Skip to main content
hc
Submit
toolsSource-backedReview first Safety ✓ Privacy ✓

ClawHub

MIT-licensed OpenClaw skill and plugin registry with a hosted catalog, `clawhub` CLI, npm package, native OpenClaw install flows, SKILL.md publishing, plugin package publishing, vector search, scan status, moderation controls, install lockfiles, and opt-out install telemetry.

by OpenClaw·added 2026-06-18·
CLI
HarnessCLI
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • ClawHub installs agent skills and OpenClaw plugins. Inspect source links, files, changelogs, declared runtime metadata, scan state, and plugin compatibility before installing or updating.
  • `clawhub install`, `openclaw skills install`, and update commands write local skill files and metadata such as `.clawhub/lock.json` and per-skill origin records. Pin important local installs before updating shared workspaces.
  • `clawhub token` prints the stored API token to stdout. Avoid exposing tokens through shell history, CI logs, support transcripts, screenshots, or model prompts.
  • Publishing a skill to ClawHub releases it under MIT-0 according to the skill-format docs; do not publish proprietary, private, customer, or conflicting-license content.
  • Plugin publishing resolves local folders, GitHub repositories, GitHub refs, or archives and checks OpenClaw compatibility metadata. Use `--dry-run`, verify artifacts, and review ClawPack digest/scan output before public release.
  • Scan-held or blocked releases can be hidden from public catalog and install surfaces while remaining visible to owners; do not assume search visibility proves a release is safe or accepted.

Privacy notes

  • The CLI stores API token and registry configuration in the operating-system config directory or the path set by `CLAWHUB_CONFIG_PATH`.
  • Logged-in `clawhub install` may send best-effort install telemetry containing the skill slug and version only; set `CLAWHUB_DISABLE_TELEMETRY=1` to opt out.
  • ClawHub public listings can expose skill files, source links, versions, changelogs, install counts, stars, comments, publisher identity, and scan summaries.
  • Publishing uploads `SKILL.md` plus supporting text files to the hosted registry. Keep secrets, private prompts, customer data, proprietary code, and credentials out of published bundles.
  • Self-hosting ClawHub involves Convex, GitHub OAuth, JWT/JWKS keys, OpenAI embeddings for vector search, file storage, moderation data, and report handling.

Prerequisites

  • Node.js 22 or newer for the published `clawhub` npm CLI.
  • OpenClaw installed and configured when using native `openclaw skills` or `openclaw plugins` install/update commands.
  • A GitHub-backed ClawHub account or API token for publishing, delete/undelete, scan, and other authenticated registry workflows.
  • A valid skill folder with `SKILL.md` when publishing skills, or an OpenClaw-compatible plugin package/source when publishing plugins.
  • A review process for registry content, scan status, changelogs, compatibility metadata, published licenses, and local install destinations before installing into an agent runtime.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
15 minutes
Difficulty
intermediate
Tool listing metadata
Pricing
free
Disclosure
editorial
Application category
DeveloperApplication
Operating system
Cross-platform
Full copyable content
npm install -g clawhub
clawhub --help
clawhub search "calendar"
clawhub inspect @openclaw/demo

openclaw skills search "calendar"
openclaw skills install @openclaw/demo
openclaw plugins install clawhub:<package>

About this resource

Overview

ClawHub is the public registry for OpenClaw skills and plugins. It hosts versioned text-based agent skills built around SKILL.md, plus OpenClaw code plugins and bundle plugins with package metadata, compatibility data, source links, scan summaries, stars, install counters, and moderation state.

Use it when you want an OpenClaw-native way to discover reusable agent skills, inspect them before install, publish skill versions with changelogs, or ship OpenClaw plugin packages through a catalog rather than passing around ad hoc GitHub links.

Install

Install the ClawHub CLI from npm:

npm install -g clawhub
clawhub --help

The upstream docs distinguish two command surfaces:

  • Use native OpenClaw commands when installing into OpenClaw:
openclaw skills search "calendar"
openclaw skills install @openclaw/demo
openclaw skills update --all
openclaw plugins search "calendar"
openclaw plugins install clawhub:<package>
openclaw plugins update --all
  • Use the clawhub CLI for registry-authenticated workflows:
clawhub login
clawhub whoami
clawhub search "calendar"
clawhub inspect @openclaw/demo
clawhub package explore

