Mastra Agent Skills
mastra-ai/skillsMastra's official skills: a framework guide that routes to current docs and ten references, and a Factory supervisor skill for the mastra api CLI.
A reference skill for writing Agent Development Kit code in Python or Go: agent types, tools, callbacks, state, orchestration and recipes.
A compact, well-indexed ADK reference; useful if you use ADK, pointless if you do not.
This skill is the API cheat sheet the agent reads before writing ADK code. It covers agent definitions, tool definitions, orchestration patterns (sequential, parallel and loop agents, custom agents), callbacks, plugins, state and artifacts, the graph Workflow API, A2A and live or voice agents. A references folder holds six files: Python and Go core references, workflow references for each language, a live-agent reference and a recipes index. The recipes index maps a need, such as sandboxed code execution, cross-session memory, approval gates before risky actions, tool guardrails, per-user credentials or scheduled runs, to a worked implementation to study. For deeper questions it points the agent to the ADK docs index (adk.dev/llms.txt) and to the installed package source. It refuses to write agent code until a project is scaffolded with agents-cli scaffold create or enhance, and it defers scaffolding, deployment and evaluation to sibling skills. The SKILL.md itself is short, about 4.5 KB, and the substance sits in the reference files.
A short 4.5 KB SKILL.md backed by six reference files, but no scripts or evals of its own.
Markdown-only reference for writing ADK agent code (agents, tools, callbacks, state, workflows); it contains no scripts. It tells the agent to use the agents-cli tool and to read ADK documentation from adk.dev. The agents-cli tool itself was not reviewed and, per the repo README, sends usage telemetry that can be disabled with an environment variable.
uv tool install google-agents-cli; reference docs also mention pip install google-adk[a2a].SKILL.md:20The skill folder (7 files) on Oct 29, 2026. Not a full review: it relies on code outside the repository: agents-cli (PyPI package google-agents-cli, installed with uv tool install).
NVIDIA SkillSpector static scan: 8 pattern hits (Privilege Escalation 2, Excessive Agency 2, Supply Chain 1, Prompt Injection 1, Data Exfiltration 1, MCP Rug Pull 1). Hits are documentation: credential matches are ADK auth examples (APIKey from env vars), 'silently send' is a sentence about Live model region fallback, requests.post is an example against a local ADK server, 'timeout=None' and 'npx required' are code samples. The curl of adk.dev/llms.txt is a docs-index lookup, not piped to a shell.
A review, not a certification. Skills change after we check them — read the files before installing.
Apache-2.0 — commercial use allowed.
Not really. It is a reference skill consulted while coding, not a loop.
Mastra's official skills: a framework guide that routes to current docs and ten references, and a Factory supervisor skill for the mastra api CLI.
Google's official collection of about 180 skills for Google Cloud, Gemini APIs, Analytics, Data Manager, sign-in and other Google products.
The AI SDK repo's skills: one public ai-sdk skill for building with the SDK plus about a dozen maintainer-only skills for the monorepo.
A reference skill for writing Agent Development Kit code in Python or Go: agent types, tools, callbacks, state, orchestration and recipes.
It ships in the google/agents-cli repository. Run uvx google-agents-cli setup or npx skills add google/agents-cli; the skill expects the agents-cli binary (uv tool install google-agents-cli).
The skill is markdown with reference files and no scripts. It sends the agent to fetch ADK docs pages, and the agents-cli it relies on has opt-out usage telemetry.