OpenClaw Skill Assessment
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_15292d5a/yjkj-skill-assessment.
About this skill
Problem
When evaluating OpenClaw skills, README files and examples often do not reveal practical quality issues: missing documentation, unclear configuration, risky code patterns, or stalled maintenance can affect adoption. skill-assessment provides a lightweight static-analysis perspective for comparing candidates before installation, reviewing a skill before publishing, or batch-inspecting local skill directories.
How It Works
The skill focuses on four scoring dimensions: documentation completeness, code quality, configuration friendliness, and maintenance activity.
- Documentation completeness checks whether usage notes cover the information needed for reliable adoption.
- Code quality looks for quality and safety signals in code, without replacing full SAST or manual audits.
- Configuration friendliness assesses whether options are clear, understandable, and easy to adjust locally.
- Maintenance activity uses versioning and upkeep signals to indicate whether a skill is still evolving.
The report is useful for comparing similar skills, pre-publish review, and batch triage of local skills. It turns “does it look usable?” into a trackable list of weaknesses for follow-up improvements.
Boundaries
skill-assessment performs static analysis; it does not run complex runtime validation or provide security certification. For skills that depend heavily on runtime behavior, private APIs, or organization-specific policy, results should be combined with manual review.
Use Cases
- Compare similar OpenClaw skills before installation using documentation, configuration, and maintenance signals.
- Check documentation completeness, code safety signals, and configuration clarity before publishing a skill.
- Batch-review a local skill directory to find missing docs, unclear config, or stalled maintenance.
- Use the score report to identify documentation or configuration gaps and prioritize follow-up iterations.
Best For
- Developers publishing OpenClaw skills who need a pre-release check of docs, configuration, and versioning signals.
- Platform engineers maintaining team skill directories who need batch triage of local skills and weak maintenance signals.
- Application engineers selecting third-party OpenClaw skills who want quality-scored comparison before integration.
- Tech leads maintaining internal skill repositories who need review results turned into trackable improvement items.
Related Skills
Automatically indexes Gradle-cached AAR/JAR dependency classes and returns library coordinates, versions, and public APIs by fully qualified name, using only the Python standard library.
Codifies AMT and YourMT3 training conventions, script patterns, hyperparameters, precision, checkpoints, and NaN safeguards.
Retrieve relevant chunks from a customer-managed PKM dataset by dataset_id and return concise, source-annotated answers.
Convert PRDs, user stories, or functional specs into prioritized test-point checklists covering functional, business-rule, boundary, exception, and non-functional dimensions.