Hook-manager exfiltration chain

HOME=~
root
---
~/.nvm/versions/node/v24.15.0/lib/node_modules/openclaw/skills/

OK   1password
OK   apple-notes
OK   apple-reminders
OK   bear-notes
OK   blogwatcher
OK   blucli
OK   camsnap
OK   clawhub
OK   coding-agent
OK   diagram-maker
OK   eightctl
OK   gemini
OK   gh-issues
OK   gifgrep
OK   github
OK   gog
OK   goplaces
OK   healthcheck
OK   himalaya
OK   mcporter
OK   meme-maker
OK   model-usage
OK   nano-pdf
OK   node-connect
OK   node-inspect-debugger
OK   notion
OK   obsidian
OK   openai-whisper-api
OK   openai-whisper
OK   openhue
OK   oracle
OK   ordercli
OK   peekaboo
OK   python-debugpy
OK   sag
OK   session-logs
OK   sherpa-onnx-tts
OK   skill-creator
OK   songsee
OK   sonoscli
OK   spike
OK   spotify-player
OK   summarize
OK   taskflow-inbox-triage
OK   taskflow
OK   things-mac
OK   tmux
OK   trello
OK   video-frames
OK   weather
OK   xurl

ci.md
providers/vllm.md
providers/openai.md
concepts/context.md
concepts/agent.md
concepts/agent-loop.md
concepts/system-prompt.md
concepts/agent-workspace.md
concepts/multi-agent.md
concepts/features.md
security/THREAT-MODEL-ATLAS.md
cli/path.md
cli/onboard.md
cli/index.md
cli/policy.md
cli/setup.md
cli/skills.md
cli/security.md
cli/config.md
cli/agents.md
cli/migrate.md
cli/plugins.md
cli/doctor.md
cli/configure.md
help/testing.md
help/faq-first-run.md
help/faq.md
help/troubleshooting.md
prose.md
agent-runtime-architecture.md
channels/feishu.md
channels/irc.md
channels/matrix.md
channels/telegram.md
channels/mattermost.md
channels/slack.md
channels/broadcast-groups.md
channels/imessage.md
channels/line.md
channels/nextcloud-talk.md

cli/skills.md:75:`--global`, they target the shared managed skills directory. `list`/`info`/`check`
cli/skills.md:103:| `--global`                       | Targets the shared managed skills directory; cannot combine with `--agent <id>`.                                                                                                                                                                                                  |
cli/skills.md:105:| `update @owner/<slug>`           | Updates a single tracked skill. Add `--global` to target the shared managed skills directory instead of the workspace.                                                                                                                                                            |
cli/skills.md:106:| `update --all`                   | Updates tracked ClawHub installs in the selected workspace, or the shared managed skills directory with `--global`.                                                                                                                                                               |
help/faq.md:282:    Native `openclaw skills install` writes into the active workspace `skills/` directory by default. Add `--global` to install into the shared managed skills directory for all local agents. Install the separate `clawhub` CLI only to publish or sync your own skills. Use `agents.defaults.skills` or `agents.list[].skills` to narrow which agents see shared skills.
clawhub/cli.md:37:`--global` for the shared managed skills directory. Plugin installs need the
install/migrating-claude.md:57:    - Claude skills with a `SKILL.md` file are copied into the OpenClaw workspace skills directory.

