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

70%

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

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, mostly lean workflow skill with concrete commands and a clear step sequence, weakened by redundancy across its changeset-body sections, the absence of a complete worked example, and missing verification checkpoints in the workflow.

Suggestions

Consolidate the three overlapping breaking-change/code-example sections ("Changeset body quality" #5, "Changeset format", and "Code examples in changesets") into one to remove redundancy.

Add one complete worked example of a finished changeset — first line, body, and a code block — so the guidance is copy-paste ready.

Insert explicit verification checkpoints in the workflow, e.g. "Confirm all transitive dependents are selected before running yarn changeset" and "grep docs/READMEs and confirm no stale API references remain after updating."

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and avoids explaining concepts Claude already knows, but breaking-change/code-example guidance recurs across three sections ("Changeset body quality" #5, "Changeset format", and "Code examples in changesets") and could be tightened, matching the score-2 anchor.	2 / 3
Actionability	Concrete commands and paths are present ("yarn changeset", the @data-client/* transitive package map, docs/ and website/blog/ locations, BREAKING prefixes), but there is no complete worked example of an assembled changeset, so it falls short of the copy-paste-ready score-3 bar.	2 / 3
Workflow Clarity	A clear six-step sequence (Analyze → Determine packages → Run changesets → Update docs → Update blog → Update skills) is present, but there are no explicit validation/verification checkpoints for the batch-style multi-package, multi-file updates, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	As a single well-sectioned SKILL.md with no bundle files, it is cleanly organized into Overview/Steps/guidance sections and appropriately points one level deep to external rule files (blog-posts.mdc, markdown-formatting.mdc) rather than inlining them, meeting the score-3 bar for a compact, well-organized skill.	3 / 3
	Total	9 / 12 Passed

Description

82%

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 specific, well-targeted description that names concrete actions and natural trigger terms for a distinct release-tooling niche. Its only real gap is the missing explicit "Use when..." trigger, which caps completeness at 2.

Suggestions

Add an explicit trigger clause such as "Use when preparing a release, bumping package versions, or writing changelog/release notes" so Claude knows when to invoke the skill.

Spell out the release scenarios that should trigger the skill (e.g., after merging a feature/fix, when cutting a release, when documenting a breaking change) to convert the implied "when" into an explicit one.

Dimension	Reasoning	Score
Specificity	"Create user-focused changesets (changelog entries) for semver bumps, release notes, breaking changes, and docs" enumerates multiple concrete deliverable types, matching the score-3 anchor of listing several specific concrete actions rather than a single domain action.	3 / 3
Completeness	The "what" is explicit (create changesets for semver bumps, release notes, breaking changes, docs) but there is no "Use when..." clause or equivalent trigger, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Natural release-tooling terms appear with synonym variation — "changesets (changelog entries)", "release notes", "breaking changes", "semver bumps" — giving good coverage of phrases a developer would actually say, above the single-keyword score-2 bar.	3 / 3
Distinctiveness Conflict Risk	The description carves a clear niche — release/changeset tooling for a monorepo library — with distinct triggers unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	11 / 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: reactive/data-client
Path: .cursor/skills/changeset/SKILL.md
Commit: e823560

Reviewed: 1 day 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.