mflux-release

Prepare a release in mflux (version bump, changelog, contributors, uv lock) without tagging/publishing. Use when preparing a release branch or release PR.

Quality

93%

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

87%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.

The body is actionable and token-efficient with concrete commands and useful guardrails, and is well-organized for a simple skill. Its main weakness is workflow clarity: the checklist lacks explicit validation checkpoints and treats verification as optional for a consequential batch operation.

Suggestions

Promote the sanity checks from optional to a required validation checkpoint (e.g., run `make test-fast` and confirm `uv lock` produces no unexpected diff before committing), with a fix-and-retry loop on failure.

Convert the release-prep checklist into an explicit numbered sequence so the ordering (bump → review commits → write changelog → source contributors → uv lock → verify → commit) is unambiguous.

Add a brief final verification step that confirms the changelog entry, version, and lockfile are mutually consistent before creating the "Release <version>" commit.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: no concept re-explanation, and every line is task-specific guidance (commands, commit naming, contributor sourcing rules) that earns its place.	3 / 3
Actionability	Provides concrete executable commands ("git log --oneline v.<last-version>..HEAD", "gh pr list --state merged", "uv lock", "make test-fast"), a specific commit name ("Release <version>"), and real GitHub URLs — copy-paste ready.	3 / 3
Workflow Clarity	Steps are present as a checklist but sequencing is implicit and validation is marked "optional unless requested", leaving checkpoints missing for a batch-style release-prep operation per the cap guidance.	2 / 3
Progressive Disclosure	Under 50 lines with no bundle files needed; content is organized into clear "When to Use" and "Instructions" sections, satisfying the simple-skill allowance for well-organized single-file structure.	3 / 3
	Total	11 / 12 Passed

Description

100%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 concise, concrete, and complete: it names specific actions, scopes out tagging/publishing, and gives an explicit "Use when" trigger. It is clearly distinguishable and uses natural trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "version bump, changelog, contributors, uv lock" — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Clearly states what it does (prepare a release with named sub-tasks) and when to use it ("Use when preparing a release branch or release PR"), satisfying both what and when with an explicit trigger.	3 / 3
Trigger Term Quality	Natural user terms "release", "release branch", and "release PR" appear in the explicit trigger clause, giving good coverage of phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped to mflux release prep with distinct, domain-specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: filipstrand/mflux
Path: .cursor/skills/mflux-release/SKILL.md
Commit: 4ac641e

Reviewed: 8 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.