ci-validation-gates

Defensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22

Quality

65%

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 ./.copilot/skills/ci-validation-gates/SKILL.md

Quality

Content

71%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 body is highly actionable with executable validation gates and a useful failure-mode table, organized cleanly into a single appropriately-sized file. The main drag is incident/charter provenance prose in the Context section that pads tokens without aiding execution, and the lack of a single ordered end-to-end publish workflow tying the gates together.

Suggestions

Trim the Context provenance narrative (the v0.8.22 story and the Drucker/Trejo charter sentence) to one line, keeping only what Claude needs to apply the patterns.

Add a short ordered 'Publish workflow' sequence (validate semver -> set SKIP_BUILD_BUMP=1 -> publish -> verify with retry) that ties the standalone gates into one checkpointed flow.

Consider adding an executable snippet or one-line command for NPM Automation-token verification so the token pattern matches the actionability of the semver and retry blocks.

Dimension	Reasoning	Score
Conciseness	The pattern guidance is lean and assumes CI/CD knowledge, but the Context section carries incident/charter provenance padding ('learned from the v0.8.22 release disaster...', 'Both Drucker... and Trejo... carried this knowledge in their charters — now centralized here') that does not help Claude execute.	3 / 5
Actionability	Two complete copy-paste YAML blocks (semver gate, retry loop) plus concrete specifics (5 attempts, 15s intervals, Automation token, SKIP_BUILD_BUMP=1, trigger on 'release: published') give mostly executable guidance; the token-verification, draft-detection, and build-protection patterns are bullet-only with no snippet, a minor gap.	4 / 5
Workflow Clarity	Validation gates are present for the destructive/batch operations (semver check before publish, retry-on-verify, draft detection, SKIP_BUILD_BUMP), clearing the cap of 3, but the gates are presented as standalone patterns rather than one explicitly ordered end-to-end publish sequence with checkpoints.	4 / 5
Progressive Disclosure	A compact single-purpose skill (~77 lines) with clear sections (Context, Patterns, Known Failure Modes, Anti-Patterns) and no external references; per the simple-skills note this well-organized single-file structure merits a 5.	5 / 5
	Total	16 / 20 Passed

Description

58%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 distinct, listing four concrete defensive CI/CD patterns, but it omits any 'Use when...' trigger guidance and leans on technical jargon over the natural phrases users would actually say. Adding an explicit usage trigger with synonyms would lift the completeness and trigger-term scores.

Suggestions

Append a 'Use when...' clause naming concrete trigger situations, e.g. 'Use when publishing npm packages, fixing EOTP or invalid-semver publish failures, or hardening release workflows'.

Add natural-language trigger terms and synonyms users say in distress ('npm publish failing', 'EOTP', 'invalid semver', 'draft release') rather than only pattern-category jargon.

Drop or relocate the 'earned from v0.8.22' provenance from the description so the limited budget foregrounds capability and trigger guidance.

Dimension	Reasoning	Score
Specificity	The description enumerates four concrete defensive patterns ('semver validation', 'token checks', 'retry logic', 'draft detection'), which is several specific actions, but each reads as a category label rather than a fully-specified concrete action like the 5-anchor example.	4 / 5
Completeness	A clear 'what' is present (defensive CI/CD patterns with named sub-actions), but there is no 'Use when...' or equivalent trigger clause; 'earned from v0.8.22' is provenance, not usage guidance, so per the rubric completeness caps at 3.	3 / 5
Trigger Term Quality	Terms like 'CI/CD patterns', 'semver validation', 'token checks', 'retry logic', and 'draft detection' are domain jargon; the natural phrases a user in distress would say ('npm publish failing', 'invalid semver', 'EOTP', 'draft release') and their synonyms are absent.	3 / 5
Distinctiveness Conflict Risk	The release/publish CI-hardening niche ('semver validation', 'token checks', 'retry logic', 'draft detection') is mostly distinct with only minor overlap risk against general CI/CD skills.	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: bradygaster/squad
Path: .copilot/skills/ci-validation-gates/SKILL.md
Commit: 9587fcd

Reviewed: 1 day 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.