Capabilities

Area ClawHub Coverage
Skill registry Hosts versioned SKILL.md bundles with supporting text files, semver versions, tags, changelogs, and source links
OpenClaw install flow Native openclaw skills and openclaw plugins commands search, install, and update registry-hosted content
CLI workflows clawhub supports login, device login, whoami, search, explore, inspect, install, update, list, pin, unpin, uninstall, publish, scan, delete, and undelete flows
Plugin catalog Stores OpenClaw code-plugin and bundle-plugin packages with family, trust, capability, compatibility, and artifact metadata
Publishing Publishes skills from folders containing SKILL.md and plugins from local folders, GitHub repos, GitHub refs, URLs, or archives
Search Combines exact matching and OpenAI embedding-backed vector search through the hosted registry stack
Local state Writes .clawhub/lock.json and per-skill .clawhub/origin.json; pinned skills are skipped by update commands and reject force overwrites
Review signals Public listings can include scan summaries, moderation state, version history, changelogs, stars, comments, and install counts
Operator controls CLI supports registry/site/workdir/config overrides, proxy environment variables, token output, and opt-out install telemetry

Use Cases

  • Find and install OpenClaw-compatible agent skills without manually copying SKILL.md folders from random repositories.
  • Publish a skill package with versioning, tags, changelogs, and declared runtime requirements.
  • Publish OpenClaw plugins with compatibility metadata such as plugin API and OpenClaw version support.
  • Inspect a skill or plugin before install, including files, versions, source links, scan status, and metadata.
  • Pin a local install so automated updates do not overwrite a reviewed version.
  • Build a skill review workflow around ClawHub scan reports, moderation state, and source-backed registry metadata.

Source Review

Verified on 2026-06-18:

  • GitHub metadata reported openclaw/clawhub as an MIT-licensed TypeScript repository with the description Skill + Plugin Registry for OpenClaw, a homepage at clawhub.ai, active updates on 2026-06-18, and latest release v0.22.0 published on 2026-06-16.
  • The README describes ClawHub as the public skill registry for OpenClaw, focused on publishing, versioning, and searching text-based agent skills built from SKILL.md plus supporting files.
  • The README states that ClawHub also exposes a native OpenClaw package catalog for code plugins and bundle plugins.
  • The public docs say to use native openclaw commands for installing into OpenClaw, and the separate clawhub CLI for registry authentication, publishing, delete/undelete, and registry-specific workflows.
  • The quickstart documents skill search/install/update commands, plugin search/install/update commands, npm and pnpm CLI installation, GitHub login, skill publishing, plugin publishing, --dry-run, and inspect-before-install commands.
  • docs/cli.md documents the clawhub package and binary, global flags, config file locations, token output, search/explore/inspect/install/update commands, lockfile behavior, pinning, skill publishing, plugin publishing, scan report download, and noninteractive options.
  • docs/telemetry.md states that telemetry is only sent when a user is logged in, runs clawhub install, and telemetry is not disabled; the event contains the skill slug and version, not folder paths, file contents, logs, prompts, or CLI output.
  • docs/skill-format.md documents SKILL.md requirements, accepted text-based supporting files, frontmatter metadata under metadata.openclaw, supported install kinds, 50 MB bundle limit, MIT-0 licensing for published skills, and the lack of paid-skill support.
  • packages/clawhub/package.json declares npm package clawhub, version 0.22.0, MIT license, Node.js >=22, repository directory packages/clawhub, and the clawhub binary.
  • The npm registry metadata for clawhub/latest reported version 0.22.0, an npm tarball, provenance attestation metadata, MIT licensing, and the clawhub/clawdhub binary mapping.

Safety and Privacy

ClawHub is a distribution surface for agent behavior. Treat skills and plugins as code-adjacent content, not as harmless documentation. Inspect files, declared environment requirements, plugin compatibility, source links, changelogs, and scan status before installing into a real OpenClaw workspace.

Publishing is also consequential. Skill uploads become public registry content licensed under MIT-0 on ClawHub. Use --dry-run, keep private material out of bundles, and make sure runtime requirements are declared in SKILL.md so users and scan tools can see what the skill expects.

Logged-in installs may report aggregate install telemetry unless CLAWHUB_DISABLE_TELEMETRY=1 is set. The upstream telemetry docs say the event contains only slug and version, but tokens, registry config, source URLs, and published files still need normal secret-handling discipline.

