release-process

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

Quality

67%

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

77%Weight 40%Scale 1-3

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

This is a highly actionable, well-sequenced runbook with strong validation checkpoints and error-recovery feedback loops. Its main weakness is token efficiency: heavy internal repetition and version-specific padding inflate the file, and nothing is offloaded into reference files.

Suggestions

De-duplicate the failure-mode guidance: keep the symptom/root-cause/fix catalog in one place and have Pre-Release Validation and Post-Mortem cross-reference it rather than restating each cause.

Remove the verbatim-duplicated Local Development recovery block (it appears both as a Common Failure Mode fix and again as its own top-level section).

Move the Post-Mortem Reference / Key learnings and the full incident history into a separate reference file (e.g. INCIDENTS.md) referenced one level deep, and isolate time-sensitive version numbers in a deprecated/old-patterns section.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable rather than explanatory, but it repeats the same root-cause/fix guidance in three places (Pre-Release Validation, Common Failure Modes, Post-Mortem learnings) and the local-dev recovery bash block appears verbatim twice; version-specific incident padding is scattered throughout rather than isolated in a deprecated section.	2 / 3
Actionability	Every step ships copy-paste-ready commands (semver validation, npm version, gh release create, npm view/dist-tag, git tag/push, rollback) with expected outputs annotated, matching the fully-executable anchor.	3 / 3
Workflow Clarity	A clear 7-step release sequence is paired with explicit "Checkpoint:" markers, STOP validation gates, a phase-organized checkbox Validation Checklist, and a symptom/root-cause/fix feedback section for error recovery.	3 / 3
Progressive Disclosure	The skill is a monolithic ~540-line file with no bundle files, and content that could be split (Post-Mortem Reference, Common Failure Modes catalog, Local Development recovery) is inline; the few external references (.squad team skill, retrospective, PUBLISH-README.md) are clearly signaled but the skill itself is not appropriately split.	2 / 3
	Total	10 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 distinctive to Squad's release process but is missing an explicit usage trigger and a fuller enumeration of concrete actions. It is competent but not exemplary.

Suggestions

Add an explicit trigger clause, e.g. "Use when releasing Squad to npm or when the user asks to publish/ship a new Squad version."

List the concrete actions covered (version bump, tag, GitHub Release, npm publish verification, rollback) so the description reads as multiple specific capabilities rather than a single artifact.

Replace incident-specific tokens ("v0.8.22 and v0.9.4-style disasters") with general trigger terms like "publish", "ship", "dist-tag", and "rollback" that a user would naturally say.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain and deliverable ("Step-by-step release checklist for Squad") but lists only a single action-type rather than multiple specific concrete actions, so it falls short of the score-3 anchor.	2 / 3
Completeness	It clearly states what the skill is (a release checklist) but provides no explicit "Use when…" trigger, so per the judging guidelines completeness is capped at 2 even though the "when" is implied.	2 / 3
Trigger Term Quality	"release" and "checklist" are natural terms a user might say, but common variations (publish, ship, deploy, npm publish, version bump) are absent, and the version numbers are incident-specific rather than general triggers.	2 / 3
Distinctiveness Conflict Risk	The product-specific scope ("for Squad") plus the incident references (v0.8.22, v0.9.4) carve out a clear niche unlikely to conflict with generic release or deployment skills.	3 / 3
	Total	9 / 12 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: e23dd92

Reviewed: 6 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.