openkata-review-rule
Skill1 starsChanged 18 days agoMITView on GitHub
Reviews a rule against the rule design checklist, validates conventions are enforceable, and checks token cost. Use when the user creates a new rule, updates an existing rule, asks to review a rule, or says "review" in the context of rules.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- openkata-eval-runnerSkill
- openkata-optimize-skillsSkill
- openkata-review-skillSkill
- openkata-rule-conventionsSkill
- openkata-ryu-releaseSkill
- openkata-skill-conventionsSkill
- clear-writingSkill
- commit-conventionsSkill
- create-adrSkill
- create-evalsSkill
- create-profileSkill
- create-ruleSkill
- create-skillSkill
- critical-thinkingSkill
- github-create-prSkill
- git-worktreeSkill
- grill-meSkill
- grill-with-docsSkill
- makefile-conventionsSkill
- spec-workflowSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
If ambiguous, list available rules and ask.
- Very specific: line 38
If over, identify what can move to references/.
- Distinctive: line 44
Use ✅ for pass, ⚠️ for minor issues, ❌ for failures.
- Very specific: line 56
Don't add guidance to create-rule for one-off issues.
- Distinctive: line 57
Only update it when a pattern repeats across multiple rules.
- Distinctive: line 74
Check enforceability, line count, and duplicates
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Review Rule
Review a rule against the design checklist. No external tooling — rules are validated by reading and checking.
Workflow
- Identify the rule — Determine which rule to review. If ambiguous, list available rules and ask.
- Read the rule — Read RULE.md in full.
- 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
- 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.
- Check line count — RULE.md must be under 100 lines.
If over, identify what can move to
references/. - Check for duplicates — Scan for conventions stated more than once across sections.
- Report — Summarize findings per checklist section. Use ✅ for pass, ⚠️ for minor issues, ❌ for failures.
- Feed learnings back — After every review, check
whether the findings could improve
create-ruleor 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-ruleif the issue was a gap in the creation workflow. - Don't add guidance to
create-rulefor one-off issues. Only update it when a pattern repeats across multiple rules.
Example Scenario
User: "Review the bash-style rule."
- Reads
rules/bash-style/RULE.md - Evaluates against checklist: Problem/Scope ✅, Convention Quality ⚠️ (one subjective qualifier found)
- 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-rulewithout asking
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
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.