Duplicate Check

Checked current content/tools/, content/mcp/, content/agents/, content/skills/, guides, README entries, open pull requests, and repository-wide content for ClawHub, openclaw/clawhub, OpenClaw skill registry, OpenClaw plugin registry, clawhub CLI, ClawHub package catalog, and matching source URLs. No dedicated ClawHub entry, exact source URL duplicate, target file, or open duplicate PR was found.

Disclosure

Editorial listing. No paid placement or affiliate link is used. ClawHub is MIT-licensed open-source software; OpenClaw, npm, GitHub, Convex, OpenAI, hosting providers, plugin packages, model providers, and third-party services used by individual skills or plugins may have separate licenses, billing, terms, privacy controls, and operational requirements.

#clawhub#openclaw#agent-skills#skill-registry#plugins#cli#vector-search#moderation

Source citations

Add this badge to your README

Show that ClawHub is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/tools/clawhub.svg)](https://heyclau.de/entry/tools/clawhub)

How it compares

ClawHub side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

FieldClawHub

MIT-licensed OpenClaw skill and plugin registry with a hosted catalog, `clawhub` CLI, npm package, native OpenClaw install flows, SKILL.md publishing, plugin package publishing, vector search, scan status, moderation controls, install lockfiles, and opt-out install telemetry.

Open dossier 		Skills CLI

MIT-licensed `skills` CLI from Vercel Labs for installing, using, finding, listing, updating, removing, and initializing Agent Skills across Claude Code, Codex, Cursor, OpenCode, OpenClaw, Gemini CLI, GitHub Copilot, Windsurf, Zed, and dozens of other agent hosts.

Open dossier 		Google Workspace CLI

Apache-2.0 `gws` command-line tool for Google Workspace APIs with structured JSON output, dynamic Discovery API commands, npm and release installers, Gemini CLI extension metadata, and 100+ bundled Agent Skills.

Open dossier 		Skillshare

MIT-licensed Go CLI for syncing AI agent skills, agents, rules, commands, prompts, and other file-based resources across Codex, Claude Code, OpenClaw, Cursor, Windsurf, Gemini-style targets, and dozens of other AI CLI tools.

