ADK Skill Patterns
v1.0.05 proven agent skill design patterns (Tool Wrapper, Generator, Reviewer, Inversion, Pipeline) from Google's ADK. Build reliable, composable skills with templ...
⭐ 0· 53·0 current·0 all-time
byMax Hutchinson@maxlauriehutchinson
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
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.
Instruction Scope
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.
Install Mechanism
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.
Credentials
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.
Persistence & Privilege
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.
Assessment
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.Like a lobster shell, security has layers — review code before you run it.
adkvk976yytbftd3drgp1yvj09hpt983t17dagentsvk976yytbftd3drgp1yvj09hpt983t17dlatestvk976yytbftd3drgp1yvj09hpt983t17dpatternsvk976yytbftd3drgp1yvj09hpt983t17dskillsvk976yytbftd3drgp1yvj09hpt983t17d
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧩 Clawdis