Openkata Review Rule

Review Rule

Review a rule against the design checklist. No external tooling — rules are validated by reading and checking.

Workflow

1. Identify the rule — Determine which rule to review.

If ambiguous, list available rules and ask.

1. Read the rule — Read RULE.md in full.

1. Run the checklist — Evaluate each section of the

rule design checklist from skills/create-rule/references/rule-design-checklist.md:

• Problem and Scope
• Convention Quality
• Packaging
• Validation
• Portability
• Token Cost

1. Check enforceability — For every convention in the

rule, verify it is literally enforceable. If a convention requires interpretation ("keep it clean", "be consistent"), flag it.

1. Check line count — RULE.md must be under 100 lines.

If over, identify what can move to references/.

1. Check for duplicates — Scan for conventions stated

more than once across sections.

1. Report — Summarize findings per checklist section.

Use ✅ for pass, ⚠️ for minor issues, ❌ for failures.

1. Feed learnings back — After every review, check

whether the findings could improve create-rule or the rule design checklist itself. If a pattern keeps surfacing, ask the user if they want to update the relevant skill so future rules benefit.

When Applying Fixes

• Fix the rule first, then update create-rule if the

issue was a gap in the creation workflow.

• Don't add guidance to create-rule for one-off issues.

Only update it when a pattern repeats across multiple rules.

Example Scenario

User: "Review the bash-style rule."

1. Reads rules/bash-style/RULE.md
2. Evaluates against checklist: Problem/Scope ✅,

Convention Quality ⚠️ (one subjective qualifier found)

1. Reports: 97 lines (under limit), one enforceability

issue flagged, no duplicates

Boundaries

DOES:

• Evaluate rules against the design checklist
• Check enforceability, line count, and duplicates
• Report findings and suggest improvements

Does NOT:

• Fix rules automatically without user confirmation
• Create new rules
• Modify create-rule without asking

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: tovrleaf
• Source: tovrleaf/openkata
• License: MIT

Install and usage instructions live in the source repository linked above.