agentleFS
lowtidebuildlowtidebuild/second-review-agent/.claude/skills/formatting-reviewer/SKILL.md

formatting-reviewer

Skill1 starsChanged 7 months agoApache-2.0View on GitHub

Evaluate formatting and presentation quality (Dimension 6) via DOCX XML inspection and LLM judgment. After formatting review completes, the main agent updates checkpoint.json: - step_5.status → "completed" - step_5.output → "working/dim6-findings.json" - last_completed_step → 5

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run after Step 4 (substantive review) and before Step 6 (consolidation)

    line 23
  2. Distinctive:

    If DOCX XML is too complex to parse → log limitation, assess from rendered text only

    line 42
  3. Very specific:

    After formatting review completes, the main agent updates checkpoint.json:

    line 48

≈ “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

formatting-reviewer Skill

Evaluate formatting and presentation quality (Dimension 6) via DOCX XML inspection and LLM judgment.

Capabilities

  1. DOCX Format Inspection (scripts/docx-format-inspector.py)
    • Unzips DOCX, inspects word/document.xml and word/styles.xml
    • Checks: font family/size consistency, heading style consistency, table width/alignment, margin uniformity, page break logic, numbering format
    • Reports findings with specific XML element locations
    • Usage: python3 docx-format-inspector.py <docx_path> <output_path>
  2. LLM-Based Presentation Review (no script)
    • Professional appearance assessment
    • Layout balance and readability evaluation
    • Visual hierarchy effectiveness
    • White space usage and page flow

When to Use

  • WF1 Step 5: Formatting & Presentation Review
  • Input: Original DOCX file (not the parsed text — needs access to XML formatting)
  • Run after Step 4 (substantive review) and before Step 6 (consolidation)

Checks Performed

CheckScriptLLM
Font family consistency✓
Font size consistency✓
Heading style consistency✓
Table width/alignment✓
Margin uniformity✓
Page break placement✓✓
Numbering format✓
Professional appearance✓
Layout balance✓
Readability✓

Failure Handling

  • If DOCX XML is too complex to parse → log limitation, assess from rendered text only
  • Script failures are non-blocking for LLM-based assessment
  • Formatting findings are typically Minor or Suggestion severity

Checkpoint

After formatting review completes, the main agent updates checkpoint.json:

  • step_5.status → "completed"
  • step_5.output → "working/dim6-findings.json"
  • last_completed_step → 5

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.