domains / families / agent-tooling / skill-creator

skill-creator

combined

Create or improve OpenChatCut custom skills. Use whenever the user asks to create a skill, capture a workflow as a skill, write a SKILL.md, add a reusable workflow, 创建技能, 把流程做成技能, 写一个技能, or improve an existing custom skill. Pushy: treat any workflow the user repeats as a skill candidate, even if they do not say "skill". Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

When to use

• create a skill
• capture a workflow as a skill
• write a SKILL.md
• add a reusable workflow
• improve an existing custom skill
• modify and improve existing skills
• measure skill performance
• run evals to test a skill

When not to use

• edit bundled skills
• create skills with malicious content
• create skills that facilitate unauthorized access
• create skills that facilitate data exfiltration

Skill page

Conflict

The four copies overlap on the core loop (capture intent, interview, write SKILL.md, test/iterate) but each contains material steps or constraints the others lack. The Anthropic copy is the only one with a full quantitative eval/benchmark loop and a description-improver step. The OpenAI copy is the only one with a 'degrees of freedom' design principle and a specific agents/openai.yaml UI metadata generation step. The OpenChatCut copy is the only one with environment-specific constraints (slug whitelist, body size limits, manage_skill tool, security rules). The finance-skills copy is the only one with a structural pattern taxonomy (Linear, Router, etc.) and a runtime detection flow. Crowning one would hide these real alternatives.