release

Worktrunk release workflow. Use when user asks to "do a release", "release a new version", "cut a release", or wants to publish a new version to crates.io and GitHub.

Quality

83%

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

Quality

Content

77%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.

A highly actionable, well-sequenced release runbook with strong validation gates and feedback loops. Its weaknesses are verbosity in the prose-coaching sections and a monolithic structure that inlines material (verification template, finder charters) better suited to reference files.

Suggestions

Move the changelog-verification subagent prompt template and the data-loss finder charters into reference files (e.g. references/verify-changelog.md, references/data-loss-finders.md) and link to them one level deep, trimming SKILL.md toward an overview.

Tighten the CHANGELOG prose-coaching sections — collapse the 'No editorial framing' Good/Bad pair and the 'Sentences stretch to fit / ratchet' narrative into a few compact rules, since they restate writing craft rather than release mechanics.

Consider a short 'Quick start' summary of the 13 steps at the top so the core sequence is legible before the detailed rationale.

Dimension	Reasoning	Score
Conciseness	Much of the detail is earned project-specific gotcha knowledge (why --ff-only vs wt up, why nightly vs ci.yaml), but the prose-style coaching sections ('No editorial framing' Good/Bad pair, 'Sentences stretch to fit…', the ratchet narrative) are explanation that could be tightened, matching the 'mostly efficient but some unnecessary explanation' anchor.	3 / 5
Actionability	Nearly every step ships copy-paste-ready bash including jq filters for run discovery and an awk word-count check; specific commands cover the common release cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	A clear 13-step sequence with explicit validation gates (local + cross-platform tests, changelog-covers-main check, MANDATORY verify-each-entry subagent, sign-off before tag) and re-run-until-clean feedback loops, matching the top anchor for a destructive/publishing workflow.	5 / 5
Progressive Disclosure	No bundle files exist and the ~340-line body is monolithic; sizable chunks (the changelog-verification subagent template, the data-loss finder charters) are inlined where reference files would serve, though in-skill headers and signaled links to CLAUDE.md/evals/README.md keep it organized, landing on the 'some structure, content that should be separate is inline' anchor.	3 / 5
	Total	16 / 20 Passed

Description

90%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.

A tight, well-constructed description: explicit what-and-when with natural trigger synonyms and a clear Worktrunk-specific niche. The only gap is that it states the domain and one publish action rather than enumerating the several concrete release steps.

Dimension	Reasoning	Score
Specificity	Names the domain ('Worktrunk release workflow') and one concrete action ('publish a new version to crates.io and GitHub'), but does not enumerate the several concrete release actions, matching the 'names domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	Explicitly answers both 'what' (release workflow / publish to crates.io and GitHub) and 'when' with concrete 'Use when...' trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Covers multiple natural synonyms a user would actually say — 'do a release', 'release a new version', 'cut a release' — plus platform targets, matching the comprehensive-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Scoped to 'Worktrunk release workflow' with release-specific trigger phrases, giving it a clear niche and minimal overlap with other skills.	5 / 5
	Total	18 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 5 suspicious	Warning

	Total	13 / 16 Passed

Repository: max-sixty/worktrunk
Path: .claude/skills/release/SKILL.md
Commit: 6c263ed

Reviewed: 9 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.