Skill Maker Pro
Paste the following prompt into your AI chat to install this skill:
Please install @user_8d26dabd/skill-maker-pro following https://skillhub.cn/install/skillhub.md.
About this skill
Problem addressed
When a validated workflow, methodology, or script is packaged as an Agent skill, it may still be hard to reuse: trigger words feel unnatural, structure is unclear, quality is hard to judge, and the skill drifts after release. Skill Maker Pro addresses this by turning skill production into a reviewable engineering process.
How it works
- Choose the form first: decide whether the skill should be
scenario-routing,prompt-only, orworkflowshaped, instead of stuffing everything into oneSKILL.md. - Tiered quality gates: use
T1/T2/T3exposure levels to decide which checks are mandatory and which are advisory, so low-exposure local tools are not overburdened. - Structured checks: combine
auto-test.py,PFgates,APanti-patterns, and release checklists; fixP0issues before polishing triggers, examples, and presentation. - Traceable iteration: track evolution with
E0-E3, review existing skills, upgrade versions, and distill sub-skill capabilities.
Boundaries
It focuses on how to build and audit skills; it does not execute domain tasks such as translation, data analysis, or PPT generation. Publishing, overwrite-style changes, and risky external writes require human confirmation.
Use Cases
- Package a personal data-processing script into a skill that other agents can call, with clear trigger words and boundaries.
- Audit an existing skill’s SKILL.md structure, triggers, examples, and quality gates, then fix P0 issues first.
- Check displayName, YAML frontmatter, LF line endings, and auto-test.py reports before publishing to avoid blocked releases.
- Split adjacent skills by responsibility and add related-skill routing instead of merging similar capabilities into one bloated skill.
Best For
- AI agent engineers who want to turn private workflows into reusable team skills
- Meta-skill authors maintaining multiple agent skills with shared quality gates and pre-release checks
- Independent developers preparing to publish prompt methodologies on SkillHub but worried about weak triggers and examples
- Platform skill operators reviewing existing skills against AP anti-patterns and exposure-tier quality gates
Related Skills
Model routing, persistent parameter management, self-check repair, and global default model control for XiaoYi Claw.
Install, update, and manage OpenClaw Skills through SkillHub, with automatic detection after installation.
Provides API endpoints for AI agents to post bottles and graffiti, browse the feed, and interact with likes and comments.
ReqPlan constrains agent development, debugging, and analysis workflows with a seven-stage state machine, checkpoints, quality audits, and local Harness artifacts.