Author or review AgentSkills: create, repair, validate, or restructure SKILL.md files and bundled resources.
Install
npx skills add https://github.com/openclaw/openclaw --skill skill-creatorSKILL.md
Skill Creator
Workflow
Establish the contract.
- Read the existing skill and its resources, or collect concrete requests for a new skill.
- Separate actual workflow branches from synonyms for the same branch.
- Done when: every branch has a concrete trigger, expected outcome, and persistence target.
Choose invocation.
- Model-discoverable: write a model-facing
description; omitdisable-model-invocation. - Manual-only: set
disable-model-invocation: true; write a human-facing summary. - Direct tool command: add
command-dispatch: tool,command-tool, andcommand-arg-modeonly when the command bypasses the model. - Done when: frontmatter matches how the skill will actually be reached.
- Model-discoverable: write a model-facing
Structure the skill.
- Map shared ordered procedure to
SKILL.md; end every step with a checkable completion criterion and finish with verification. - Keep routing conditions in
description; start the body with execution. - Map branch-only detail to
references/, deterministic helpers toscripts/, output resources toassets/, and optional UI metadata toagents/. - Done when: every planned resource has one purpose and a direct pointer from
SKILL.md.
- Map shared ordered procedure to
Draft and persist.
- Live workspace skill: use
skill_workshopto create or revise a pending proposal; keep live files unchanged until apply. - Repository-owned skill source: use the repository's normal edit and review workflow.
- Done when: the proposal or source diff implements every branch from step 1 and contains every resource from step 3.
- Live workspace skill: use
Validate.
- Run
python {baseDir}/scripts/quick_validate.py <skill-directory>and execute every touched helper's focused test. - Done when: frontmatter passes, resource pointers resolve, and every touched helper passes its focused test.
- Run
Frontmatter
Required: name, description.
OpenClaw also supports metadata, homepage, license, allowed-tools, user-invocable, disable-model-invocation, command-dispatch, command-tool, and command-arg-mode. Add optional fields only when they change runtime behavior or discovery.
Related skills
find-skillsvercel-labs3.6MHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.handoffmattpocock883KCompact the current conversation into a handoff document for another agent to pick up.microsoft-foundrymicrosoft618KBuild, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, create agent, update agent, add tool to agent, invoke agent, agent.yaml, agent insights, pull agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, prompt optimizer, optimize agcavemanjuliusbrussee544KUltra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".