CtrlK
BlogDocsLog inGet started
Tessl Logo

pre-changelog

Use before merging a kimi-code release PR to preview the user-facing CLI changelog in Chinese. Reads the changelog that changesets pre-generated in the release PR, then reuses sync-changelog's strip / classify / translate logic to render a Chinese preview. Writes no files.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

A well-structured, lean skill body with executable commands, clear stop-condition checkpoints, and smart reuse of a sibling skill to avoid restating rules. It is read-only so the absence of file-writing validation steps is appropriate.

DimensionReasoningScore

Conciseness

The body is dense actionable instruction with no padding explaining what a changelog or changeset is, and it defers detailed rules to sync-changelog ('Read sync-changelog first') so every token earns its place.

3 / 3

Actionability

Provides executable `gh pr list` and `gh api ... --jq` commands, a concrete diff-extraction rule, explicit strip/classify/translate steps, and a copy-paste-ready output template with `<version>(预览)` and `无` placeholders.

3 / 3

Workflow Clarity

A clear 4-step sequence with explicit validation checkpoints ('If none is open ... stop', 'If the CLI changelog is not in the diff ... stop', 'If an upstream entry is not in English ... stop'), and the read-only nature means the destructive/batch cap does not apply.

3 / 3

Progressive Disclosure

Content is cleanly split into Workflow and Rules sections, and the only external reference (sync-changelog) is one level deep and clearly signaled; no bundle files exist to organize.

3 / 3

Total

12

/

12

Passed

Description

85%

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 focused, third-person description that clearly states what the skill does and when to use it, with concrete actions and a distinct niche. Trigger-term quality is slightly weakened by internal jargon rather than natural user phrasing.

Suggestions

Soften internal jargon in the description—e.g., phrase the trigger around what a user would say ('preview the Chinese changelog before merging a release PR') rather than 'changesets pre-generated' and 'sync-changelog's strip/classify/translate'.

DimensionReasoningScore

Specificity

Names multiple concrete actions—'preview the user-facing CLI changelog in Chinese', 'Reads the changelog that changesets pre-generated', 'reuses sync-changelog's strip / classify / translate logic', 'Writes no files'.

3 / 3

Completeness

Explicitly answers both what (preview the CLI changelog in Chinese by reusing sync-changelog logic) and when ('Use before merging a kimi-code release PR').

3 / 3

Trigger Term Quality

Contains real natural terms ('before merging a release PR', 'changelog', 'Chinese preview') but leans on internal jargon ('changesets pre-generated', 'sync-changelog's strip/classify/translate') and misses common variations.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (pre-merge release-PR CLI changelog preview in Chinese) and is differentiated from its sibling sync-changelog skill by data source and output, so it is unlikely to trigger for the wrong skill.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

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.