cli/skills.md:2:summary: "CLI reference for `openclaw skills` (search/install/update/verify/list/info/check/workshop)"
cli/skills.md:5:  - You want to search ClawHub or install skills from ClawHub, Git, or local directories
cli/skills.md:13:Inspect local skills, search ClawHub, install skills from ClawHub/Git/local
cli/skills.md:14:directories, verify ClawHub skills, and update ClawHub-tracked installs.
cli/skills.md:28:openclaw skills install @owner/<slug>
cli/skills.md:29:openclaw skills install @owner/<slug> --version <version>
cli/skills.md:30:openclaw skills install git:owner/repo
cli/skills.md:31:openclaw skills install git:owner/repo@main
cli/skills.md:32:openclaw skills install ./path/to/skill --as custom-name
cli/skills.md:33:openclaw skills install @owner/<slug> --force
cli/skills.md:34:openclaw skills install @owner/<slug> --force-install
cli/skills.md:35:openclaw skills install @owner/<slug> --acknowledge-clawhub-risk
cli/skills.md:36:openclaw skills install @owner/<slug> --agent <id>
cli/skills.md:37:openclaw skills install @owner/<slug> --global
cli/skills.md:39:openclaw skills update @owner/<slug> --force-install
cli/skills.md:75:`--global`, they target the shared managed skills directory. `list`/`info`/`check`
cli/skills.md:88:Gateway-backed skill dependency installs triggered from onboarding or Skills
cli/skills.md:89:settings use the separate `skills.install` request path instead.
cli/skills.md:103:| `--global`                       | Targets the shared managed skills directory; cannot combine with `--agent <id>`.                                                                                                                                                                                                  |
cli/skills.md:105:| `update @owner/<slug>`           | Updates a single tracked skill. Add `--global` to target the shared managed skills directory instead of the workspace.                                                                                                                                                            |
cli/skills.md:106:| `update --all`                   | Updates tracked ClawHub installs in the selected workspace, or the shared managed skills directory with `--global`.                                                                                                                                                               |
cli/skills.md:109:| `verify` version selector        | `verify` uses `.clawhub/origin.json` for installed ClawHub skills, so it verifies the installed version against the registry it came from. `--version` and `--tag` override the version selector but keep that installed registry when origin metadata exists.                    |
cli/skills.md:118:Resolver-backed GitHub skills rely on ClawHub's install resolver to enforce
cli/migrate.md:132:Running `openclaw migrate codex` in an interactive terminal previews the full plan, then opens checkbox selectors before the final apply confirmation. Skill copy items are prompted first. Use `Toggle all on` or `Toggle all off` for bulk selection. Press Space to toggle rows, or Enter to activate the highlighted row and continue. Planned skills start checked, conflict skills start unchecked, and `Skip for now` skips skill copies for this run while still continuing to plugin selection. When source-installed curated Codex plugins are migratable and `--plugin` was not supplied, migration then prompts for native Codex plugin activation by plugin name. Plugin items start checked unless the target OpenClaw Codex plugin config already has that plugin. Existing target plugins start unchecked and show a conflict hint such as `conflict: plugin exists`; choose `Toggle all off` to migrate no native Codex plugins in that run, or `Skip for now` to stop before applying.
cli/plugins.md:308:Compatible bundles install into the normal plugin root and participate in the same list/info/enable/disable flow. Today, bundle skills, Claude command-skills, Claude `settings.json` defaults, Claude `.lsp.json` / manifest-declared `lspServers` defaults, Cursor command-skills, and compatible Codex hook directories are supported; other detected bundle capabilities are shown in diagnostics/info but are not yet wired into runtime execution.
cli/doctor.md:203:- Doctor warns when skills allowed for the default agent are unavailable in the current runtime environment (missing bins, env vars, config, or OS requirements). `doctor --fix` can disable those unavailable skills with `skills.entries.<skill>.enabled=false`; install/configure the missing requirement instead if you want to keep the skill active.
help/testing.md:891:- Skill install smoke: `pnpm test:docker:skill-install` installs the packed OpenClaw tarball globally in Docker, disables uploaded archive installs in config, resolves the current live ClawHub skill slug from search, installs it with `openclaw skills install`, and verifies the installed skill plus `.clawhub` origin/lock metadata.
help/faq-first-run.md:329:    - **Advanced/full onboarding:** longer when provider sign-in, channel pairing, daemon install, network downloads, or skills need extra setup.
help/faq-first-run.md:478:    7. **Skills** - installs recommended skills and optional dependencies.
help/faq.md:131:    Use managed overrides instead of editing the repo copy. Put changes in `~/.openclaw/skills/<name>/SKILL.md` (or add a folder via `skills.load.extraDirs` in `~/.openclaw/openclaw.json`). Precedence: `<workspace>/skills` -> `<workspace>/.agents/skills` -> `~/.agents/skills` -> `~/.openclaw/skills` -> bundled -> `skills.load.extraDirs`, so managed overrides win over bundled skills without touching git. To install globally but limit visibility to some agents, keep the shared copy in `~/.openclaw/skills` and control visibility with `agents.defaults.skills` / `agents.list[].skills`. Only upstream-worthy edits should go out as PRs against the repo copy.
help/faq.md:135:    Yes: add directories via `skills.load.extraDirs` in `~/.openclaw/openclaw.json` (lowest precedence in the order above). `clawhub` installs into `./skills` by default, which OpenClaw treats as `<workspace>/skills` on the next session. To limit visibility to certain agents, pair with `agents.defaults.skills` or `agents.list[].skills`.
help/faq.md:266:  <Accordion title="How do I install skills on Linux?">
help/faq.md:272:    openclaw skills install @owner/<skill-slug>
help/faq.md:273:    openclaw skills install @owner/<skill-slug> --version <version>
help/faq.md:274:    openclaw skills install @owner/<skill-slug> --force
help/faq.md:275:    openclaw skills install @owner/<skill-slug> --global
help/faq.md:282:    Native `openclaw skills install` writes into the active workspace `skills/` directory by default. Add `--global` to install into the shared managed skills directory for all local agents. Install the separate `clawhub` CLI only to publish or sync your own skills. Use `agents.defaults.skills` or `agents.list[].skills` to narrow which agents see shared skills.
help/faq.md:338:    openclaw skills install @owner/<skill-slug>
help/faq.md:342:    Native installs land in the active workspace `skills/` directory; use `--global` for all local agents, or configure `agents.defaults.skills` / `agents.list[].skills` to limit visibility. Some skills expect Homebrew-installed binaries; on Linux that means Linuxbrew.
help/faq.md:1444:    Rust and WASM can provide stronger isolation for some code classes, but do not solve prompt injection, bad allowlists, public gateway exposure, overbroad tools, or a browser profile already logged in to sensitive accounts. Treat these as the primary controls: keep the Gateway private or authenticated, use pairing and allowlists for DMs/groups, deny or sandbox risky tools for untrusted inputs, install only trusted plugins and skills, and run `openclaw security audit --deep` after config changes.

