CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 feedback loops. Its weak spots are overall length and the absence of progressive disclosure — the entire detailed workflow and CHANGELOG/data-loss guidance sit inline in one file.

Suggestions

Move the CHANGELOG style guidance (section order, length/tone, Good/Bad editorial-framing examples) and the Data-Loss Surface Review into reference files (e.g. references/CHANGELOG.md, references/data-loss-review.md), leaving SKILL.md as a lean overview that links to them — this would lift both conciseness and progressive_disclosure.

Tighten the prose rationale in the numbered steps (e.g. the --ff-only / wt up aside in step 1 and the drift explanation in step 12) to imperative instruction plus a one-line reason, cutting tokens while preserving the failure-prevention intent.

If the full workflow must stay inline, add a short top-of-file table of contents linking to each major section so the long single file is navigable as a one-level overview.

DimensionReasoningScore

Conciseness

The body is dense with project-specific, non-obvious detail (not generic concepts Claude already knows), but at ~290 lines it carries prose-heavy rationale passages (e.g. the --ff-only / wt up aside, the CHANGELOG tone guidance with Good/Bad examples) that could be tightened without losing clarity.

2 / 3

Actionability

Packed with executable, copy-paste-ready commands (cargo release ... -x --no-publish, git tag vX.Y.Z "$MERGE_SHA", gh pr view --json mergeCommit) plus concrete templates for the changelog-verify subagent and entry formats.

3 / 3

Workflow Clarity

A clearly numbered 13-step sequence with explicit validation checkpoints and feedback loops: pre-merge hook, semver-checks, the drift check ("Expect a single line ... re-run the check"), the MANDATORY changelog-verify subagent, and required sign-off before tagging.

3 / 3

Progressive Disclosure

No bundle files exist; the full detailed material lives inline in one ~290-line SKILL.md rather than the file being an overview pointing to reference materials, though it is well-organized with internal anchor links.

2 / 3

Total

10

/

12

Passed

Description

90%

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 strong, well-targeted description with explicit triggers and a clear niche. Its only weakness is that the capability statement leans on trigger synonyms rather than listing the concrete actions the workflow performs.

DimensionReasoningScore

Specificity

Names the domain ("Worktrunk release workflow") and concrete publish targets ("crates.io and GitHub"), but the distinct concrete actions are limited and mostly phrased as trigger synonyms ("do a release", "cut a release") rather than enumerated capabilities.

2 / 3

Completeness

Explicitly answers both what ("Worktrunk release workflow") and when ("Use when user asks to ...") with an explicit trigger clause.

3 / 3

Trigger Term Quality

Covers multiple natural phrases a user would actually say — "do a release", "release a new version", "cut a release", and "publish a new version to crates.io and GitHub".

3 / 3

Distinctiveness Conflict Risk

A clear, project-specific niche (releasing Worktrunk to crates.io and GitHub) with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 3 suspicious

Warning

Total

13

/

16

Passed

Repository
max-sixty/worktrunk
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.