github.com/google/adk-samples
| Skill | Added | Review |
|---|---|---|
agents-cli-aqua core/python/ambient-quality-agent/skills/agents-cli-aqua/SKILL.md Work with the Ambient Quality Agent (AQuA) added to this agents-cli project: augment the agents-cli agent with AQuA or attach the agent to an AQuA deployed elsewhere, read the quality insights it finds in production conversations, get AQuA's root-cause diagnosis, read what the developer asked it to remember, and fix the defects in the agent's code. Propose proactively when the user mentions AQuA or AQA, wants to monitor the quality of a deployed agent, mentions traces or observability, asks what is going wrong with their agent in production, wants to fix AQuA insights, or wants to publish code metrics to AQuA. Also propose it when traces from an evaluation run are in the telemetry table AQuA reads. Don't use it for scoring a local agent against a golden dataset (use google-agents-cli-eval) or for deploys without AQuA (google-agents-cli-deploy). | 73 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e05958e | |
align-recipe-pyproject .agents/skills/align-recipe-pyproject/SKILL.md Aligns a Python recipe's pyproject.toml with the repo's standards enforced by .github/workflows/python-validate-recipe.yml, plus one critical [build-system] presence check. Scope is pyproject.toml only — standalone ruff.toml / .ruff.toml files (also forbidden in recipes) are caught by the CI workflow instead, not by this skill. Runs in two modes: a read-only --dry-run that reports what needs alignment, and an apply mode that rewrites pyproject.toml (and optionally manifest.yaml) using comment-preserving TOML/YAML editors. Use when the user wants to "align the recipe's pyproject.toml", "fix pyproject to match the repo standard", "check what needs changing in a recipe's pyproject", or clean up a recipe before submitting a PR. | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e05958e | |
approvals core/python/adk-voice-agent/sandbox/skills/approvals/SKILL.md What to do when a tool call is paused for the user's approval or declined (sending, inviting, deleting, posting, merging), and when you are resumed after one. | 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e05958e | |
blog-writer contrib/python/agent-skills-tutorial/app/skills/blog-writer/SKILL.md Blog post writing skill with structure templates and style guidelines. Guides the agent through writing well-structured, engaging technical blog posts with proper formatting, section flow, and reader engagement techniques. | 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e05958e | |
bootstrap-google-tools core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools/SKILL.md Install/auth CLIs the sandbox lacks - `gws` (Drive, Gmail, Sheets, Calendar), `gcloud`, `agents-cli`, `mcp-cli` (MCP servers). Use on "command not found" or before GCP/Workspace/MCP work. | 68 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e05958e | |
coding-workflow core/python/adk-voice-agent/sandbox/skills/coding-workflow/SKILL.md How to work in a code repository under ~/code. Use for any thread that diagnoses, fixes, changes, reviews, or tests code. | 71 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e05958e | |
content-research-writer contrib/python/agent-skills-tutorial/app/skills/content-research-writer/SKILL.md Content research and SEO writing methodology. Guides the agent through topic research, keyword identification, competitive analysis, and writing SEO-optimized content that ranks well and provides genuine value to readers. | 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e05958e | |
custom-investigation core/python/ambient-quality-agent/src/ambient_quality_agent/skills/custom-investigation/SKILL.md Run a custom investigation: review a chosen slice of conversations instead of a random sample, by writing a SQL selector over the observed agent's telemetry, and optionally narrow what the reviewer reports. Use when a message asks to investigate only certain conversations -- ones that hit an error, used a particular tool, ran slowly, mention a topic, looped, or were abandoned -- or asks to re-review conversations already seen with a different focus. Covers the telemetry table a selector reads, writing the selector, previewing what it matched, and starting the run. | 74 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e05958e | |
deliverables core/python/adk-voice-agent/sandbox/skills/deliverables/SKILL.md How to write a document the user will read (report, itinerary, comparison, plan, notes) and save it to their Google Drive. Use when a thread's result is a document rather than a code change. | 67 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e05958e | |