concepts/system-prompt.md:144:When eligible skills exist, OpenClaw injects a compact `<available_skills>` list (`formatSkillsForPrompt`) with the **file path** and a content-derived `<version>sha256:...</version>` marker per skill. The prompt instructs the model to use `read` to load the SKILL.md at the listed location (workspace, managed, or bundled), and to re-read a skill when its `<version>` differs from a previous turn. If no skills are eligible, the Skills section is omitted.
concepts/multi-agent.md:35:Skills load from each agent workspace plus shared roots such as `~/.openclaw/skills`, then filter by the effective agent skill allowlist. Use `agents.defaults.skills` for a shared baseline and `agents.list[].skills` for a per-agent replacement (explicit entries replace the default, they do not merge). See [Skills: per-agent vs shared](/tools/skills#per-agent-vs-shared-skills) and [Skills: agent allowlists](/tools/skills#agent-allowlists).
help/faq.md:131:    Use managed overrides instead of editing the repo copy. Put changes in `~/.openclaw/skills/<name>/SKILL.md` (or add a folder via `skills.load.extraDirs` in `~/.openclaw/openclaw.json`). Precedence: `<workspace>/skills` -> `<workspace>/.agents/skills` -> `~/.agents/skills` -> `~/.openclaw/skills` -> bundled -> `skills.load.extraDirs`, so managed overrides win over bundled skills without touching git. To install globally but limit visibility to some agents, keep the shared copy in `~/.openclaw/skills` and control visibility with `agents.defaults.skills` / `agents.list[].skills`. Only upstream-worthy edits should go out as PRs against the repo copy.
help/faq.md:471:    Your **workspace** (AGENTS.md, memory files, skills, etc.) is separate, configured via `agents.defaults.workspace` (default: `~/.openclaw/workspace`).
tools/skills.md:91:      { id: "docs", skills: ["docs-search"] }, // replaces defaults entirely
tools/skills.md:193:    then install with `skills.install({ source: "upload", ... })`. This path is
tools/skills.md:194:    off by default and requires `skills.install.allowUploadedArchives: true` in
tools/skills-config.md:311:      { id: "docs", skills: ["docs-search"] }, // replaces defaults entirely
releases/2026.6.11.md:250:- Canvas, Discord, Slack, Voice Call, and WhatsApp users keep the same skill guidance with each installed or bundled plugin, while references to the former root `skills/...` paths need to move into the relevant plugin directory. [#95664](https://github.com/openclaw/openclaw/pull/95664) Thanks @vincentkoc.
platforms/mac/skills.md:22:- Otherwise the gateway picks one preferred installer using current install preferences (`skills.install.preferBrew`, `skills.install.nodeManager`) and host binaries: Homebrew first when `preferBrew` is enabled and `brew` is present, then `uv`, then the configured node manager, then Homebrew again if available (even without `preferBrew`), then `go`, then `download`.
gateway/config-agents.md:48:    defaults: { skills: ["github", "weather"] },
gateway/config-agents.md:51:      { id: "docs", skills: ["docs-search"] }, // replaces defaults
gateway/config-agents.md:1059:        skills: ["docs-search"], // replaces agents.defaults.skills when set
gateway/config-agents.md:1096:- `skills`: optional per-agent skill allowlist. If omitted, the agent inherits `agents.defaults.skills` when set; an explicit list replaces defaults instead of merging, and `[]` means no skills.
gateway/configuration.md:226:          { id: "docs", skills: ["docs-search"] }, // replaces defaults

</AccordionGroup>

## Skills and automation

<AccordionGroup>
  <Accordion title="How do I customize skills without keeping the repo dirty?">
    Use managed overrides instead of editing the repo copy. Put changes in `~/.openclaw/skills/<name>/SKILL.md` (or add a folder via `skills.load.extraDirs` in `~/.openclaw/openclaw.json`). Precedence: `<workspace>/skills` -> `<workspace>/.agents/skills` -> `~/.agents/skills` -> `~/.openclaw/skills` -> bundled -> `skills.load.extraDirs`, so managed overrides win over bundled skills without touching git. To install globally but limit visibility to some agents, keep the shared copy in `~/.openclaw/skills` and control visibility with `agents.defaults.skills` / `agents.list[].skills`. Only upstream-worthy edits should go out as PRs against the repo copy.
  </Accordion>

