ultraskill
Skill22 starsChanged 5 months agoNo licenceView on GitHub
One front door for making creative output and the skills that produce it better. Reads the session and picks a pathway: polish (critique one finished creative and regenerate it, skill untouched), heal (trace blatant defects in an output back to the producing skill, mutate it, regenerate until clean), learn (eval-driven loop that mutates a skill until its assertion pass rate stops rising), or create and improve a skill (skill-creator writes it, then learn and heal run on it). Asks once only when two pathways are equally supported. Triggers: 'ultraskill', 'autoskill', 'polish this', 'critique and redo', 'make this creative better', 'heal this', 'heal the skill', 'fix and prevent', 'output is broken', 'improve skill', 'skill eval', 'benchmark skill', 'optimize skill', 'skill loop', 'self-improve', 'create and improve a skill', 'skill pipeline', 'perfect skill'.
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.
In this repository36 other files it gives its agents.
- agent-controlSkill
- animated-carouselsSkill
- animation-designerSkill
- brainstormingSkill
- brand-image-generatorSkill
- cleanupSkill
- conversion-copywritingSkill
- dan-kennedy-copywriterSkill
- design-motion-principlesSkill
- easy-api-dopplerSkill
- frontend-designSkill
- google-trackingSkill
- hero-section-designerSkill
- hetzner-vpsSkill
- hyros-integrationSkill
- icon-set-creatorSkill
- image-enhancerSkill
- landing-page-auditorSkill
- LGJ-graphicsSkill
- n8n-code-javascriptSkill
- n8n-code-pythonSkill
- n8n-expression-syntaxSkill
- n8n-mcp-tools-expertSkill
- n8n-node-configurationSkill
- n8n-safetySkill
- n8n-validation-expertSkill
- n8n-workflow-patternsSkill
- live-testSkill
- mobile-testSkill
- motion-graphicsSkill
- reeperSkill
- senior-frontendSkill
- social-proof-builderSkill
- tasteSkill
- testimonial-editSkill
- whatsappSkill
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.