Skip to main content
Skill Workshop is OpenClaw’s governed path for creating and updating workspace skills. Agents and operators never write SKILL.md directly through this path — they create a proposal (pending draft with content, target binding, scanner state, hashes, and rollback metadata) that becomes a live skill only when applied. Skill Workshop writes workspace skills only. It never touches bundled, plugin, ClawHub, extra-root, managed, personal-agent, or system skills.

​
How it works

  • Proposal first: generated content is stored as PROPOSAL.md, not SKILL.md.
  • Apply is the only live write: create, update, and revise never change active skills.
  • Workspace scoped: creates target the workspace skills/ root; updates are allowed only for writable workspace skills.
  • No clobber: create fails if the target skill already exists.
  • Hash bound: update proposals bind to the current target hash and go stale if the live skill changes before apply.
  • Scanner gated: apply reruns the security scanner before writing.
  • Recoverable: apply writes rollback metadata before touching live files.
  • Consistent surfaces: chat, CLI, and Gateway all call the same service.

​
Lifecycle

Only a pending proposal can be revised, applied, rejected, or quarantined.

​
Lifecycle curation

The Gateway tracks aggregate skill usage in the shared state database. Once a day, it reviews skills created and applied by Skill Workshop. Skills unused for more than 30 days become stale; after 90 days they become archived and are left out of new agent skill snapshots. Archived skill files remain unchanged on disk. Manually authored skills are never curated; only skills created by Skill Workshop proposals enter lifecycle curation. Pinned skills bypass lifecycle transitions. A stale skill returns to active after it is used and the next sweep runs. Archived skills return only through an explicit restore: Lifecycle transitions and restores apply to new sessions; running sessions keep their current skill snapshot.
All curator commands accept --json. Status also reports deterministic overlap candidates as suggestions only; it never merges skills or calls a model.

​
Chat

Ask the agent for the skill you want; it calls skill_workshop and returns a proposal id.

​
Learn from recent work

Use /learn to turn the current conversation or named sources into one standards-guided skill proposal:
With no request, /learn asks the agent to distill the reusable workflow from the current conversation. With a request, the agent treats paths, URLs, pasted notes, and conversation references as sources while honoring focus, scope, and naming requirements. It gathers the sources with its existing tools, then calls skill_workshop with action: "create". The resulting proposal stays pending; /learn never applies it. Review and apply it through the normal approval flow or with openclaw skills workshop. Create:
Update an existing workspace skill:
Iterate on a pending proposal:
Agent-initiated apply, reject, and quarantine run without an additional approval prompt by default. Set skills.workshop.approvalPolicy to "pending" to require operator approval before those actions. When approval is required, the prompt identifies the proposal id and target skill, and shows the proposal description, support-file count, and body size. Approval requests are bounded to finish before the agent tool watchdog. If no decision arrives before the prompt expires, the lifecycle action does not run: the proposal stays pending and unchanged. Decide later in the Skill Workshop UI or run openclaw skills workshop apply|reject|quarantine <proposal-id>. Agents should not retry an expired lifecycle action in a loop.

​
CLI

Every subcommand takes --agent <id> (target workspace; defaults to cwd-inferred, then the default agent) and --json (structured output). propose-create, propose-update, and revise also take --goal <text> and --evidence <text> to record proposal context alongside --proposal.

​
Proposal content

While pending, the proposal is stored as PROPOSAL.md with proposal-only frontmatter:
On apply, Skill Workshop writes the active SKILL.md and removes the proposal-only fields: status, proposal version, and proposal date.

​
Support files

Use --proposal-dir when the proposed skill needs files beside PROPOSAL.md:
The directory must contain PROPOSAL.md. Support files must live under assets/, examples/, references/, scripts/, or templates/. Skill Workshop scans, hashes, and stores them with the proposal, then writes them beside the live SKILL.md only on apply. Rejected support-file paths: absolute paths, hidden path segments, path traversal, overlapping paths, executable files, non-UTF-8 text, null bytes, and paths outside the standard support folders.

​
Agent tool

The model uses skill_workshop with one required action: create | update | revise | list | inspect | apply | reject | quarantine. Other parameters apply depending on the action: Agents must use skill_workshop for generated skill work. They must not create or change proposal files through write, edit, exec, shell commands, or direct filesystem operations.
skill_workshop is a built-in agent tool and is included in tools.profile: "coding". If a stricter policy hides it, add skill_workshop to the active tools.allow list, or use tools.alsoAllow: ["skill_workshop"] when the scope uses a profile without an explicit tools.allow. Sandboxed runs do not construct the host-side Skill Workshop tool, so run proposal review actions from a normal host-side agent session or the CLI.