  <Accordion title="Can I load skills from a custom folder?">
    Yes: add directories via `skills.load.extraDirs` in `~/.openclaw/openclaw.json` (lowest precedence in the order above). `clawhub` installs into `./skills` by default, which OpenClaw treats as `<workspace>/skills` on the next session. To limit visibility to certain agents, pair with `agents.defaults.skills` or `agents.list[].skills`.
  </Accordion>

  <Accordion title="How can I use different models or settings for different tasks?">
    Supported patterns:

openclaw skills list --eligible
    openclaw skills check
    ```

    Native `openclaw skills install` writes into the active workspace `skills/` directory by default. Add `--global` to install into the shared managed skills directory for all local agents. Install the separate `clawhub` CLI only to publish or sync your own skills. Use `agents.defaults.skills` or `agents.list[].skills` to narrow which agents see shared skills.

  </Accordion>

  <Accordion title="Can OpenClaw run tasks on a schedule or continuously in the background?">
    Yes, via the Gateway scheduler:

    - **Cron jobs** for scheduled or recurring tasks (persist across restarts).
    - **Heartbeat** for main-session periodic checks.

`search`, `update`, and `verify` use ClawHub directly. `install @owner/<slug>`
installs a ClawHub skill, `install git:owner/repo[@ref]` clones a Git skill,
and `install ./path` copies a local skill directory. By default, `install`,
`update`, and `verify` target the active workspace `skills/` directory; with
`--global`, they target the shared managed skills directory. `list`/`info`/`check`
still inspect the local skills visible to the current workspace and config.
Workspace-backed commands resolve the target workspace from `--agent <id>`,
then the current working directory when it is inside a configured agent
workspace, then the default agent.

Git and local directory installs expect `SKILL.md` at the source root. The
install slug comes from `SKILL.md` frontmatter `name` when it is valid, then
the source directory or repository name; use `--as <slug>` to override it.
`--version` is ClawHub-only. Skill installs do not support npm package specs
or zip/archive paths, and `openclaw skills update` updates ClawHub-tracked
installs only.

Gateway-backed skill dependency installs triggered from onboarding or Skills
settings use the separate `skills.install` request path instead.

Notes:

| Flag/behavior                    | Description                                                                                                                                                                                                                                                                       |
| -------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `search [query...]`              | Optional query; omit it to browse the default ClawHub search feed.                                                                                                                                                                                                                |
| `search --limit <n>`             | Caps returned results.                                                                                                                                                                                                                                                            |
| `install git:owner/repo[@ref]`   | Installs a Git skill. Branch refs may contain slashes, such as `git:owner/repo@feature/foo`.                                                                                                                                                                                      |
| `install ./path/to/skill`        | Installs a local directory whose root contains `SKILL.md`.                                                                                                                                                                                                                        |
| `install --as <slug>`            | Overrides the inferred slug for Git and local directory installs.                                                                                                                                                                                                                 |
| `install --version <version>`    | Applies only to ClawHub skill refs.                                                                                                                                                                                                                                               |
| `install --force`                | Overwrites an existing workspace skill folder for the same slug.                                                                                                                                                                                                                  |
| `install/update --force-install` | Installs a pending GitHub-backed ClawHub skill before ClawHub's scan completes.                                                                                                                                                                                                   |
| `--global`                       | Targets the shared managed skills directory; cannot combine with `--agent <id>`.                                                                                                                                                                                                  |
| `--agent <id>`                   | Targets one configured agent workspace; overrides current working directory inference.                                                                                                                                                                                            |
| `update @owner/<slug>`           | Updates a single tracked skill. Add `--global` to target the shared managed skills directory instead of the workspace.                                                                                                                                                            |
| `update --all`                   | Updates tracked ClawHub installs in the selected workspace, or the shared managed skills directory with `--global`.                                                                                                                                                               |
| `verify @owner/<slug>`           | Prints ClawHub's `clawhub.skill.verify.v1` JSON envelope by default. There is no `--json` flag because JSON is already the default. Bare slugs are accepted for compatibility when the skill is already installed or unambiguous; owner-qualified refs avoid publisher ambiguity. |
| `verify` provenance              | When ClawHub returns server-resolved source provenance, verify JSON also includes a commit-pinned `openclaw.verifiedSourceUrl`. Unavailable or self-declared source URLs stay only in the raw provenance envelope and are not promoted.                                           |
| `verify` version selector        | `verify` uses `.clawhub/origin.json` for installed ClawHub skills, so it verifies the installed version against the registry it came from. `--version` and `--tag` override the version selector but keep that installed registry when origin metadata exists.                    |
| `verify --card`                  | Prints the generated Skill Card Markdown instead of JSON. Exits non-zero when ClawHub returns `ok: false` or `decision: "fail"`; unsigned signatures are informational unless ClawHub policy changes.                                                                             |
| Skill Card fingerprint           | Installed ClawHub bundles can include a generated `skill-card.md`. OpenClaw treats verification as a ClawHub server decision and does not reject an installed skill just because that generated card changes the bundle fingerprint.                                              |
| `check --agent <id>`             | Checks the selected agent's workspace and reports which ready skills are actually visible to that agent's prompt or command surface.                                                                                                                                              |
| `list`                           | Default action when no subcommand is provided.                                                                                                                                                                                                                                    |
| `list`/`info`/`check` output     | Rendered output goes to stdout. With `--json`, the machine-readable payload stays on stdout for pipes and scripts.                                                                                                                                                                |

