  "check_type": "numbering_gap"
}

Quality Checks

  • Numbering issues are typically Minor (cosmetic) unless they cause ambiguity in cross-references (then Major)
  • Cross-reference errors are Major if the referenced section contains substantive content
  • Defined-term issues: unused terms are Minor; used-but-undefined terms are Major
  • Missing mandatory sections per document type are Major

Checkpoint

This skill runs as part of Step 4 alongside substance-reviewer and writing-quality-reviewer. The main agent updates checkpoint.json only after ALL Step 4 skills complete — see substance-reviewer/SKILL.md for details.

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.