generate-manifest

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 skills/.

Quality

88%

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

88%Weight 40%Scale 1-5

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

A highly actionable, well-sequenced skill body with strong validation feedback loops and concrete copy-paste artifacts. Its main weakness is minor verbosity from inlined configuration specifics rather than pointing one level deep.

Suggestions

Move the exact policy.yml size-limit numbers out of the 'large' field rule and replace with a one-line pointer to .github/policy.yml (recipe_size_limits), keeping the overview free of time-sensitive specifics.

Tighten repeated ownership cautions in steps 3 and 6 into a single stated rule referenced once, to reduce token weight on the same guidance.

Dimension	Reasoning	Score
Conciseness	Dense, actionable content with almost no padding of concepts Claude already knows; a few spots could be trimmed, e.g. the inlined policy numbers in the 'large' field rule and some restated cautions. It is efficient rather than maximally lean, so not a 5.	4 / 5
Actionability	Provides copy-paste-ready guidance: the exact `uv run validate manifest <recipe-path>` command, literal placeholder strings the validator checks for, and a complete inline YAML template with allowed options per field.	5 / 5
Workflow Clarity	A clearly sequenced 7-step process with an explicit validation checkpoint (step 6) that distinguishes real schema errors (fix and re-validate) from expected placeholder errors (leave as-is), forming a genuine validate→fix→retry feedback loop.	5 / 5
Progressive Disclosure	Well-organized into clear sections with a single self-contained file and no nested references (no bundle files exist). Not a 5 because some inline detail, like the policy.yml size numbers, is inlined where a one-level pointer would keep the overview leaner.	4 / 5
	Total	18 / 20 Passed

Description

87%Weight 40%Scale 1-5

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

A strong, specific description with an explicit 'Use when' trigger and concrete artifact/path references. It clearly communicates both capability and invocation context with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Names two concrete actions ('Scan an ADK recipe directory' and 'generate a manifest.yaml') tied to a specific schema path, listing specific actions with only minor coverage gaps; it is not a 5 because it stops at scan+generate without enumerating the validate/inspect sub-actions.	4 / 5
Completeness	Explicitly answers both 'what' (scan a recipe directory and generate a manifest.yaml against a named schema) and 'when' (a 'Use when the user wants to create or generate a manifest.yaml for a recipe under core/, contrib/, or skills/' clause with concrete triggers).	5 / 5
Trigger Term Quality	Includes natural user phrases like 'create or generate a manifest.yaml' plus concrete location terms 'core/, contrib/, or skills/'; good keyword coverage, though it lacks obvious synonyms a user might say like 'recipe metadata'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (ADK recipe manifest generation under specific top-level dirs) with distinct triggers and a unique artifact (manifest.yaml), so overlap with other skills is minimal.	5 / 5
	Total	18 / 20 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-manifest/SKILL.md
Commit: 2d0c272

Reviewed: 3 days 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.