20:      extraDirs: ["~/Projects/agent-scripts/skills"],
56:## Loading (`skills.load`)
58:<ParamField path="skills.load.extraDirs" type="string[]">
63:<ParamField path="skills.load.allowSymlinkTargets" type="string[]">
71:<ParamField path="skills.load.watch" type="boolean" default="true">
76:<ParamField path="skills.load.watchDebounceMs" type="number" default="250">
357:  real target is already trusted by `skills.load.allowSymlinkTargets`. Keep
388:      extraDirs: ["~/Projects/manager/skills"],
396:is accepted after realpath resolution. `extraDirs` scans the sibling repo
462:skills.load.extraDirs (lowest)

creating-skills.md
skill-workshop.md
skills-config.md
skills.md

concepts/agent.md:72:- Managed/local: `~/.openclaw/skills`
concepts/agent-workspace.md:118:- `~/.openclaw/skills/` (managed skills)
concepts/multi-agent.md:35:Skills load from each agent workspace plus shared roots such as `~/.openclaw/skills`, then filter by the effective agent skill allowlist. Use `agents.defaults.skills` for a shared baseline and `agents.list[].skills` for a per-agent replacement (explicit entries replace the default, they do not merge). See [Skills: per-agent vs shared](/tools/skills#per-agent-vs-shared-skills) and [Skills: agent allowlists](/tools/skills#agent-allowlists).
cli/skills.md:75:`--global`, they target the shared managed skills directory. `list`/`info`/`check`
cli/skills.md:103:| `--global`                       | Targets the shared managed skills directory; cannot combine with `--agent <id>`.                                                                                                                                                                                                  |
cli/skills.md:105:| `update @owner/<slug>`           | Updates a single tracked skill. Add `--global` to target the shared managed skills directory instead of the workspace.                                                                                                                                                            |
cli/skills.md:106:| `update --all`                   | Updates tracked ClawHub installs in the selected workspace, or the shared managed skills directory with `--global`.                                                                                                                                                               |
help/faq.md:131:    Use managed overrides instead of editing the repo copy. Put changes in `~/.openclaw/skills/<name>/SKILL.md` (or add a folder via `skills.load.extraDirs` in `~/.openclaw/openclaw.json`). Precedence: `<workspace>/skills` -> `<workspace>/.agents/skills` -> `~/.agents/skills` -> `~/.openclaw/skills` -> bundled -> `skills.load.extraDirs`, so managed overrides win over bundled skills without touching git. To install globally but limit visibility to some agents, keep the shared copy in `~/.openclaw/skills` and control visibility with `agents.defaults.skills` / `agents.list[].skills`. Only upstream-worthy edits should go out as PRs against the repo copy.
help/faq.md:282:    Native `openclaw skills install` writes into the active workspace `skills/` directory by default. Add `--global` to install into the shared managed skills directory for all local agents. Install the separate `clawhub` CLI only to publish or sync your own skills. Use `agents.defaults.skills` or `agents.list[].skills` to narrow which agents see shared skills.
help/faq.md:315:    3. Override the skill metadata (workspace or `~/.openclaw/skills`) to allow Linux:
help/faq.md:479:    - **State dir (`~/.openclaw`)**: config, channel/provider state, auth profiles, sessions, logs, shared skills (`~/.openclaw/skills`).
clawhub/cli.md:37:`--global` for the shared managed skills directory. Plugin installs need the
tools/skills.md:42:| 4           | Managed / local skills | `~/.openclaw/skills`                    |
tools/skills.md:74:| Shared managed | `~/.openclaw/skills`         | All agents on this machine  |
tools/skills.md:156:| Update a shared managed skill      | `openclaw skills update @owner/<slug> --global`        |
tools/skills.md:157:| Update all shared managed skills   | `openclaw skills update --all --global`                |
tools/skills.md:166:    `~/.openclaw/skills` directory, visible to all local agents unless agent
tools/skills.md:214:    Managed `~/.openclaw/skills` and personal `~/.agents/skills` may contain
tools/skills-config.md:336:  registries such as `~/.openclaw/skills/config/mcporter.json`. For
tools/skills-config.md:417:Managed `~/.openclaw/skills` and personal `~/.agents/skills` directories

skill name appears in multiple places, the highest source wins.

