5 proven agent skill design patterns (Tool Wrapper, Generator, Reviewer, Inversion, Pipeline) from Google's ADK. Build reliable, composable skills with templ...
Security Analysis
high confidenceInstruction-only skill that provides reusable agent design patterns and templates; its files, instructions, and required capabilities are coherent and proportionate to the stated purpose.
The skill advertises five ADK patterns and only includes documentation and templates to implement those patterns. It requests no binaries, env vars, or installs, which is appropriate for a patterns/templates guide.
SKILL.md and the templates instruct the agent to load local references, ask the user questions, and read user-supplied code when relevant. Those actions are consistent with a patterns/templates repo; there are no instructions to read unrelated system files, access external endpoints, or exfiltrate data.
No install specification or code files are present. Being instruction-only means nothing is downloaded or written to disk by the skill itself, which minimizes installation risk.
The skill declares no required environment variables, credentials, or config paths. The templates reference only local files inside the skill (references/, assets/, templates/), which matches the described functionality.
always is false and there is no mechanism to self-enable or persist across agents. The skill does not request elevated privileges or modify other skills or system-wide settings.
Guidance
This is an instruction-only templates/guide pack for designing agent skills and appears coherent and low-risk. Before installing, review the included templates and checklist to ensure they match your intended workflows. Note the skill will read user-supplied code or prompts when invoked (expected for Reviewer/Pipeline patterns) — avoid sending sensitive secrets or credentials to the skill. Because it has no install steps or external endpoints, its primary risk is accidental disclosure of data you feed into it, not background exfiltration. If you plan to let agents invoke skills autonomously, remember autonomous invocation is allowed by default; consider disabling autonomous invocation if you want manual control.
Latest Release
v1.0.0
- Initial release of adk-skill-patterns. - Documents 5 proven agent skill design patterns: Tool Wrapper, Generator, Reviewer, Inversion, Pipeline. - Includes decision trees, pattern composition guides, anti-patterns, and practical templates. - Helps structure agent skill logic for reliability, composability, and maintainability. - Provides clear implementation notes and usage instructions for OpenClaw.
Popular Skills
Published by @maxlauriehutchinson on ClawHub
