Author or review AgentSkills: create, repair, validate, or restructure SKILL.md files and bundled resources.
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/agent-skill-creator/SKILL.mdThe canonical home for this skill is skill-creator in openclaw/openclaw
Establish the contract.
Choose invocation.
description; omit disable-model-invocation.disable-model-invocation: true; write a human-facing summary.command-dispatch: tool, command-tool, and command-arg-mode only when the command bypasses the model.Structure the skill.
SKILL.md; end every step with a checkable completion criterion and finish with verification.description; start the body with execution.references/, repeatable helpers to scripts/, output resources to assets/, and optional UI metadata to agents/.SKILL.md.Draft and persist.
skill_workshop to create or revise a pending proposal; keep live files unchanged until apply.Validate.
python {baseDir}/scripts/quick_validate.py <skill-directory> and execute every touched helper's focused test.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.
administrakt0r/AGENTARDS
8e964ab
Canonical home
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.