| Priority    | Source                 | Path                                    |
| ----------- | ---------------------- | --------------------------------------- |
| 1 — highest | Workspace skills       | `<workspace>/skills`                    |
| 2           | Project agent skills   | `<workspace>/.agents/skills`            |
| 3           | Personal agent skills  | `~/.agents/skills`                      |
| 4           | Managed / local skills | `~/.openclaw/skills`                    |
| 5           | Bundled skills         | shipped with the install                |
| 6 — lowest  | Extra directories      | `skills.load.extraDirs` + plugin skills |

Skill roots support grouped layouts. OpenClaw discovers a skill whenever
`SKILL.md` appears anywhere under a configured root (up to 6 levels deep):

```text
<workspace>/skills/research/SKILL.md          ✓ found as "research"
<workspace>/skills/personal/research/SKILL.md ✓ also found as "research"
```

The folder path is for organization only. The skill's name and slash command
come from the `name` frontmatter field (or the directory name when `name` is
missing). Agent allowlists (below) also match on this `name`.

<Note>
  Codex CLI's native `$CODEX_HOME/skills` directory is **not** an OpenClaw
  skill root. Use `openclaw migrate plan codex` to inventory those skills, then
  `openclaw migrate codex` to copy them into your OpenClaw workspace.
</Note>

## Per-agent vs shared skills

In multi-agent setups, each agent has its own workspace. Use the path that
matches your desired visibility:

| Scope          | Path                         | Visible to                  |
| -------------- | ---------------------------- | --------------------------- |
| Per-agent      | `<workspace>/skills`         | Only that agent             |
| Project-agent  | `<workspace>/.agents/skills` | Only that workspace's agent |
| Personal-agent | `~/.agents/skills`           | All agents on this machine  |
| Shared managed | `~/.openclaw/skills`         | All agents on this machine  |
| Extra dirs     | `skills.load.extraDirs`      | All agents on this machine  |

## Agent allowlists

Skill **location** (precedence) and skill **visibility** (which agent can use
it) are separate controls. Use allowlists to restrict which skills an agent sees,

| ---------------------------------- | ------------------------------------------------------ |
| Install a skill into the workspace | `openclaw skills install @owner/<slug>`                |
| Install from a Git repository      | `openclaw skills install git:owner/repo@ref`           |
| Install a local skill directory    | `openclaw skills install ./path/to/skill --as my-tool` |
| Install for all local agents       | `openclaw skills install @owner/<slug> --global`       |
| Update all workspace skills        | `openclaw skills update --all`                         |
| Update a shared managed skill      | `openclaw skills update @owner/<slug> --global`        |
| Update all shared managed skills   | `openclaw skills update --all --global`                |
| Verify a skill's trust envelope    | `openclaw skills verify @owner/<slug>`                 |
| Print the generated Skill Card     | `openclaw skills verify @owner/<slug> --card`          |
| Publish / sync via ClawHub CLI     | `clawhub sync --all`                                   |

<AccordionGroup>
  <Accordion title="Install details">
    `openclaw skills install` installs into the active workspace `skills/`
    directory by default. Add `--global` to install into the shared
    `~/.openclaw/skills` directory, visible to all local agents unless agent
    allowlists narrow it.

    Git and local installs expect `SKILL.md` at the source root. The slug comes
    from `SKILL.md` frontmatter `name` when valid, then falls back to the

- Workspace: `<workspace>/skills`
- Project agent skills: `<workspace>/.agents/skills`
- Personal agent skills: `~/.agents/skills`
- Managed/local: `~/.openclaw/skills`
- Bundled (shipped with the install)
- Extra skill folders: `skills.load.extraDirs`

---

These live under `~/.openclaw/` and should NOT be committed to the workspace repo:

- `~/.openclaw/openclaw.json` (config)
- `~/.openclaw/agents/<agentId>/agent/auth-profiles.json` (model auth profiles: OAuth + API keys)
- `~/.openclaw/agents/<agentId>/agent/codex-home/` (per-agent Codex runtime account, config, skills, plugins, and native thread state)
- `~/.openclaw/credentials/` (channel/provider state plus legacy OAuth import data)
- `~/.openclaw/agents/<agentId>/sessions/` (session transcripts + metadata)
- `~/.openclaw/skills/` (managed skills)

If you need to migrate sessions or config, copy them separately and keep them out of version control.

