CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

93%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.

An exemplary instruction-only skill body: dense, executable rules with concrete examples and commands, a clear decision workflow with a confirmation gate, and clean single-file organization. The only notable gap is the absence of an explicit verify/re-validate step in the workflow sequence.

DimensionReasoningScore

Conciseness

The body is lean and imperative throughout — rules like "Never mix packages ignored in `.changeset/config.json` with non-ignored packages in one frontmatter" and "**never write it.**" carry operational weight with no padding. It never explains concepts Claude already knows (what a changeset is, how git works), so every token earns its place.

5 / 5

Actionability

Guidance is fully executable: a copy-paste-ready changeset file with exact frontmatter, concrete commands ("Run `git status` / `git diff --name-only`"), and worked example sentences for default flips, new features, and experimental flags. The common cases are covered concretely, matching the top anchor; it is not level 4 because there are no meaningful gaps in executable detail.

5 / 5

Workflow Clarity

Section 5 gives a clear numbered sequence with an explicit human-confirmation checkpoint ("Show the changeset text to whoever requested the work and get their confirmation before committing") and an uncertainty-escalation path ("Do not guess... list what is unclear and ask"). It falls short of level 5 because there is no verify-retry loop on the written artifact (e.g., re-checking the file's frontmatter against the changed packages) and the pre-release cleanup step sits outside the numbered workflow.

4 / 5

Progressive Disclosure

The skill is a self-contained ~60-line body organized into five clearly numbered sections (Whether, What, Bump Level, Which Package, Workflow) with no external bundle files and no content that belongs in a separate reference. Navigation is trivial and nothing is buried, so the top anchor fits better than level 4's 'minor organization gaps'.

5 / 5

Total

19

/

20

Passed

Description

87%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: it pairs an explicit 'Use when' trigger with a comprehensive, concrete enumeration of the decisions the skill governs, all in one lean sentence. The only weaknesses are a few missing natural synonyms (changelog, version bump) and no mention of the pre-release cleanup step.

DimensionReasoningScore

Specificity

The description enumerates five concrete decision areas — "deciding whether to write one, which package to list, the bump level, the wording, and the confirmation workflow" — which goes well beyond the 1-2 actions of the level-3 anchor. It is not level 5 because coverage has a minor gap: the pre-release changeset cleanup workflow is not mentioned.

4 / 5

Completeness

It explicitly answers both questions: "Use when generating changesets in the kimi-code repository" states when, and the enumerated decisions (whether, package, bump, wording, workflow) explicitly state what the skill governs. This matches the anchor requiring both what and when with concrete trigger phrases, and clearly exceeds level 4 where the 'when' is less explicit.

5 / 5

Trigger Term Quality

Terms like "generating changesets", "bump level", and "package" are ones a user in this repository would naturally say, matching the good-coverage anchor. It falls short of level 5 because common variations such as "changelog entry", "version bump", or "release notes" are absent.

4 / 5

Distinctiveness Conflict Risk

The description is scoped to a clear niche — changesets in the kimi-code repository — with distinct triggers, so overlap with other skills is minimal. It is not level 4 because there is no meaningful overlap risk with closely related skills; the repo and task scoping are unambiguous.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

MoonshotAI/kimi-code

Path

.agents/skills/gen-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.