openclaw-skills
Six OpenClaw skills: four-source search, page extraction to Markdown, GitHub repository analysis and dependency checks.
- 55 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The skills send queries to external search services with your keys, and `gitclaw-backup` uploads the agent workspace to a GitHub repository.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/blessonism-openclaw-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skills send queries to external search services with your keys, and `gitclaw-backup` uploads the agent workspace to a GitHub repository.
This is third-party code. Review the repository files before installing.
What it does
openclaw-skills is a set of six independent skills for the OpenClaw agent. `search-layer` queries Brave, Exa, Tavily and Grok at once, scores results by query intent and follows citation chains. `content-extract` turns a URL into clean Markdown and falls back to the MinerU service for sites that resist parsers. `github-explorer` gathers repository data from several sources and writes an assessment. `dependency-tracker` scans skill, npm and pip versions and reports drift, and `gitclaw-backup` syncs the OpenClaw workspace to a GitHub repository. `mineru-extract` wraps the MinerU API for PDF, Office documents and HTML.
Who it is for. OpenClaw users who rely on the agent for research: searching several engines, reading pages and judging other people's repositories.
Good fit when
- Web search is needed with Brave, Exa, Tavily and Grok results merged.
- A WeChat or Zhihu article must become clean Markdown while an ordinary request gets blocked.
- Before choosing a library you want a structured assessment of its GitHub repository.
- The agent workspace must be copied regularly to a repository as a backup.
Not a fit when
- The agent is not OpenClaw: install paths and links in the skills assume its directories.
- There are no keys for search services and no MinerU token: `search-layer` and `mineru-extract` do not work fully without them.
- The agent's built-in search and a single source are enough.
Example request
Use search-layer to find fresh overviews about MCP servers, extract the two best articles to Markdown and write a short summary.Limitations
The README is in Chinese. Installation is manual: clone the repository into `~/.openclaw/workspace/_repos/` and symlink the needed skills into the skills directory; you can also ask OpenClaw to install them from the repository address. `search-layer` needs the Python packages `requests`, `trafilatura`, `beautifulsoup4` and search service keys. The licence is MIT; the last commit dates from October 2026 with nothing after it on the day of review.
How to disable. Remove the skill symlinks from the OpenClaw skills directory and, if wanted, the clone in `_repos/`. Erase keys from environment variables separately.
FAQ
Do I install all six skills?
No. They are independent except `github-explorer`, which needs `search-layer` and `content-extract`. The rest install one by one.
Which keys does search need?
`search-layer` works with Brave, Exa, Tavily and Grok. Keys are needed for the services you want to use and are listed in the configuration section.
What does content-extract do with protected sites?
For WeChat and Zhihu it falls back to MinerU automatically. That needs a service token.
How does the backup reach GitHub?
`gitclaw-backup` syncs the OpenClaw workspace to your repository through `git`. You provide the repository and its access.
Will they work in Claude Code?
The folders contain `SKILL.md`, but paths and install steps assume OpenClaw. Claude Code needs manual adaptation.
Discussion
No questions or reviews yet.
Related
SkillsThree search skills: four-source search scored by intent, deep thread tracing and clean Markdown extraction from pages.
A web research skill: SearXNG searches, Camofox reads pages and CloakBrowser opens sites that check their visitors
Local-first Rust tool for web extraction: scrape, crawl and structured data for LLMs, with a CLI, REST API and MCP server
Three skills and four utilities that let an agent search the web, read pages, pull video subtitles and process media
Six skills for OpenCLI: an agent reads, searches and posts on dozens of sites through your Chrome and repairs adapters.
Official Brave skills that teach an agent to call the Search API for web, news, images, videos, places and page extracts for LLMs
README in short
A table of six skills with dependencies, a diagram of how they connect, three install methods and a search key section.