## Git backup (recommended, private)

Treat the workspace as private memory. Put it in a **private** git repo so it is backed up and recoverable.

~/.nvm/versions/node/v22.23.2/lib/node_modules

/usr/local/bin/openclaw

~/.nvm/versions/node/v24.15.0/lib/node_modules/openclaw/openclaw.mjs
---
lrwxrwxrwx 1 root root 46 Aug 14 07:48 /usr/local/bin/openclaw -> /root/.nvm/versions/node/v24.15.0/bin/openclaw
---
/root/.nvm/versions/node/v24.15.0/lib/node_modules/openclaw/openclaw.mjs

v22.23.2
---
/usr/local/bin/node
---
~/.nvm/versions/node/v24.15.0/bin/node

name: openclaw
version: 2026.7.1-2
files: [
  "CHANGELOG.md",
  "LICENSE",
  "npm-shrinkwrap.json",
  "openclaw.mjs",
  "pnpm-workspace.yaml",
  "README.md",
  "THIRD_PARTY_NOTICES.md",
  "dist/",
  "!dist/.buildstamp",
  "!dist/.runtime-postbuildstamp",
  "!dist/**/*.map",
  "!dist/plugin-sdk/.tsbuildinfo",
  "!dist/plugin-sdk/agent-runtime-test-contracts.js",
  "!dist/plugin-sdk/agent-runtime-test-contracts.d.ts",
  "!dist/plugin-sdk/channel-contract-testing.js",
  "!dist/plugin-sdk/channel-contract-testing.d.ts",
  "!dist/plugin-sdk/channel-target-testing.js",
  "!dist/plugin-sdk/channel-target-testing.d.ts",
  "!dist/plugin-sdk/channel-test-helpers.js",
  "!dist/plugin-sdk/channel-test-helpers.d.ts",
  "!dist/plugin-sdk/codex-native-task-runtime.js",
  "!dist/plugin-sdk/codex-native-task-runtime.d.ts",
  "!dist/plugin-sdk/plugin-test-api.js",
  "!dist/plugin-sdk/plugin-test-api.d.ts",
  "!dist/plugin-sdk/plugin-test-contracts.js",
  "!dist/plugin-sdk/plugin-test-contracts.d.ts",
  "!dist/plugin-sdk/plugin-state-test-runtime.js",
  "!dist/plugin-sdk/plugin-state-test-runtime.d.ts",
  "!dist/plugin-sdk/plugin-test-runtime.js",
  "!dist/plugin-sdk/plugin-test-runtime.d.ts",
  "!dist/plugin-sdk/provider-http-test-mocks.js",
  "!dist/plugin-sdk/provider-http-test-mocks.d.ts",
  "!dist/plugin-sdk/provider-test-contracts.js",
  "!dist/plugin-sdk/provider-test-contracts.d.ts",
  "!dist/plugin-sdk/reply-payload-testing.js",
  "!dist/plugin-sdk/reply-payload-testing.d.ts",
  "!dist/plugin-sdk/sqlite-runtime-testing.js",
  "!dist/plugin-sdk/sqlite-runtime-testing.d.ts",
  "!dist/plugin-sdk/ssrf-runtime-internal.js",
  "!dist/plugin-sdk/ssrf-runtime-internal.d.ts",
  "!dist/plugin-sdk/test-env.js",
  "!dist/plugin-sdk/test-env.d.ts",
  "!dist/plugin-sdk/test-fixtures.js",
  "!dist/plugin-sdk/test-fixtures.d.ts",
  "!dist/plugin-sdk/test-node-mocks.js",
  "!dist/plugin-sdk/test-node-mocks.d.ts",
  "!dist/plugin-sdk/test-utils.js",
  "!dist/plugin-sdk/test-utils.d.ts",
  "!dist/plugin-sdk/testing.js",
  "!dist/plugin-sdk/testing.d.ts",
  "!dist/plugin-sdk/src/agents/test-helpers/**",
  "!dist/plugin-sdk/src/test-helpers/**",
  "!dist/plugin-sdk/src/test-utils/**",
  "!dist/plugin-sdk/src/plugin-sdk/test-helpers/**",
  "!dist/extensions/acpx/**",
  "!dist/extensions/amazon-bedrock/**",
  "!dist/extensions/amazon-bedrock-mantle/**",
  "!dist/extensions/anthropic-vertex/**",
  "!dist/extensions/node_modules/**",
  "!dist/extensions/*/node_modules/**",
  "!dist/extensions/arcee/**",
  "!dist/extensions/brave/**",
  "!dist/extensions/cerebras/**",
  "!dist/extensions/chutes/**",
  "!dist/extensions/clickclack/**",
  "!dist/extensions/cloudflare-ai-gateway/**",
  "!dist/extensions/codex/**",
  "!dist/extensions/copilot/**",
  "!dist/extensions/deepinfra/**",
