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.

76

Quality

95%

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

100%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 with repo-specific rules, concrete examples for every common case, and a workflow with explicit confirmation and escalation checkpoints. It assumes Claude's competence throughout and contains no filler or content that should be split into reference files.

DimensionReasoningScore

Conciseness

Every line is a project-specific rule or example ("Never mix packages ignored in `.changeset/config.json` with non-ignored packages in one frontmatter", the pi-tui exception) that Claude could not know otherwise; there is no concept explanation or padding. This matches the lean, every-token-earns-its-place anchor, not anchor 4 which requires some over-explanation to trim.

5 / 5

Actionability

Guidance is fully executable: a copy-paste-ready changeset file example, concrete commands (`git status` / `git diff --name-only`), and quoted wording examples for the common cases (bug fix, default flip with escape hatch, new feature). Anchor 5's requirement that specific examples cover the common cases is met; anchor 4 would require gaps, and the only un-exampled case (experimental features) has an explicit instruction for the enable flag.

5 / 5

Workflow Clarity

The workflow is a clear 5-step sequence with an explicit validation checkpoint ("Show the changeset text to whoever requested the work and get their confirmation before committing") and an error-recovery loop ("finish the parts that are clear, then list what is unclear and ask"). The destructive pre-release deletion step is preceded by a review of accumulated entries, satisfying the feedback-loop requirement; this matches anchor 5 rather than 4.

5 / 5

Progressive Disclosure

This is a single-purpose policy skill with no bundle files and no content that belongs in a separate reference — all rules are appropriately inline and organized under five clearly headed sections (Whether to Write, What to Write, Bump Level, Which Package, Workflow). Per the simple-skill guidance, well-organized sections with no need for external references warrant the top score.

5 / 5

Total

20

/

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, repo-scoped description with an explicit 'Use when' trigger and a concrete enumeration of the decisions the skill governs. The only weaknesses are minor: a few missing natural synonyms (version bump, changelog, release notes) and no mention of the pre-release changeset cleanup covered in the body.

DimensionReasoningScore

Specificity

The description enumerates concrete decision points ("deciding whether to write one, which package to list, the bump level, the wording, and the confirmation workflow"), matching the anchor for several specific actions with minor gaps. It is not 5 because the body also covers pre-release cleanup of accumulated changesets, which the description omits.

4 / 5

Completeness

It explicitly answers when ("Use when generating changesets in the kimi-code repository") and what (the enumerated decisions: whether to write, package, bump level, wording, confirmation workflow). Both are concrete and explicit, matching anchor 5; anchor 4's weaker 'when' does not apply since the trigger is fully specified and repo-scoped.

5 / 5

Trigger Term Quality

"generating changesets" and "bump level" are natural phrases a user would say, giving good keyword coverage, but common synonyms like "version bump", "changelog", or "release notes" are missing, so it falls just short of the comprehensive anchor 5 and clearly above anchor 3.

4 / 5

Distinctiveness Conflict Risk

"changesets in the kimi-code repository" carves out a clear niche with distinct triggers and minimal conflict risk with other skills. It is well above anchor 4, which presumes overlap with closely related 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.

Validation — 16 / 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.