scaffold-python-recipe

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

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exemplar of a lean, actionable scaffolding skill: concise, fully executable commands, explicit validation gates, and clean one-level file structure. No dimension falls below the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what ADK, a recipe, uv, pytest, or manifest fields are — and every line is an operational guardrail, validation rule, or executable command, matching the 'every token earns its place' anchor 3.	3 / 3
Actionability	It gives a fully executable scaffold command with clearly marked <RECIPE_NAME>/<OUTPUT_DIRECTORY> placeholders, exact quick-start commands (uv sync, uv run pytest, uv run adk run app), precise naming rules, fixed output directories, and specific manifest fields to fill — copy-paste ready per anchor 3.	3 / 3
Workflow Clarity	A clear Inputs → Run → Respond sequence carries explicit pre-run validation gates ('Do not proceed until a valid choice is confirmed', 'validate it against these rules... Do not proceed until a valid name is confirmed'); the operation is non-destructive (the script refuses to overwrite an existing target), so per the simple-skill scoring note this merits anchor 3.	3 / 3
Progressive Disclosure	The body is organized into well-separated sections (Rules, Inputs, Run, Respond) and references a single one-level-deep bundle file, scripts/scaffold.py, which was verified to exist; there are no nested references and no monolithic wall of text, matching anchor 3.	3 / 3
	Total	12 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: explicit trigger guidance, natural varied trigger terms, third-person voice, and a clear niche. Its only weakness is specificity — the 'what' names a single action mechanism rather than enumerating the concrete artifacts produced.

Suggestions

Name the concrete artifacts the script produces (e.g. recipe directory structure, manifest.yaml, README.md, test scaffolding) alongside 'copy template files and resolve basic placeholders' to reach the 'lists multiple specific concrete actions' anchor for specificity.

Since the five trigger phrases all express one scaffolding intent, consider adding distinct concrete outcome verbs (e.g. 'creates', 'validates naming', 'populates placeholders') so the capability list reads as multiple specific actions rather than restatements of one.

Dimension	Reasoning	Score
Specificity	It names the domain ('Python ADK sample') and one concrete action mechanism ('utilizes an automated script to copy template files and resolve basic placeholders'), but the five quoted trigger phrases all describe variations of a single intent rather than multiple distinct concrete actions, matching anchor 2 rather than anchor 3.	2 / 3
Completeness	It explicitly answers both 'what' ('utilizes an automated script to copy template files and resolve basic placeholders') and 'when' via an explicit 'This skill should be used when the user wants to...' clause, so it is not capped at 2 and matches anchor 3; voice is third-person so no specificity penalty applies.	3 / 3
Trigger Term Quality	It provides five natural, varied phrasings a user would actually say ('create a new Python ADK sample', 'scaffold a new Python sample recipe', 'add a new Python sample to the adk-samples repository', 'generate a new Python sample in contrib', 'create a Python adk sample'), giving good coverage of trigger variations per anchor 3.	3 / 3
Distinctiveness Conflict Risk	It is narrowly niched to scaffolding Python ADK samples in a named repository with distinct, specific triggers, making it unlikely to fire for an unrelated skill per anchor 3.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: google/adk-samples
Path: .agents/skills/scaffold-python-recipe/SKILL.md
Commit: a862ebc

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.