agentleFS
GoogleKnown publishergoogle/adk-samples/.agents/skills/scaffold-python-recipe/SKILL.md

scaffold-python-recipe

Skill11k starsChanged 45 days agoApache-2.0View on GitHub

This skill should be used when the user wants to "create a new Python ADK recipe", "scaffold a new Python recipe", "generate a new Python recipe in contrib", "add a new Python recipe to the adk-recipes repository", or "create a Python adk recipe". It utilizes an automated script to copy template files and resolve basic placeholders.

1 other project uses a version of this.

Trending

More talk lately.about the whole repository

Dec 2025: 1 mentionJan 2026: 1 mentionFeb 2026: 2 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 1 mentionJun 2026: 1 mentionJul 2026: 2 mentionsAug 2026: 0 mentionsSep 2026: 4 mentionsOct 2026: 4 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the google/adk-samples repository that our weekly crawl found. There is no adoption data for this file yet.

Most recently taken up by

Who's talking about google/adk-samples

The biggest 5 of 32 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 32

Talked about on GitHub, Bluesky, Hacker News and Stack Overflow (32 times).

On GitHub · 23

18 more on GitHub

On Bluesky · 4

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill to scaffold a new Python ADK recipe inside this repository using the automated script at scripts/scaffold.py.

    line 16
  2. Very specific:

    No Manual Boilerplate Writing: Always use scripts/scaffold.py to create the recipe.

    line 22
  3. Distinctive:

    Use the Correct Terminology (Recipe): Always refer to what is being created as a recipe, never as a "project".

    line 24
  4. Distinctive:

    If the user has not specified which directory, ask them to choose.

    line 39
  5. Distinctive:

    Does not start or end with a hyphen

    line 48
  6. Distinctive:

    If the user provided a name, validate it against these rules before proceeding.

    line 50
  7. Distinctive:

    Do not make any further changes.

    line 77

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Scaffolding a New Python ADK Recipe

Use this skill to scaffold a new Python ADK recipe inside this repository using the automated script at scripts/scaffold.py.


Rules

  1. No Manual Boilerplate Writing: Always use scripts/scaffold.py to create the recipe. Never write the boilerplate files manually.
  2. Do Not Modify After Scaffolding: Once the script runs successfully, do not make any further changes to the recipe in this turn.
  3. Use the Correct Terminology (Recipe): Always refer to what is being created as a recipe, never as a "project". Ensure all output messages, instructions, and explanations to the user use "recipe" exclusively.

Inputs

You must have both pieces of information below before running the script. If either is missing or was not explicitly provided by the user, ask for it — do not assume or use a default.

1. Output Directory (Required — must ask if not provided)

The user must choose one of these valid locations:

  • contrib/python/ — community recipes; preferred for new Python recipes
  • core/python/ — curated recipes
  • contrib/ — legacy flat layout, still accepted; prefer contrib/python/

If the user has not specified which directory, ask them to choose. Do not proceed until a valid choice is confirmed.

This skill cannot scaffold a vertical plugin (plugins/<vertical>/<solution>/). Those have a different shape — SKILL.md, EVAL.yaml, scripts/, assets/, references/, tests/unit/ — and no template ships for them yet. If the user asks for one, tell them so rather than scaffolding into the wrong place.

2. Recipe Name (Required — must ask if not provided)

The recipe name must satisfy all of the following rules:

  • Contains only lowercase letters and hyphens (a-z, -)
  • Is 30 characters or less
  • Does not start or end with a hyphen

If the user provided a name, validate it against these rules before proceeding. If it is invalid, explain which rule it violates and ask for a corrected name. Do not proceed until a valid name is confirmed.


Run

Execute the scaffold script:

python3 .agents/skills/scaffold-python-recipe/scripts/scaffold.py --name <RECIPE_NAME> --output-dir <OUTPUT_DIRECTORY>

The script accepts exactly two flags: --name (required) and --output-dir (required). Do not pass any other flags.


Respond

Once the script succeeds, inform the user the recipe is ready and highlight the following required next steps:

  1. Update manifest.yaml: Fill in the description, ownership.team, and ownership.poc fields (placeholders are marked with TODO:). This file is validated by CI and must not contain placeholder values. Use the generate-manifest skill if you want it populated automatically from the source code.
  2. Update README.md: Replace the generic title and description with details specific to this recipe (ownership/POC live in manifest.yaml, above — not in the README).

Then, provide these quick-start commands:

cd <OUTPUT_DIRECTORY>/<RECIPE_NAME>
uv sync                  # install dependencies
uv run pytest            # run the test suite
uv run adk run app       # run the agent interactively

Do not make any further changes. End your turn.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.