​
Suggested skills

OpenClaw detects durable instructions such as “next time,” “remember to,” and reactive corrections when an interactive turn ends, including failed turns. On the next turn, the agent offers to save the most recent detected workflow through skill_workshop; the user decides whether to create a proposal. This built-in suggestion does not create or change a skill by itself. Enable skills.workshop.autonomous.enabled to create pending proposals directly instead. In the Control UI, the Workshop tab offers the same setting as a Self-learning toggle in the page header, and as an enable button on the empty proposal board.

​
Scan past sessions

The Control UI can review older work without enabling autonomous self-learning. Open Plugins → Workshop and select Find skill ideas. The scan starts with the newest eligible sessions and reviews a bounded window of substantial work. It skips cron, heartbeat, hook, subagent, ACP, plugin-owned, and internal review sessions, plus conversations with fewer than six model turns. The reviewer uses the selected agent’s configured model and receives a secret-redacted, size-bounded transcript bundle. It applies the same conservative bar as experience review: a concrete recovery pattern or a stable procedure that would remove at least two future model or tool calls. Routine work and one-off facts should produce no proposal. One scan can create or revise at most three pending proposals. It cannot apply, reject, quarantine, or edit a live skill. The Workshop shows cumulative coverage, for example 20 sessions reviewed · Jun 18–today · 2 ideas found. Select Scan earlier work to continue from the persisted oldest-session cursor. After the available history is exhausted, the action becomes Scan new work. Historical review is manual even when skills.workshop.autonomous.enabled is false. Each click starts a model run, so provider pricing and data-handling terms apply. The cursor and coverage counts are stored in the shared OpenClaw state database; transcript content is not copied into scan state. With autonomous capture enabled, OpenClaw can also perform a conservative review after successful, substantial work and after the whole agent system becomes idle. That isolated review can create or revise at most one pending proposal. It cannot update a live skill or apply, reject, or quarantine a proposal, even when approvalPolicy is "auto". See Self-learning for enablement, eligibility, privacy and cost details, the proposal threshold, and troubleshooting.

​
Approval and autonomy

Autonomous capture recognizes prospective rules (for example, “from now on”) and reactive corrections (for example, “that’s not what I asked”). It groups new instructions by topic into up to three proposals per turn, routes vocabulary matches to existing writable workspace skills, and revises its own pending proposal when another correction targets the same skill. For successful substantial work without an explicit correction, an isolated run of the selected model decides whether the completed trajectory clears the conservative proposal bar. The foreground model is not prompted to learn before it replies. The background reviewer preserves the foreground run as proposal provenance, cannot access general agent tools, and cannot make lifecycle decisions. The review starts only when the foreground runtime reports both its exact resolved model and that skill_workshop was actually available. Restrictive or unknown tool policy therefore fails closed and creates no proposal. See Self-learning for the complete autonomous review behavior and safety model. Proposal descriptions are always capped at 160 bytes, independent of maxSkillBytes.

​
Gateway methods

requestRevision is Gateway-only (no CLI or agent-tool equivalent): it forwards free-text revision instructions to the owning agent’s chat session instead of replacing PROPOSAL.md directly, for UIs that ask the agent to revise rather than submit literal new content. historyStatus and historyScan are Control UI support methods. historyScan accepts direction: "older" | "newer"; it always leaves results as pending proposals.

​
Storage

Default state directory: ~/.openclaw.
  • proposal.json: canonical proposal record.
  • proposals.json: fast listing index, rebuildable from proposal folders.
  • PROPOSAL.md: pending skill proposal.
  • rollback.json: recovery metadata written before apply changes live files.

​
Limits

​
Troubleshooting

​
Tool-policy diagnostic

When autonomous capture is enabled, openclaw doctor runs the core/doctor/skill-workshop-tool-policy check for the default agent. If policy hides skill_workshop, the warning names the first excluding config layer and the exact allow or alsoAllow change to make. Older runbooks may still use openclaw plugins inspect skill-workshop; that command now explains that Skill Workshop is built in and prints the same policy hint when applicable.