Open dossier
Trust
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Categorytoolstoolstoolstools
Sourcesource-backedsource-backedsource-backedsource-backed
AuthorOpenClawVercel LabsGoogle Workspace CLI Contributorsrunkids
Added2026-06-182026-06-182026-06-182026-06-18
Platforms
CLI
CursorCodexCLI
CLI
CursorCodexCLI
Source repo————
Safety notes✓ClawHub installs agent skills and OpenClaw plugins. Inspect source links, files, changelogs, declared runtime metadata, scan state, and plugin compatibility before installing or updating. `clawhub install`, `openclaw skills install`, and update commands write local skill files and metadata such as `.clawhub/lock.json` and per-skill origin records. Pin important local installs before updating shared workspaces. `clawhub token` prints the stored API token to stdout. Avoid exposing tokens through shell history, CI logs, support transcripts, screenshots, or model prompts. Publishing a skill to ClawHub releases it under MIT-0 according to the skill-format docs; do not publish proprietary, private, customer, or conflicting-license content. Plugin publishing resolves local folders, GitHub repositories, GitHub refs, or archives and checks OpenClaw compatibility metadata. Use `--dry-run`, verify artifacts, and review ClawPack digest/scan output before public release. Scan-held or blocked releases can be hidden from public catalog and install surfaces while remaining visible to owners; do not assume search visibility proves a release is safe or accepted.✓Agent Skills are executable instructions for coding agents. Inspect `SKILL.md` and supporting files before installing or using skills from unknown repositories. `skills add`, `skills update`, `skills remove`, and `experimental_sync` can write, replace, symlink, copy, or remove skill folders across many local agent directories. Review `--agent`, `--skill`, `--all`, `--global`, and `--yes` flags before running broad operations. `skills use` can materialize a skill into a temporary directory and print the generated prompt, or start a supported agent interactively with that prompt. Treat untrusted skill text as prompt-bearing code. Symlink install mode keeps a canonical copy and links agent directories to it. Copy mode creates independent copies. Choose deliberately when working across shared repos, Windows environments, containers, or synchronized directories. The CLI includes explicit warnings for OpenClaw community skills in `skills use`; do not bypass those warnings unless you understand the trust model for the selected source. The security audit lookup is best-effort and never blocks installation. A missing or safe-looking audit result is not a substitute for reviewing the skill source.✓`gws` can read, create, update, send, delete, share, upload, export, and administer Google Workspace resources depending on OAuth scopes and the command used. Require user confirmation before agent-initiated Gmail sends, Drive sharing, Calendar changes, Admin SDK actions, Apps Script pushes, file uploads, or destructive operations. Use `--dry-run` for write workflows when supported, and keep OAuth scopes narrow instead of granting broad Workspace access for convenience. The npm package runs a postinstall script that downloads a platform-specific binary from GitHub Releases and verifies the published SHA256 checksum before extracting it. Model Armor sanitization can screen API responses before they reach an agent, but it may send prompt or response content to the configured Google Cloud Model Armor template. The README says this project is under active development and not an officially supported Google product; expect breaking changes before v1.0.✓Skillshare writes into multiple agent skill directories. A bad sync can propagate unsafe, stale, or target-incompatible instructions across every configured AI CLI. Run `skillshare sync --dry-run` before the first sync, after target changes, and before `--force`, especially when local skills already exist in target directories. The README documents shell and PowerShell installers that download and execute release artifacts from GitHub. Inspect installer scripts or use a pinned release/Homebrew path when supply-chain control matters. The Unix installer may use `sudo` when installing to `/usr/local/bin`; review `INSTALL_DIR` and PATH behavior before running in managed environments. The audit engine is a useful gate for prompt injection, hidden Unicode, credential access, data exfiltration, destructive commands, hardcoded secrets, and tamper checks, but it is pattern-based and does not prove a skill is safe. Avoid `--force` and broad include patterns until target filters, `.skillignore`, copy/symlink behavior, and backups have been reviewed.
Privacy notes✓The CLI stores API token and registry configuration in the operating-system config directory or the path set by `CLAWHUB_CONFIG_PATH`. Logged-in `clawhub install` may send best-effort install telemetry containing the skill slug and version only; set `CLAWHUB_DISABLE_TELEMETRY=1` to opt out. ClawHub public listings can expose skill files, source links, versions, changelogs, install counts, stars, comments, publisher identity, and scan summaries. Publishing uploads `SKILL.md` plus supporting text files to the hosted registry. Keep secrets, private prompts, customer data, proprietary code, and credentials out of published bundles. Self-hosting ClawHub involves Convex, GitHub OAuth, JWT/JWKS keys, OpenAI embeddings for vector search, file storage, moderation data, and report handling.✓By default, the CLI can send telemetry to `add-skill.vercel.sh` unless `DISABLE_TELEMETRY` or `DO_NOT_TRACK` is set. Telemetry fields in source include CLI version, CI flag, detected agent name, event type, source, selected skills, selected agents, global flag, source type, update counts, find query, and result counts. Security-audit lookup requests can send the skill source and selected skill slugs to the audit endpoint. Local project and global installs can persist source names, selected skills, agent targets, canonical paths, lock data, symlinks, and copied skill contents on disk. Skill contents used through `skills use` are embedded into the generated prompt and may be sent to the downstream model provider or interactive agent process.