CtrlK
BlogDocsLog inGet started
Tessl Logo

gen-changesets

Use when generating changesets in the kimi-code repository, including package bump selection, internal package and CLI bundle handling, bump levels, major confirmation, and English changelog wording.

75

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

85%

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

A highly actionable, well-structured changeset guide with strong workflow checkpoints and concrete examples. Its main weakness is redundancy: the web-app and pi-tui rules are each stated in three places, which could be consolidated to improve token efficiency.

Suggestions

Consolidate the web-app rules: state them once in '## Web app changes' and have Core Rule 4 / Red Flags link back to it instead of restating the bundle-and-prefix guidance.

Similarly, describe the pi-tui exception once in its dedicated section and reduce the intro/Core Rule 4 mentions to a single cross-reference.

Prune overlapping Red Flags entries that merely restate Core Rules (e.g. the ignored/non-ignored mixing and missing-CLI-entrypoints flags) to cut repetition.

DimensionReasoningScore

Conciseness

Most content is repo-specific knowledge Claude lacks (changesets config, ignored packages, CLI bundling), but web-app handling is repeated across Core Rule 4, the '## Web app changes' section, and Red Flags, and pi-tui's exception is restated in the intro, Core Rule 4, and its own section — redundancy that could be tightened.

2 / 3

Actionability

Copy-paste-ready changeset frontmatter templates, a concrete bump-level table, specific wording exemplars for slash commands/flags/subcommands, and a Red Flags checklist give fully executable guidance.

3 / 3

Workflow Clarity

Numbered Workflow and Core Rules are clearly sequenced, with explicit feedback loops: the Major Rule's stop-explain-ask-fallback path and the 'When You Are Unsure' ask-before-digging loop act as validation checkpoints.

3 / 3

Progressive Disclosure

A single-file skill with no need for external references, organized into well-signaled sections (Core Rules, Workflow, Bump Levels, Wording Rules, examples, Red Flags); per the simple-skill note this qualifies.

3 / 3

Total

11

/

12

Passed

Description

100%

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-triggered description that answers both what and when while staying tightly scoped to its repository niche. It is a strong example of the form.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'package bump selection, internal package and CLI bundle handling, bump levels, major confirmation, and English changelog wording' — rather than vague claims.

3 / 3

Completeness

An explicit 'Use when generating changesets...' trigger answers 'when', and the clause after it clearly answers 'what'.

3 / 3

Trigger Term Quality

'generating changesets', 'changelog', and 'package bump' are natural terms a user would say; the remaining technical phrases stay relevant to the domain.

3 / 3

Distinctiveness Conflict Risk

Scoped to 'the kimi-code repository' changesets, giving it a clear niche unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

12

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.