changeset

Create user-focused changesets (changelog entries) for semver bumps, release notes, breaking changes, and docs; prefer impact and code examples over implementation detail

Quality

71%

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 ./.cursor/skills/changeset/SKILL.md

Quality

Content

76%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.

The skill body is concise, actionable, and well-structured with clear external references, but its batch workflow lacks explicit validation/verification checkpoints, which the rubric caps at 3 for workflow clarity. Adding a verification step before completion would substantially raise the score.

Suggestions

Add an explicit validation/verification step to the workflow (e.g. re-run `yarn changeset status` or confirm every changed API usage in docs/READMEs has been updated before finishing).

Include one concrete copy-paste example of a complete changeset body (with a breaking-change Before/After) to push actionability to 5.

Add a short final checklist summarizing the verification gates (changesets written, docs updated, blog updated, skills updated) to strengthen the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, never explaining what a changeset or semver is; every section earns its place, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	Provides concrete commands (`yarn changeset`), specific paths, and explicit package-mapping rules, but stops short of a literal copy-paste example of a complete changeset body, leaving minor gaps versus the fully executable 5.	4 / 5
Workflow Clarity	The six steps are clearly sequenced, but this batch/multi-file operation touches docs, blog, and skills across many packages with no validation or verification checkpoint, and the rubric caps workflow clarity at 3 for batch/destructive work without validation.	3 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections with one-level-deep references to external rule files (`@website/blog/.cursor/rules/blog-posts.mdc`, `@.cursor/rules/markdown-formatting.mdc`); minor organization gaps keep it just below the ideal 5.	4 / 5
	Total	16 / 20 Passed

Description

66%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.

The description names a concrete, well-scoped set of actions with good trigger vocabulary, but it omits any explicit 'Use when' trigger clause, which caps its completeness. It is a strong, mostly-distinct description that would benefit from a trigger clause.

Suggestions

Add an explicit 'Use when ...' clause, e.g. 'Use when preparing a release, bumping versions, or drafting changelog/release-note entries for user-facing changes.'

Add common synonyms like 'version bump' or 'changelog' phrasing users might naturally say to push trigger_term_quality toward 5.

Tighten the 'docs' reference to a more specific scope to reduce overlap with general documentation skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("changesets (changelog entries) for semver bumps, release notes, breaking changes, and docs") with only minor coverage gaps, matching the 'lists several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	It clearly states the 'what' but contains no explicit 'Use when...' trigger clause, and the rubric caps completeness at 3 when trigger guidance is only weakly implied.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ("changesets", "changelog entries", "semver bumps", "release notes", "breaking changes") with good coverage; a few synonyms (e.g. "version bump") are missing, so it sits above 3 but below the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The changeset/release-notes niche is mostly distinct with clear triggers, though the broad mention of "docs" creates minor overlap risk with documentation skills, placing it just below the minimal-conflict 5.	4 / 5
	Total	15 / 20 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: reactive/data-client
Path: .cursor/skills/changeset/SKILL.md
Commit: ef4653f

Reviewed: 4 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.