Design and build OpenClaw skills. Use when asked to "make/build/craft a skill", extract ad-hoc functionality into a skill, or package scripts/instructions for reuse. Covers OpenClaw-specific integration (tool calling, memory, message routing, cron, canvas, nodes) and ClawHub publishing.
Security Analysis
high confidenceInstruction-only skill that provides a structured, coherent guide for authoring OpenClaw skills; it requests no credentials or installs and its instructions align with its stated purpose.
The name/description (skill designer for OpenClaw) matches the content: the SKILL.md and pattern files are templates and guidance for packaging skills, routing, cron, memory, and publishing. No unrelated binaries, env vars, or install steps are requested.
The runtime instructions tell the agent to inspect available skills, workspace files, and to place state under `{baseDir}`/`<workspace>`. This is expected for a skill-authoring guide, but it means the agent will read other skills and workspace files when following these instructions — review those reads if you have sensitive data in workspace files or other skill bodies.
No install spec and no code files — instruction-only. This is the lowest-risk install profile (nothing is downloaded or written by an installer).
The skill declares no required environment variables or credentials. It does provide guidance for how skill authors should *store* secrets (env vars, keychain, 1Password CLI), which is advisory and not a request for secrets from the runner.
always:false and no config paths requested. The skill recommends locations for skill-local state files but does not request global agent configuration changes or persistent privileges.
Guidance
This skill is an authoring guide and is internally consistent. Because it instructs agents to read other skills and workspace files, review any workspace content and other skills for sensitive data before using it to auto-extract or package code. The skill itself asks for no credentials and performs no installs, but be cautious if you follow its guidance to add state files or to request environment variables later when authoring new skills — never hardcode secrets into SKILL.md or published skill files, and review any resulting SKILL.md or install steps before publishing or installing. If you do not want agents to autonomously create/publish skills, consider controlling invocation or review outputs manually.
Latest Release
v1.0.0
Opus 4.6 overhaul: 60% slimmer, OpenClaw naming, {baseDir} paths, new frontmatter keys, model-tier guidance, direct docs links
Popular Skills
Published by @jmz1 on ClawHub
