clawhub-recommender

Recommends popular and highly-rated skills from ClawHub based on user intent and conversation context. Use for: finding new skills, discovering popular tools...

MIT-0 · Free to use, modify, and redistribute. No attribution required.
0 · 128 · 0 current installs · 0 all-time installs
MIT-0
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name/description (recommend ClawHub skills) matches the provided artifacts. The skill is instruction-only and only requires reading bundled reference files to produce recommendations; no unrelated binaries, env vars, or external credentials are requested.
Instruction Scope
Runtime instructions explicitly direct the agent to read local files at /home/ubuntu/skills/clawhub-recommender/references/*. Those reference files are included in the bundle. This is expected for a recommender, but the instructions assume a specific absolute path and an Ubuntu-like layout — if the agent runs in a different environment the paths may not exist. The instructions do not direct the agent to read arbitrary system files, secrets, or send data to unknown endpoints.
Install Mechanism
No install spec or downloads are present (instruction-only). Nothing will be written to disk or executed beyond normal agent behavior, so install risk is low.
Credentials
The skill requests no environment variables, credentials, or config paths. The data it needs (reference markdown files) are bundled with the skill, so there is no disproportionate access requested.
Persistence & Privilege
The skill does not request always:true, does not write persistent configuration, and leaves autonomous invocation at the platform default. It does not claim system-wide privileges or modify other skills.
Assessment
This skill is coherent and low-risk as packaged: it uses only the included reference files to generate recommendations and does not ask for credentials or install code. Before installing or following any recommendation it produces, review the recommended skills' pages yourself — some recommended skills (for example 'capability-evolver' or connectors like 'wacli') can have powerful/automated capabilities and may require additional permissions or carry operational risk. Also verify that your agent environment will expose the skill's reference files at the paths shown (the SKILL.md uses absolute /home/ubuntu/... paths). If you want extra assurance, inspect the linked skill pages and their install commands before running them.

Like a lobster shell, security has layers — review code before you run it.

Current versionv1.0.0
Download zip
latestvk97b22vrq3fmvqz6qzym5y2m6n82qfsf

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

SKILL.md

ClawHub Recommender

This skill helps users discover the best and most popular skills on ClawHub by analyzing their current conversation context and intent.

Core Functionality

The ClawHub Recommender identifies the user's needs and matches them with high-quality, community-vetted skills. It prioritizes skills with high download counts, star ratings, and official status to ensure reliability and performance.

When to Use

  • When a user expresses a need for a specific functionality (e.g., "I need to manage my GitHub issues").
  • When a user asks for general recommendations for popular or useful skills.
  • When a user is performing a task that could be significantly improved by an existing ClawHub skill.

Recommendation Workflow

To provide the most relevant recommendations, follow these steps:

  1. Analyze Context: Identify the user's current task, expressed pain points, or specific requests for new capabilities.
  2. Identify Intent: Map the user's need to a category such as Development, Productivity, Communication, or Search.
  3. Consult References: Read the following reference files to find the best matches:
    • /home/ubuntu/skills/clawhub-recommender/references/popular_skills.md: A curated list of top-rated skills with metrics and descriptions.
    • /home/ubuntu/skills/clawhub-recommender/references/recommendation_logic.md: Guidelines for matching intents to specific skill categories.
  4. Formulate Recommendation: Provide a clear and concise recommendation including the skill name, its popularity metrics, a brief description, and why it is a good fit for the current context.
  5. Provide Installation Details: Include the official link and the installation command (e.g., clawhub install <slug>).

Recommendation Guidelines

CategoryRecommended SkillsKey Metrics
Developmentgithub, fast-io, capability-evolverHigh (Official), 35k+ Downloads
Productivitylinear, byterover, automation-workflowsHigh (Official), 17k+ Downloads
Communicationwacli, bird16k+ Downloads, High
Searchtavily, gogHigh, High

Selection Criteria

  • Popularity: Prioritize skills with over 10,000 downloads or high star counts.
  • Official Status: Prefer official integrations (e.g., github, linear) for stability and security.
  • Contextual Relevance: Ensure the recommended skill directly addresses the user's current task or expressed need.
  • Reliability: Mention verified skills to build trust with the user.

Example Recommendation

Skill Name: GitHub (github) Metrics: High (Official Integration) Description: Manage repositories, issues, and pull requests directly from your agent. Why it fits: Since you are currently working on a React project and need to track your progress, the GitHub skill will allow you to manage your issues and commits seamlessly. Link: GitHub Skill on ClawHub Install Command: clawhub install github

Files

3 total
Select a file
Select a file to preview.

Comments

Loading comments…