  "!dist/extensions/deepseek/**",
  "!dist/extensions/diagnostics-otel/**",
  "!dist/extensions/diagnostics-prometheus/**",
  "!dist/extensions/diffs/**",
  "!dist/extensions/diffs-language-pack/**",
  "!dist/extensions/discord/**",
  "!dist/extensions/exa/**",
  "!dist/extensions/feishu/**",
  "!dist/extensions/featherless/**",
  "!dist/extensions/firecrawl/**",
  "!dist/extensions/fireworks/**",
  "!dist/extensions/google-meet/**",
  "!dist/extensions/googlechat/**",
  "!dist/extensions/gmi/**",
  "!dist/extensions/gradium/**",
  "!dist/extensions/groq/**",
  "!dist/extensions/inworld/**",
  "!dist/extensions/irc/**",
  "!dist/extensions/kilocode/**",
  "!dist/extensions/kimi-coding/**",
  "!dist/extensions/line/**",
  "!dist/extensions/llama-cpp/**",
  "!dist/extensions/lobster/**",
  "!dist/extensions/longcat/**",
  "!dist/extensions/mattermost/**",
  "!dist/extensions/memory-lancedb/**",
  "!dist/extensions/matrix/**",
  "!dist/extensions/moonshot/**",
  "!dist/extensions/msteams/**",
  "!dist/extensions/nextcloud-talk/**",
  "!dist/extensions/nostr/**",
  "!dist/extensions/parallel/**",
  "!dist/extensions/perplexity/**",
  "!dist/extensions/qianfan/**",
  "!dist/extensions/qqbot/**",
  "!dist/extensions/raft/**",
  "!dist/extensions/pixverse/**",
  "!dist/extensions/qa-channel/**",
  "!dist/extensions/qa-lab/**",
  "!dist/extensions/qa-matrix/**",
  "!dist/extensions/openshell/**",
  "!dist/extensions/qwen/**",
  "!dist/extensions/searxng/**",
  "!dist/extensions/signal/**",
  "!dist/extensions/slack/**",
  "!dist/extensions/sms/**",
  "!dist/extensions/stepfun/**",
  "!dist/extensions/synology-chat/**",
  "!dist/extensions/tavily/**",
  "!dist/extensions/tencent/**",
  "!dist/extensions/tokenjuice/**",
  "!dist/extensions/tlon/**",
  "!dist/extensions/twitch/**",
  "!dist/extensions/venice/**",
  "!dist/extensions/vercel-ai-gateway/**",
  "!dist/extensions/voice-call/**",
  "!dist/extensions/whatsapp/**",
  "!dist/extensions/zai/**",
  "!dist/extensions/zalo/**",
  "!dist/extensions/zalouser/**",
  "!dist/plugin-sdk/extensions/qa-channel/**",
  "!dist/plugin-sdk/extensions/qa-lab/**",
  "!dist/plugin-sdk/qa-channel.*",
  "!dist/plugin-sdk/qa-channel-protocol.*",
  "!dist/plugin-sdk/qa-lab.*",
  "!dist/plugin-sdk/qa-runtime.*",
  "!dist/plugin-sdk/src/**",
  "!dist/plugin-sdk/src/plugin-sdk/qa-channel.d.ts",
  "!dist/plugin-sdk/src/plugin-sdk/qa-channel-protocol.d.ts",
  "!dist/plugin-sdk/src/plugin-sdk/qa-lab.d.ts",
  "!dist/plugin-sdk/src/plugin-sdk/qa-runtime.d.ts",
  "!dist/qa-runtime-*.js",
  "docs/",
  "!docs/.generated/**",
  "!docs/channels/qa-channel.md",
  "!docs/assets/**",
  "!docs/images/**",
  "!docs/**/*.jpg",
  "!docs/**/*.png",
  "src/agents/templates/",
  "scripts/crabbox-wrapper-providers.mjs",
  "scripts/crabbox-wrapper.mjs",
  "patches/",
  "skills/",
  "scripts/npm-runner.mjs",
  "scripts/prepare-git-hooks.mjs",
  "scripts/preinstall-package-manager-warning.mjs",
  "scripts/lib/official-external-channel-catalog.json",
  "scripts/lib/official-external-plugin-catalog.json",
  "scripts/lib/official-external-provider-catalog.json",
  "scripts/lib/package-dist-imports.mjs",
  "scripts/postinstall-bundled-plugins.mjs",
  "scripts/windows-cmd-helpers.mjs"
]
directories: {
  "doc": "docs",
  "test": "test"
}
bin: {
  "openclaw": "openclaw.mjs"
}
workspaces: undefined