CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

changesets

Use when: adding changesets to pull requests, determining semver bump types, versioning packages, or preparing releases. Covers changeset file format, semver guidance, when changesets are required, and the release pipeline.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is changesets in primer/react

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A well-crafted instruction skill: concrete, copy-paste-ready examples, unambiguous creation paths, and a useful good/avoid contrast for description writing. The main improvement levers are trimming contextual narration and adding an explicit validation checkpoint (e.g., confirming the changeset-bot result) to the workflow.

Suggestions

Trim the "Release pipeline" section to a short note that changesets feed an automated Version Packages PR, and point to the contributor docs for pipeline detail — the current narrative explains context rather than instructing the author.

Add an explicit validation step to the creation workflow, e.g. "After opening the PR, check the changeset-bot comment to confirm the changeset was detected; if flagged, verify the frontmatter package name and bump type."

Consider moving the detailed patch/minor/major bullet lists into the already-referenced contributor-docs/versioning.md, keeping inline only the ambiguous cases (e.g., type broadening/narrowing, data-component attributes) that authors most often get wrong.

DimensionReasoningScore

Conciseness

The body is efficient — every section carries operational weight (file format, good/avoid examples, bump lists, skip rules) and avoids explaining generic concepts. Minor trimming opportunities remain, e.g., the "Understanding the release pipeline helps explain why changesets are required" framing, which is context rather than instruction. It does not reach level 5 because not every token earns its place, but it is well above the 'mostly efficient with some unnecessary explanation' of level 3.

4 / 5

Actionability

Guidance is fully executable: two copy-paste-ready changeset file examples with exact YAML frontmatter syntax, the concrete command "npx changeset", filename conventions (lowercase kebab-case in .changeset/), and the exact "skip changeset" label that bypasses CI. The common cases (create a changeset, choose a bump, skip when unneeded) are all covered with ready-to-use material.

5 / 5

Workflow Clarity

Sequences are clear: two creation options, an ordered bump-type decision reference, explicit skip rules, and a numbered release pipeline. Validation exists only implicitly via the external changeset-bot comment, with no explicit step telling the author how to confirm their changeset is valid. This matches 'clear sequence with most checkpoints present; minor validation gaps' rather than the explicit validate-and-recover loop of level 5.

4 / 5

Progressive Disclosure

Sections are well organized and references are clearly signaled and one level deep — "For the full decision table with detailed examples, see contributor-docs/versioning.md" — plus a "Common files" index. However, the inline semver bullet lists and the multi-step release pipeline narrative are detail that could largely live in the referenced contributor docs, so content placement is good rather than optimally split.

4 / 5

Total

17

/

20

Passed

Description

92%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.

A strong description with an explicit and concrete "Use when" trigger clause paired with a clear statement of what the skill covers. All named actions are specific and domain-appropriate; the only gap is a few missing natural synonyms (e.g., changelog) in the trigger vocabulary.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "adding changesets to pull requests, determining semver bump types, versioning packages, or preparing releases" — and the second sentence enumerates the skill's full scope (file format, semver guidance, when required, release pipeline), matching the comprehensive-coverage anchor. It does not fit the level-4 anchor because there are no minor gaps in coverage.

5 / 5

Completeness

It explicitly answers "when" with an explicit "Use when:" clause containing four concrete triggers, and answers "what" with "Covers changeset file format, semver guidance, when changesets are required, and the release pipeline". Both halves are explicit and concrete, matching the top anchor; level 4 would require the "when" to be less specific, which it is not.

5 / 5

Trigger Term Quality

Natural phrases users would say are well covered ("changesets", "pull requests", "semver bump", "versioning packages", "preparing releases"), but a few natural synonyms such as "changelog" and "version bump" are missing. This is good-but-not-comprehensive keyword coverage rather than the comprehensive synonym/extension coverage of the top anchor.

4 / 5

Distinctiveness Conflict Risk

The changeset/semver/release-preparation niche is distinct and the triggers (changesets, semver bumps, versioning, releases) are unlikely to fire for an unrelated skill. Clear niche with distinct triggers and minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

primer/react

Path

.agents/skills/changesets/SKILL.md

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.