Name: generate-python-runnability-test
Rating: 75.2 (1 reviews)
Author: google

generate-python-runnability-test

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`.

Quality

92%

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

85%

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

The body is highly actionable with a clear, validated workflow and appropriate use of a bundle script. Its main weakness is conciseness, due to verbose rationale and some duplication between the Rules and Respond sections.

Suggestions

Trim the historical-bug anecdote and the `ast.walk` breadth rationale to a single sentence each, or move them into a comment in the script where the logic lives.

Consolidate the overlapping guidance in 'Rules for the Agent' and 'Respond' so each behavior is stated once; the Respond section can reference the rules rather than restating them.

Consider shortening the multi-paragraph 'What This Skill Does' rationale to bulleted facts, keeping only what the agent needs to decide when to invoke the skill.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and repo-specific, but verbose rationale (e.g. the 'Historical bug closed by this' anecdote, the `ast.walk` breadth parenthetical) and duplicated guidance between 'Rules for the Agent' and 'Respond' could be tightened without losing clarity.	2 / 3
Actionability	Provides multiple complete, executable `uv run` commands, a full input-field table, an exact output schema, and copy-paste-ready apply/overwrite/override examples.	3 / 3
Workflow Clarity	A clear numbered 1–5 sequence with an explicit dry-run-first validation checkpoint, `refused_overwrite`/`error` feedback loops, edit-safety safeguards, and a post-apply pytest reminder.	3 / 3
Progressive Disclosure	Implementation is delegated to the real bundle file `scripts/generate_runnability_test.py` (verified present), with SKILL.md serving as a well-organized one-level-deep instruction layer.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 specific, complete, and distinctive, with explicit natural-language triggers and concrete capabilities. It is among the strongest examples for this rubric.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — generating `tests/test_runnability.py`, importing the agent module and asserting `root_agent`/`app`, parsing with `ast`, mocking `vertexai.init`/`google.auth.default`, setting `GOOGLE_CLOUD_PROJECT`/`INTEGRATION_TEST`, and dry-run/apply modes — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers what it does (generation, parsing, modes) and when to use it via an explicit 'Use when...' clause with multiple triggers, satisfying the top anchor.	3 / 3
Trigger Term Quality	Explicit natural triggers ('add a runnability test', 'generate test_runnability.py', 'create a smoke test for the recipe', fix missing-required-file failure) give good coverage of phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A very specific niche (runnability test for Python recipes, naming the `python-validate-recipe.yml` CI file) makes it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 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/generate-python-runnability-test/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.