Skill Factory
Paste the following prompt into your AI chat to install this skill:
Please install @user_4cc88af7/skill-factory-new into your AI assistant according to the guide at https://skillhub.cn/install/skillhub.md.
About this skill
What problem it solves
Many SKILL.md files fail on format. A user may know the desired behavior but not how to write the YAML frontmatter, define capability limits, specify workflow steps, or produce examples. The result is often vague, over-scoped, and not directly usable. Skill Factory narrows the task: turn a natural-language request into an executable SKILL.md.
How it works
It extracts the core requirement, then designs the Skill structure, including name, description, capabilities, workflow, output format, and examples. Generation emphasizes at most 5 capabilities, 3–5 workflow steps, and examples that cover the main input-output paths. It also writes explicit boundaries, such as what the Skill should not do. For complex asks, it recommends splitting the requirement into smaller Skills, merging duplicate capabilities, or sharpening differentiation. It refuses requests involving illegal, discriminatory, fraudulent, or real-person impersonation use cases.
Limits and cautions
This is useful for converting personal tools, expense tracking, schedule management, or copywriting helpers into maintainable SKILL.md files. It does not turn vague product goals into finished systems, and it does not replace review of real business rules, API constraints, or security boundaries. The output is meant for engineers to check whether the trigger scope is accurate, the capabilities are too broad, and the examples demonstrate the core path well enough.
Use Cases
- A solo developer turns an expense-tracking assistant idea into a reviewable SKILL.md draft.
- An operations lead writes a Skill for weekly table consolidation and fixed report generation with clear capabilities and examples.
- A product manager drafts a customer-support tone-check Skill with explicit boundaries and rejection rules.
- A tester checks whether the generated Skill keeps capabilities within a focused five-item limit.
Best For
- Solo developers who want a reviewable SKILL.md draft from a personal tool requirement.
- Operations leads who need to turn recurring reporting or copy-review workflows into reusable Skills.
- Product managers who need capability boundaries, examples, and rejection rules in a review draft.
- Testers who want to check generated Skills for over-scoped capabilities and vague descriptions.
Related Skills
An AI workflow that structures personal knowledge bases, IMA, Yuque, and Feishu content into approved personas for paid WeChat mini-agent deployment.
Local workflow memory with matching and SOP updates.
An OpenClaw live streaming executor that initializes TRTC streaming, starts a real-time dashboard, generates viewer URLs, and continuously reports live events.
Breaks down physical supply chains for super-trends to identify second- and third-layer bottlenecks, runs valuation and reverse checks, and maintains trackable reports.