skill-release-gate

Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./phases/13-tools-and-protocols/27-skill-evals-packaging-and-portability/outputs/skill-release-gate/SKILL.md

Quality

Content

85%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.

The content is a tight, well-structured release-gate workflow with explicit validation and a clear failure feedback loop, supported by real one-level-deep bundle references; the main gap is presenting the evaluator invocation as a ready-to-run command rather than prose.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence (no explanations of what a skill, hash, or attestation is), though steps 8 and 11 are wordy and could be tightened without losing substance.	4 / 5
Actionability	It gives concrete file paths and flags ('scripts/evaluate_skill.py', '--fixture-demo', '--attestation', '--trusted-attestation-sha256') and explicit argv construction, but presents the command line in prose rather than as a copy-paste-ready invocation.	4 / 5
Workflow Clarity	Eleven well-sequenced steps include explicit validation checkpoints (hash verification in step 7, external attestation in step 9) and a 'Failure behavior' section that forms a clear stop-and-report feedback loop for failed gates.	5 / 5
Progressive Disclosure	SKILL.md is a lean overview pointing one level deep to real, clearly signaled bundle files (references/eval-contract.md, scripts/evaluate_skill.py, assets/hosts.json, assets/manifest.json), all verified present, with well-organized sections.	5 / 5
	Total	18 / 20 Passed

Description

62%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.

The description is specific and occupies a well-distinguished niche, but it lacks an explicit 'Use when...' trigger clause and relies on technical jargon over natural user phrasings, capping the trigger and completeness dimensions at 3.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases, e.g. 'Use when publishing, shipping, or distributing an Agent Skill bundle, or when the user asks to review a skill before release.'

Swap some technical terms for user-natural synonyms (publish/ship/distribute a skill, check before release) to improve trigger term coverage.

Keep the seven evaluation domains but consider pairing 'Evaluate' with a second concrete verb (e.g. 'gate' or 'certify') to strengthen the specificity of actions.

Dimension	Reasoning	Score
Specificity	Names seven concrete evaluation domains ('structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability'), giving broad coverage, though it is a single verb ('Evaluate') applied to many nouns rather than multiple distinct actions.	4 / 5
Completeness	The 'what' is clear and detailed, but the 'when' is only weakly implied by 'before release' and there is no explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Relevant terms like 'Agent Skill bundle', 'release', and 'portability' appear, but they lean technical and omit the natural phrasings a user would actually say ('publish a skill', 'ship a skill', 'check my skill before publishing').	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche—gating an Agent Skill bundle for release—with distinct, specialized triggers and minimal overlap risk against other skills.	5 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rohitg00/ai-engineering-from-scratch
Path: phases/13-tools-and-protocols/27-skill-evals-packaging-and-portability/outputs/skill-release-gate/SKILL.md
Commit: c02ca08

Reviewed: 4 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.