release-process

Operate Squad's automated insider, preview, and stable release channels safely

Quality

69%

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/release-process/SKILL.md

Quality

Content

81%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 well-structured, actionable runbook with strong workflow validation and recovery guidance. Main weaknesses are minor verbatim boilerplate repetition and reliance on an external canonical runbook for 'exact commands'.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational, assuming Claude's competence, with only minor trimmable repetition of the verbatim 'Human-only... Agents must stop, hand off' boilerplate, fitting anchor 4 rather than the fully lean anchor 5.	4 / 5
Actionability	Concrete copy-paste commands appear throughout (git fetch, gh workflow run, npm view, npx vitest run), but it defers 'exact commands' to an external runbook and mixes $VERSION placeholders with a hardcoded example, placing it at anchor 4 rather than 5.	4 / 5
Workflow Clarity	Each channel follows a clear sequence with explicit validation checkpoints (Preconditions, 'stop if any version-only change appears'), a Verify step, and a Recovery feedback loop, satisfying anchor 5 and avoiding the missing-validation cap.	5 / 5
Progressive Disclosure	The file is well-sectioned (Preconditions, Preview, Insider, Stable, Verify, Recovery) with a clearly signaled one-level external reference to the canonical runbook, but no bundle files exist to split content further, fitting anchor 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

57%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 clearly distinct but lacks explicit trigger guidance, capping completeness and trigger quality. Adding a 'Use when...' clause with natural synonyms would lift the weaker dimensions.

Suggestions

Append a 'Use when...' clause naming natural triggers (e.g., 'Use when preparing or cutting a Squad insider, preview, or stable release').

Expand action vocabulary beyond 'Operate' to concrete verbs like 'prepare, validate, dispatch, and verify' to raise specificity.

Add common synonyms or aliases users might say (e.g., 'cut a release', 'publish', 'promote') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the release domain and three concrete channel targets (insider, preview, stable) but offers only a single generic action verb ('Operate'), fitting anchor 3 rather than 4 which requires several distinct actions.	3 / 5
Completeness	It clearly states what the skill does but provides no 'Use when...' trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant terms like 'release channels', 'insider', 'preview', and 'stable' are present but the set is limited with no synonyms or file extensions, matching anchor 3 rather than the broader coverage of anchor 4.	3 / 5
Distinctiveness Conflict Risk	The Squad-specific release channel niche is highly targeted with distinct triggers and minimal overlap risk, matching anchor 5.	5 / 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/release-process/SKILL.md
Commit: 2099faf

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.