clawhub
ClawHub CLI manages agent skills through a command-line interface, enabling users to search and install skills from clawhub.com, update existing installations to specific or latest versions, and publish new or modified skill folders to the registry. Use this skill when you need to discover available agent capabilities, synchronize local skill installations, or contribute new skills to the ClawHub ecosystem.
git clone --depth 1 https://github.com/beita6969/ScienceClaw /tmp/clawhub && cp -r /tmp/clawhub/skills/clawhub ~/.claude/skills/clawhubSKILL.md
# ClawHub CLI Install ```bash npm i -g clawhub ``` Auth (publish) ```bash clawhub login clawhub whoami ``` Search ```bash clawhub search "postgres backups" ``` Install ```bash clawhub install my-skill clawhub install my-skill --version 1.2.3 ``` Update (hash-based match + upgrade) ```bash clawhub update my-skill clawhub update my-skill --version 1.2.3 clawhub update --all clawhub update my-skill --force clawhub update --all --no-input --force ``` List ```bash clawhub list ``` Publish ```bash clawhub publish ./my-skill --slug my-skill --name "My Skill" --version 1.2.0 --changelog "Fixes + docs" ``` Notes - Default registry: https://clawhub.com (override with CLAWHUB_REGISTRY or --registry) - Default workdir: cwd (falls back to OpenClaw workspace); install dir: ./skills (override with --workdir / --dir / CLAWHUB_WORKDIR) - Update command hashes local files, resolves matching version, and upgrades to latest unless --version is set
Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation.
Use the diffs tool to produce real, shareable diffs (viewer URL, file artifact, or both) instead of manual edit summaries.
|
|
|
|
OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.