extract-python-environment-variables .agents/skills/extract-python-environment-variables/SKILL.md Scans a Python recipe to find every place an environment variable is accessed — including `os.environ.setdefault("V", "d")`, whose "d" would otherwise be a hidden default a user editing .env.example has no way to discover — then ensures all variables are declared in `.env.example`, that `load_dotenv()` is bootstrapped in the package `__init__.py`, and that `python-dotenv>=1.0.0` is listed in `pyproject.toml`. When a new entry is added to `.env.example`, the extracted default from source is written as the value (with a `# extracted-by:extract-env-vars` marker and provenance comment); values that look like stubs (`"my-project-id"`, `"changeme"`, `"<...>"`) are downgraded to the TODO placeholder but the source string is preserved in the marker comment. Also detects hardcoded model-name string literals (e.g. `"gemini-3.5-flash"` in `agent.py`) and rewrites them to an `os.getenv(...)` call. The variable name is derived from the assignment target when it names a model (`DEFAULT_EMBEDDING_MODEL` → `EMBEDDING_MODEL`), else `MODEL_NAME` (single model) or `MODEL_NAME_GENERATED_1` / `MODEL_NAME_GENERATED_2`, … (multiple models). Normally no fallback default is written into the Python source; the one exception is when no `load_dotenv()` bootstrap could be installed (no package `__init__.py`), where the original literal is kept as the fallback so the lookup cannot evaluate to `None` at runtime. The model string is written as the value in `.env.example` with a comment prompting a rename. When re-run against a recipe whose `.env.example` already has entries, the writer classifies each entry (skill-authored vs. user-authored, TODO vs. real value) and only rewrites lines it can prove it authored; user-authored lines are always preserved. A stale TODO (either skill-authored or a bare v1-era `<TODO: update-this-value>` with no inline comment) is upgraded in place when source can supply a real default. IMPORTANT — two hard rules the skill NEVER breaks: (1) USER-EDIT SAFETY. Any `.env.example` line the skill cannot prove it authored is USER_OWNED and is never modified. The rewriter fails closed on any structural ambiguity (quoted values, backslash continuation, duplicate declarations) — a stale TODO left in place is cheap; a clobbered user edit is not. (2) ADDITIVE-ONLY FOR PYTHON FILES. The skill never writes new `os.environ.setdefault(...)` bootstrap lines into any Python file. Pre-existing `os.environ.setdefault(...)` or `os.getenv("VAR", "default")` calls that the recipe author wrote by hand are LEFT UNTOUCHED — the skill's only writes to Python files are (a) the `load_dotenv()` bootstrap; (b) `# noqa: E402` on trailing relative imports that would otherwise trip Ruff; (c) hardcoded model-literal replacement. Use when the user wants to "extract env vars", "update .env.example", "add load_dotenv", "surface setdefault defaults", "upgrade stale TODOs in .env.example", "replace hardcoded model names", or "fix environment variables" in a Python recipe. | — | |
filesystem core/python/adk-voice-agent/sandbox/skills/filesystem/SKILL.md Finding and filing things in the home. Use when a thread builds on earlier work (a note, a draft, a past thread), or files, moves, or tidies files. | 67 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e05958e | |
find-skills core/python/long-horizon-harness/horizon/builtin_skills/find-skills/SKILL.md Discover/install NEW agent skills from external sources (skills.sh). Use for capabilities you lack, e.g. "find a skill for X". Do NOT use to list skills you already have; see `<available_skills>`. | 65 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e05958e | |
generate-manifest .agents/skills/generate-manifest/SKILL.md Scan an ADK recipe directory and generate a manifest.yaml for it based on the schema at .github/schemas/manifest-schema.json. Use when the user wants to create or generate a manifest.yaml for a recipe under core/, contrib/, or plugins/. | 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e05958e | |
generate-python-runnability-test .agents/skills/generate-python-runnability-test/SKILL.md Generates a lightweight `tests/test_runnability.py` for a Python recipe. The test just imports the recipe's agent module and asserts that `root_agent is not None` (and `app is not None` if the module defines one). The skill parses agent.py with `ast` to figure out which import-time side effects need mocking (`vertexai.init`, `google.auth.default`) and which env vars need setting (`GOOGLE_CLOUD_PROJECT`, `INTEGRATION_TEST`), and only emits the boilerplate the recipe actually needs. Runs in dry-run (report + preview) and apply (write to disk) modes. Use when the user wants to "add a runnability test", "generate test_runnability.py", "create a smoke test for the recipe", or fix the missing-required-file failure from `python-validate-recipe.yml`. | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e05958e | |
