release-process

Step-by-step release checklist for Squad — prevents v0.8.22 and v0.9.4-style disasters

Quality

56%

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

76%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 highly actionable and exceptionally well-sequenced with validation checkpoints and STOP gates, making it a strong operational runbook. Its weaknesses are conciseness (significant repetition across three parallel sections) and progressive disclosure (a 540-line monolith with no bundle files and buried references).

Suggestions

Extract the Common Failure Modes catalog and Post-Mortem Reference into separate files (e.g. failure-modes.md, postmortem.md) referenced once from the main body to reduce repetition and length.

De-duplicate the three parallel checklists (Pre-Release Validation, Common Failure Modes, Validation Checklist) so each rule appears in one canonical place with cross-links.

Surface the external references (PUBLISH-README.md, team-level SKILL.md) inline at first mention rather than only in the trailing 'Related' list.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but it repeats the same validation rules in three places (Pre-Release Validation, Common Failure Modes, Validation Checklist) and the Post-Mortem Reference section rehashes learnings already embedded inline, so it could be tightened.	3 / 5
Actionability	Every step ships copy-paste-ready, executable bash with concrete package names, versions, and expected outputs, plus targeted fix commands for each failure mode.	5 / 5
Workflow Clarity	The release flow is explicitly sequenced (Step 1–7) with per-step Checkpoints, STOP conditions, and a full Validation Checklist; the destructive Rollback Procedure includes unpublish/deprecate/revert branches with validation, satisfying the feedback-loop requirement.	5 / 5
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ are absent) and the body inlines ~540 lines of runbook, failure catalog, and post-mortem that would benefit from being split into separate files; the few external pointers (PUBLISH-README.md, .squad/...SKILL.md) are buried in a 'Related' list rather than clearly signaled at point of use.	2 / 5
	Total	15 / 20 Passed

Description

36%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 names the skill's purpose and ties it to concrete past incidents, but it lacks an explicit 'Use when...' trigger clause and leans on product-specific jargon instead of natural keywords. Specificity is moderate because the only action named ('prevents disasters') is an outcome, not a capability.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when releasing Squad to npm, bumping versions, or cutting a GitHub release.'

Replace the version-number shorthand ('v0.8.22 and v0.9.4-style disasters') with concrete capabilities like 'version bumping, npm publishing, CHANGELOG validation, and dist-tag verification'.

Include natural trigger terms a user would say (publish, ship a release, npm release, CHANGELOG) instead of relying on incident names.

Dimension	Reasoning	Score
Specificity	Names the domain (release checklist) and one concrete action (prevents disasters), but the action is an outcome rather than a concrete capability and 'release checklist' is generic; it lists no specific release actions like version bumping or npm publishing.	3 / 5
Completeness	It states a clear 'what' (a step-by-step release checklist) but has no 'Use when...' trigger clause, so 'when' is entirely absent rather than merely weakly implied.	2 / 5
Trigger Term Quality	The only natural keyword is 'release checklist'; it leans on product-specific jargon (v0.8.22, v0.9.4, Squad) rather than natural phrases a user would say, and offers no synonyms or common variations like 'publish' or 'ship'.	2 / 5
Distinctiveness Conflict Risk	The Squad-specific version numbers and product name carve out a narrow niche unlikely to trigger for unrelated skills, though 'release checklist' alone could overlap with generic CI/release skills.	4 / 5
	Total	11 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (550 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: bradygaster/squad
Path: .copilot/skills/release-process/SKILL.md
Commit: c41b316

Reviewed: ~12 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.