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.
63
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/release/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description with excellent trigger terms and completeness. Its main weakness is that the 'what' portion could be more specific about the concrete steps involved in the release workflow (e.g., version bumping, tagging, changelog generation). The distinctiveness is strong due to the project-specific naming and platform-specific references.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Bumps version numbers, creates git tags, publishes crates to crates.io, and creates GitHub releases' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain ('release workflow') and mentions publishing to crates.io and GitHub, but doesn't list the specific concrete steps involved (e.g., bumping version numbers, creating tags, running tests, generating changelogs). It's more of a summary than a detailed capability list. | 2 / 3 |
Completeness | Clearly answers both 'what' (Worktrunk release workflow, publishing to crates.io and GitHub) and 'when' (explicit 'Use when' clause with multiple trigger phrases). The when clause is explicit and well-defined. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases: 'do a release', 'release a new version', 'cut a release', 'publish a new version', 'crates.io', 'GitHub'. These are exactly the phrases a user would naturally say when requesting this workflow. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Worktrunk release workflow' is project-specific, and the combination of crates.io + GitHub publishing with release-specific trigger terms creates a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%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 and well-sequenced release workflow with excellent concrete commands and validation checkpoints. However, it is severely bloated — the CHANGELOG guidance section alone is longer than many entire skills, with extensive editorial rules, contributor credit workflows, and verification procedures that should be split into separate reference files. The skill would benefit enormously from extracting the CHANGELOG details into a referenced file and keeping only a concise summary in the main workflow.
Suggestions
Extract the CHANGELOG Review section (including contributor credits, issue reporter credits, verification, and editorial guidelines) into a separate CHANGELOG_GUIDE.md and reference it with a single link from the main workflow step.
Condense the editorial guidance (tone, ordering, combining bullets) into a compact checklist rather than good/bad examples and lengthy explanations — Claude already understands writing tone.
Trim the 'Credit Issue Reporters' three-step discovery process into a compact numbered list without the extensive explanatory prose about why each step is needed.
Remove explanatory framing like 'This is non-negotiable — changelog mistakes are a recurring problem' and 'Users who take time to report bugs... deserve recognition' — these explain motivation rather than providing actionable instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~200+ lines. The CHANGELOG section alone is massive with extensive editorial guidance (tone advice, ordering rules, credit attribution workflows, mandatory subagent verification). Much of this could be condensed significantly — Claude doesn't need lengthy explanations about why commit messages mislead, editorial framing rules, or detailed 'when to credit' heuristics. The contributor credit section alone has three multi-step discovery workflows that could be a compact checklist. | 1 / 3 |
Actionability | The skill provides fully executable commands throughout — specific bash commands for tagging, git log queries, gh CLI invocations, cargo release commands with exact flags, and even a subagent prompt template. Every step has concrete, copy-paste-ready commands with clear variable placeholders (X.Y.Z). | 3 / 3 |
Workflow Clarity | The 12-step workflow is clearly sequenced with explicit validation checkpoints: running tests first, semver-checks before bumping, mandatory changelog verification via subagent, user confirmation before proceeding, and CI monitoring after tag push. The reset-and-recommit pattern in steps 7-9 is well-explained with the rationale for folding commits. Error recovery is addressed (e.g., semver-checks failure handling, verification escalation to user). | 3 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files. The massive CHANGELOG section (credit contributors, credit issue reporters, verification, link docs) could easily be split into a separate CHANGELOG_GUIDE.md. The skill has reasonable section headers but everything is inline, making it harder to navigate and consuming excessive context window space. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 |
Total | 9 / 11 Passed | |
- Repository
- max-sixty/worktrunk
- Commit
bd4c399
- Reviewed
Table of Contents
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.