github-pr-review .agents/skills/github-pr-review/SKILL.md Review a GitHub pull request and leave inline comments in a natural human reviewing voice, indistinguishable from comments typed by hand on the GitHub web UI. Deliberately bounded to defects a reader can settle by looking at the anchored line, rather than a deep audit, so every comment is cheap for the author to check. Scales to 2-20 comments by PR size, parallelises analysis across sub-agents, drafts for approval, then posts individually with human pacing. Use when the user says "review this PR", "review PR 123", pastes a github.com/.../pull/N link, or asks for comments on a pull request. Don't use for reviewing local uncommitted changes or a diff against a branch (use the `review` skill for that). | — — — Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e05958e | |
google-workspace core/python/long-horizon-harness/horizon/builtin_skills/google-workspace/SKILL.md Read/write Google Drive, Docs, Sheets, Gmail, Calendar, Chat, Tasks, Slides via the `gws` CLI. Needs an OAuth client or service account configured first. Use for any Google Workspace task. | 68 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e05958e | |
make-python-recipe-deployable .agents/skills/make-python-recipe-deployable/SKILL.md Makes an existing Python recipe deployable: generates the serving files a container needs (Dockerfile, .dockerignore, fast_api_app.py, app_utils/a2a.py, app_utils/services.py, app_utils/reasoning_engine_adapter.py) and configures the recipe to match (required serving dependencies, the App object in agent.py, the hatch wheel package, manifest.deployable). Interactive by design — it asks the recipe owner about runtime data directories and stops for a human decision when a recipe needs an ADK migration or carries a legacy app_utils generation. When docker is available it offers to PROVE the claim: it builds the generated Dockerfile, runs it, probes it, and refuses to flag a recipe deployable if the container does not come up. Does NOT deploy or write terraform. Use when the user wants to "make this recipe deployable", "add a Dockerfile to a recipe", "add the serving files", "containerize a recipe", "verify the container builds", or prepare a recipe for Cloud Build / Artifact Registry. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e05958e | |
policy core/python/long-horizon-harness/horizon/builtin_skills/policy/SKILL.md Inspect the per-workspace tool-policy overlay (.lha/policies.jsonl) that gates destructive or sensitive tool calls, and tell the user what to change if they want a rule added or removed. | 57 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e05958e | |
prepare-python-recipe .agents/skills/prepare-python-recipe/SKILL.md End-to-end orchestration to prepare or update a Python recipe under core/python/, contrib/python/, or plugins/<vertical>/<solution>/ so it passes every check in .github/workflows/python-validate-recipe.yml. Runs eight phases in order on an already-in-place recipe: manifest.yaml generation, environment-variable extraction, pyproject.toml alignment, ruff format+check, per-recipe `uv lock`, runnability-test generation, compile-and-run verification of the generated test file, and a final pass through the repo's own `validate manifest` / `validate structure` validators. Assumes the user has already done the manual prep (deactivated any venv, `git pull` and `uv sync` from the repo root, placed the recipe at its target path, renamed if needed). Delegates to the existing sub-skills (generate-manifest, extract-python-environment-variables, align-recipe-pyproject, generate-python-runnability-test) so the master never duplicates their logic. Pauses at fixed decision points (description mismatch, existing test regeneration) AND is free to interrupt for clarification any time a phase's output looks ambiguous, unexpected, or would benefit from a human judgment call — this is an interactive skill by design. Use when the user wants to "prepare a recipe", "update a recipe end to end", "run all the checks and fixes", "make this recipe PR-ready", or invokes it by name. | — | |
rca core/python/ambient-quality-agent/src/ambient_quality_agent/skills/rca/SKILL.md Root-cause analysis of one AQuA insight against the observed agent's own source code. Use when a message names an insight and asks what the root cause is, how to fix it, why the agent behaved that way, or to diagnose a failure -- for example `Diagnose insight <id> ("<label>") — what is the root cause, and how would you fix it?`. Reads the source snapshot at the revision the failure ran on, plus the complete conversations behind the insight, and answers with `<path>:<start>-<end>` citations, and records the proposed fix against the insight. | 73 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e05958e |