✓`gws` can expose emails, attachments, files, folders, shared drives, calendars, contacts, Chat spaces, Docs, Sheets, Slides, Forms, Keep notes, Meet data, Tasks, Classroom data, Apps Script projects, Admin reports, and audit logs. Interactive credentials are encrypted at rest with a key stored in the OS keyring, with a file-key fallback when configured; exported credentials and service-account JSON files are highly sensitive. `GOOGLE_WORKSPACE_CLI_TOKEN` has highest precedence when set; avoid leaking access tokens through shell history, `.env` files, CI logs, support messages, screenshots, or agent prompts. Structured JSON, NDJSON pagination, downloads, `--output` files, log files, and model-visible command output can contain personal, customer, regulated, or confidential Workspace data. Agent skills installed from the repository teach agents how to call `gws`; the data exposure risk is controlled by the authenticated account, scopes, local files, and command approvals.✓Skillshare can read, copy, symlink, collect, audit, back up, commit, push, and pull local skill, agent, rule, command, prompt, and extra files. Skills can contain prompts, workflow instructions, local paths, target-specific rules, credentials by mistake, internal URLs, repository conventions, customer context, or model-provider guidance. Audit reports, backups, UI views, logs, git commits, and synced target directories can reveal the contents of private skills and agent instructions. Remote installs from GitHub, GitLab, Bitbucket, Azure DevOps, or self-hosted Git expose repository URLs and may fetch untrusted content into the local source directory before sync. The README describes Skillshare as local, lightweight, offline-capable, and without telemetry; still treat any configured remotes, git pushes, setup actions, and hosted documentation links as external data flows.
Prerequisites
  • Node.js 22 or newer for the published `clawhub` npm CLI.
  • OpenClaw installed and configured when using native `openclaw skills` or `openclaw plugins` install/update commands.
  • A GitHub-backed ClawHub account or API token for publishing, delete/undelete, scan, and other authenticated registry workflows.
  • A valid skill folder with `SKILL.md` when publishing skills, or an OpenClaw-compatible plugin package/source when publishing plugins.
  • Node.js 18 or newer for the published `skills` npm package.
  • At least one supported agent host installed if using auto-detected targets, such as Claude Code, Codex, Cursor, OpenCode, OpenClaw, Gemini CLI, GitHub Copilot, Windsurf, Zed, or another supported agent.
  • A reviewed skill source from GitHub, GitLab, a git URL, a local path, a direct skill folder, or another supported provider.
  • A decision between project-scoped skills that live under the current repository and global skills that live under the user's home/config directories.
  • Node.js 18 or newer for the npm installer, or a platform-specific prebuilt binary from GitHub Releases.
  • A Google Cloud project and OAuth configuration, either created through `gws auth setup` or configured manually in Google Cloud Console.
  • A Google account or Google Workspace account with access to the target Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, Classroom, Meet, or other APIs.
  • Explicit scope selection for the APIs the agent may use; unverified OAuth apps in testing mode cannot request the full recommended scope set.
  • A supported install path: Homebrew, GitHub release archive, shell installer, PowerShell installer, or GitHub Actions setup action.
  • One or more local AI CLI tools with skill directories, such as Codex, Claude Code, OpenClaw, Cursor, OpenCode, Windsurf, Qwen, Goose, or a custom target.
  • A source directory for reviewed skills, agents, and extras, or a project-level `.skillshare/` configuration for repo-local skills.
  • A policy for symlink, copy, or merge mode per target, especially on Windows or tools that cannot follow symlinks.
Install
npm install -g clawhub
npm install -g skills
npm install -g @googleworkspace/cli
brew install skillshare
Config
{
  "openclawSkills": {
    "search": "openclaw skills search \"calendar\"",
    "install": "openclaw skills install @openclaw/demo",
    "update": "openclaw skills update --all"
  },
  "openclawPlugins": {
    "search": "openclaw plugins search \"calendar\"",
    "install": "openclaw plugins install clawhub:<package>",
    "update": "openclaw plugins update --all"
  },
  "clawhubCli": {
    "login": "clawhub login",
    "publishSkill": "clawhub skill publish ./my-skill --dry-run",
    "publishPlugin": "clawhub package publish <source> --family code-plugin --dry-run"
  }
}
{
  "projectInstall": "npx skills add vercel-labs/agent-skills --skill frontend-design -a claude-code",
  "globalInstall": "npx skills add vercel-labs/agent-skills --skill frontend-design -g -a claude-code -y",
  "temporaryUse": "npx skills use vercel-labs/agent-skills@web-design-guidelines | claude",
  "disableTelemetry": "DISABLE_TELEMETRY=1 npx skills list"
}
{
  "auth": {
    "interactive": "gws auth setup && gws auth login",
    "credentialsFileEnv": "GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE",
    "tokenEnv": "GOOGLE_WORKSPACE_CLI_TOKEN"
  },
  "agentSkills": {
    "all": "npx skills add https://github.com/googleworkspace/cli",
    "drive": "npx skills add https://github.com/googleworkspace/cli/tree/main/skills/gws-drive",
    "gmail": "npx skills add https://github.com/googleworkspace/cli/tree/main/skills/gws-gmail"
  },
  "safety": {
    "previewWrites": "Use --dry-run before write or delete workflows",
    "sanitize": "Use --sanitize or GOOGLE_WORKSPACE_CLI_SANITIZE_TEMPLATE when Model Armor review is required"
  }
}
source: ~/.config/skillshare/skills
mode: merge
targets:
  claude:
    path: ~/.claude/skills
  codex:
    path: ~/.codex/skills
    mode: symlink
  openclaw:
    path: ~/.openclaw/skills
  cursor:
    path: ~/.cursor/skills
    mode: copy
ignore:
  - "**/.git/**"
  - "**/node_modules/**"
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.