openkata-optimize-skills
Skill1 starsChanged 17 days agoMITView on GitHub
Improve skills to 95%+ review score with passing evals. Use when the user says "optimize skills", "fix scores", "get skills to 95%", or wants to batch-improve skill quality across the repo.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- openkata-eval-runnerSkill
- openkata-review-ruleSkill
- openkata-review-skillSkill
- openkata-rule-conventionsSkill
- openkata-ryu-releaseSkill
- openkata-skill-conventionsSkill
- 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
8 rules. About 0 are common, 4 are distinctive, and 4 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
When multiple skills are selected, run them as parallel subagents.
- Very specific: line 38
Run tessl commands without asking for confirmation.
- Very specific: line 40
Do not add repo-internal boundaries (publishing, releasing, tagging) to distributable skills.
- Very specific: line 43
After optimization, persist the final score to .tessl-plugin/plugin.json.
- Very specific: line 49
Read scores from plugin.json to find targets
- Distinctive: line 50
Run tessl lint, review, optimize
- Distinctive: line 52
Update create-skill with learned patterns
- Distinctive: line 53
Commit improvements per skill
≈ “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.
Files
Optimize Skills
Improve skills to 95%+ review score with passing evals.
Usage
optimize skills
Workflow
- Select targets — Ask the user: "All skills below 95%,
or a specific skill?" If all, read the
scorefield from eachskills/*/.tessl-plugin/plugin.jsonand list those below 95%. If specific, use the named skill. - Optimize — For each target, follow
openkata-review-skill(lint, review, optimize, checklist) thenopenkata-eval-runner(generate scenarios, run evals). Iterate until both pass 95%+, maximum 3 iterations. If still below after 3 rounds, report the final score and stop. When multiple skills are selected, run them as parallel subagents. - Learn — If you discovered a pattern that consistently
improves scores, update
skills/create-skill/SKILL.mdso future skills benefit. - Commit — One commit per skill.
Constraints
- Run
tesslcommands without asking for confirmation. - Maximum 3 optimization iterations per skill.
- Do not add repo-internal boundaries (publishing, releasing, tagging) to distributable skills. Those belong in openkata-skill-conventions.
- After optimization, persist the final score to
.tessl-plugin/plugin.json.
Boundaries
DOES:
- Read scores from plugin.json to find targets
- Run tessl lint, review, optimize
- Generate eval scenarios and run evaluation
- Update create-skill with learned patterns
- Commit improvements per skill
Does NOT:
- Create new skills
- Publish or release skills
- Modify skills scoring 95%+
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.

