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.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/52yuanchangxing/skill-gap-finderWhat This Skill Does
The Skill Gap Finder is a specialized analytical engine for the OpenClaw ecosystem, designed to audit your existing library of AI agent skills. Its primary purpose is to maintain a healthy, efficient, and non-redundant agent infrastructure. By scanning your skill directory, it identifies overlaps in functionality, detects logical gaps in your automation workflows, and highlights potential conflicts where multiple agents might be competing for the same responsibility. Rather than simply managing files, it provides a high-level strategic overview of your skill ecosystem, ensuring that your agent architecture remains scalable and clean.
Installation
To integrate the Skill Gap Finder into your environment, use the OpenClaw command-line interface. Ensure you have the necessary permissions for your skills repository, then execute the following command in your terminal:
clawhub install openclaw/skills/skills/52yuanchangxing/skill-gap-finder
Once installed, the tool will register itself as an available analysis agent, ready to process your local {baseDir}/resources/ and user-defined directories. You may need to specify the path to your target skills folder during the initial configuration.
Use Cases
- Portfolio Auditing: Regularly audit a growing collection of skills to prevent 'skill bloat' and ensure that your automation library remains lean.
- Workflow Optimization: Identify why certain automation loops are failing or overlapping by finding conflicting skill triggers.
- Scaling Strategy: Determine the most impactful next skill to develop by identifying 'missing links' in your current operational capabilities.
- Refactoring Preparation: Use the tool as a precursor to deleting or merging redundant skills, as it provides a safety audit before you perform any manual cleanup.
Example Prompts
- "Scan my current skill library in
/agent/skillsand tell me if any agents are duplicating research tasks." - "I want to improve my data scraping workflow. Can you analyze my current skill set and tell me where the biggest capability gap is?"
- "List all skills that have overlapping responsibilities in my workspace and suggest which ones should be prioritized for consolidation."
Tips & Limitations
- Non-Destructive: The tool is strictly read-only by design. It will not perform deletions or modifications. Always use it to generate a 'dry-run' plan before manual intervention.
- Dependencies: For the best results, ensure your
{baseDir}/resources/spec.jsonis up-to-date, as the tool relies on this metadata to map responsibilities accurately. - Avoiding Hallucinations: The tool is configured to explicitly list 'pending confirmation' items. If it does not have enough information to form a conclusion, it will ask for clarification rather than inventing findings.
- Security: As a read-only analysis tool, it poses no risk to your system integrity. However, when reviewing outputs, ensure you are manually verifying any recommended code deletions or refactors.
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-gap-finder": {
"enabled": true,
"auto_update": true
}
}
}Tags
Flags: file-read
Related Skills
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.
local-rag-index-planner
规划本地知识库的目录、分片粒度、命名、更新时间与访问边界,而不是直接堆 RAG。;use for rag, indexing, knowledge workflows;do not use for 直接部署向量数据库, 忽略权限隔离.
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.
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.
benchmark-lobster-forge
用元认知引导发现值得被做成小龙虾的机会点,并将其收敛为可开箱即用的基准 Agent 小龙虾。