CtrlK
BlogDocsLog inGet started
Tessl Logo

gen-changesets

Use when generating changesets in the kimi-code repository — deciding whether to write one, which package to list, the bump level, the wording, and the confirmation workflow.

67

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/gen-changesets/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 dense, well-structured instruction skill that assumes Claude's competence and gives concrete templates, commands, and a sequenced workflow with a confirmation checkpoint. Scores are held at 4 rather than 5 by minor gaps: a slightly justifiable padded clause, no explicit filename example, and the absence of a full validate-fix-retry loop.

Suggestions

Show one concrete changeset filename example (e.g. `.changeset/fix-tool-call-results.md`) so the "short kebab-case file" instruction is unambiguous.

Tighten the rule-of-thumb sentence in section 1 by dropping the explanatory trailing clause, since the bolded rule already carries the point.

Consider an explicit validate step in the workflow (e.g. re-read the one sentence against section 2's wording rules before showing it) to push workflow clarity toward the top anchor.

DimensionReasoningScore

Conciseness

Lean and decision-oriented throughout, assuming Claude knows what changesets, packages, and PRs are; the only mild padding is the justification in the rule-of-thumb sentence, which still earns its place but could be trimmed.

4 / 5

Actionability

Provides a copy-paste changeset template, concrete git commands ("git status" / "git diff --name-only"), and specific per-case rules; minor gaps such as no explicit file-naming example beyond "short kebab-case file" keep it just below fully executable.

4 / 5

Workflow Clarity

Section 5 gives a clear numbered sequence with an explicit confirmation checkpoint (step 4) and an ask-when-unclear feedback step (step 5), plus the pre-release review/delete step; this is a clear sequence with most checkpoints present rather than the full validate-fix-retry loop of the top anchor.

4 / 5

Progressive Disclosure

Well-organized into five labeled sections with no external references needed for this single-purpose skill; it sits just outside the under-50-line simple-skill exception and is self-contained, so good structure with minor organization gaps rather than a perfect 5.

4 / 5

Total

16

/

20

Passed

Description

85%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, third-person description that clearly states both what it does and when to use it, with concrete enumerated actions and a distinct, repo-scoped trigger. Its only weakness is thin keyword coverage — a single trigger term with no synonyms.

Suggestions

Add natural synonyms so users phrasing it differently still hit the trigger, e.g. "Use when generating changesets, writing changelog entries, or deciding release notes in the kimi-code repository".

Optionally surface the bump-level vocabulary (patch/minor) in the description so users mentioning version bumps route here.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "deciding whether to write one, which package to list, the bump level, the wording, and the confirmation workflow" — giving comprehensive coverage of the skill's decisions.

5 / 5

Completeness

Explicitly answers both — the "what" (the five decisions enumerated) and a concrete "when" ("Use when generating changesets in the kimi-code repository"), matching the anchor for clear what-and-when with concrete triggers.

5 / 5

Trigger Term Quality

The single natural trigger phrase "generating changesets" is relevant, but no synonyms or common variations (e.g. changelog entries, release notes) are offered, matching the anchor with some relevant keywords but missing variations.

3 / 5

Distinctiveness Conflict Risk

The trigger "generating changesets in the kimi-code repository" carves a clear niche tied to a specific repo and task, with minimal risk of firing for unrelated skills.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
MoonshotAI/kimi-code
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.