skill-pack-composer
把多个 Skill 组合成套装,检查 slug、依赖、资源和定位冲突。;use for skills, bundle, packaging workflows;do not use for 混入重复职责的 skill, 忽略依赖冲突.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/52yuanchangxing/skill-pack-composerWhat This Skill Does
The skill-pack-composer acts as the central orchestration engine for OpenClaw users aiming to bundle multiple individual AI skills into cohesive, deployable packages. Its core function is to ensure that a set of skills works in harmony before deployment, preventing environmental friction and logical errors. It meticulously analyzes your selected skill set, comparing metadata such as slugs, dependency trees, required system resources, and potential address/positioning conflicts. By automating the verification process, it ensures that your custom skill bundles are robust, conflict-free, and maintainable, preventing the common pitfalls of overlapping responsibilities or silent dependency failures.
Installation
To integrate this utility into your development environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/52yuanchangxing/skill-pack-composer
Ensure that you have write permissions to your local OpenClaw skills directory, as the installer will create the necessary directory structure and initialize the default configuration files required for analysis.
Use Cases
- Pre-deployment Verification: Before finalizing a bundle of productivity skills, use this tool to ensure no two skills share the same trigger or namespace slug.
- Dependency Resolution: Identify if two skills in a bundle require incompatible versions of a shared utility or environment variable, allowing you to refactor before deployment.
- Refactoring & Optimization: Analyze existing large-scale bundles to see if any skills exhibit duplicate responsibilities, enabling you to slim down your packages for better performance.
- Standardized Packaging: Ensure that your custom-built skills align with the organization's
spec.jsonrequirements before submitting them to a shared library.
Example Prompts
- "I'm putting together a 'Research Assistant' bundle using these five skills. Can you run a conflict check on their slugs and check if there are any conflicting resource requirements?"
- "Here is my
skill-bundle.jsonfor my new data-analysis pack. Please identify any potential dependency issues and list them as a prioritized checklist." - "I have two skills that both seem to handle file exports. Does this violate the 'no duplicate responsibility' rule? Please analyze my current bundle and suggest which one to keep or how to refactor them."
Tips & Limitations
- Read-Only Approach: This skill is designed for assessment and reporting. It will not perform destructive actions or automatic configuration changes. It treats your files as read-only, making it safe to run at any stage of development.
- Human-in-the-loop: Always treat the generated output as an 'advisory' report. The composer is excellent at identifying technical conflicts, but architectural decisions regarding business logic should always be reviewed by a human.
- Missing Information: If the skill requests information it cannot infer (like custom environment variables), always provide the details clearly. The composer is built to prompt you for 'pending confirmations' rather than hallucinating metadata values.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-52yuanchangxing-skill-pack-composer": {
"enabled": true,
"auto_update": true
}
}
}Tags
Flags: file-read
Related Skills
skill-routing-benchmark
测试多个 Skill 描述是否会路由冲突,并生成正例、反例与负向触发语句。;use for skills, routing, benchmark workflows;do not use for 只给模糊建议, 忽略高度相近的 skill.
skill-readme-rebuilder
从 SKILL.md、脚本与资源反推 README、FAQ 与示例,保持说明一致。;use for skills, readme, docs workflows;do not use for 伪造脚本能力, 跳过真实依赖声明.
skill-market-fit-ranker
对一批 Skill 选题按高频、低门槛、传播性、ROI 和风险做排序。;use for skills, market-fit, prioritization workflows;do not use for 只按个人偏好排序, 忽略发布风险.
skill-risk-splitter
把职责过杂的 Skill 拆成安全版、增强版或多子 Skill,降低扫描和维护风险。;use for skills, refactor, risk workflows;do not use for 为了拆分而失去清晰定位, 隐藏高风险行为.
skill-gap-finder
扫描现有 Skill 套装,找重复、缺口、职责冲突和最该补的空位。;use for skills, bundle, analysis workflows;do not use for 臆造目录内容, 直接删除 skill.