CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-change-analysis

手动触发的 FastGPT PR 或本地分支变更梳理技能。仅当用户显式调用 $pr-change-analysis 时使用;用于 reviewer 分析一个 GitHub PR 或当前本地分支相对 upstream/main 的需求变更、影响范围、代码质量与代码风格,不用于自动审查触发。

72

Quality

88%

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

92%Weight 40%Scale 1-3

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

The content is lean, highly actionable, and clearly sequenced with verification checkpoints; its only weakness is that everything lives inline in a single file with no reference split, leaving progressive_disclosure below the top anchor.

Suggestions

Extract the detailed 审查维度 criteria or the i18n key rules into a reference file (e.g. references/review-dimensions.md) and link to it from SKILL.md to enable one-level-deep progressive disclosure.

Consider moving the full output-format template into a references/ template file, keeping SKILL.md as a concise overview pointing to it.

DimensionReasoningScore

Conciseness

The body delivers only task-relevant review judgment criteria and concrete commands without explaining concepts Claude already knows (no 'what is a PR/diff' filler); each section earns its place with domain-specific guidance like the i18n key rules.

3 / 3

Actionability

Provides copy-ready commands with exact fields ('gh pr view <pr> ... files,additions,deletions,commits'), concrete judgment categories (合理扩散/可疑越界/高风险越界), and specific forbidden i18n patterns, matching the 'fully executable... copy-paste ready' anchor.

3 / 3

Workflow Clarity

Sequenced flow (入口判断 → 信息收集 → 审查维度 → 深挖方法 → 输出格式) with explicit verification checkpoints — 'git status --short' guard before switching PRs, 'git show upstream/main:<path>...确认不是误读', and a required '验证盲区' statement even when no issues are found.

3 / 3

Progressive Disclosure

No bundle files exist and all ~150 lines are inline in one well-sectioned file; detail such as the four 审查维度 and the i18n key rules could be split into reference files, matching 'some structure... content that should be separate is inline'.

2 / 3

Total

11

/

12

Passed

Description

85%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and clearly distinctive, but its trigger framing centers on the literal slash-command token rather than natural user phrasing, leaving trigger_term_quality slightly below the top anchor.

Suggestions

Add natural-language trigger phrases users would actually say (e.g., 'review this PR', '梳理这个分支的改动') alongside the $pr-change-analysis invocation token.

Consider including common variations like 'code review', 'PR review', 'branch diff' to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete analysis actions — '需求变更、影响范围、代码质量与代码风格' — and names the domain (FastGPT PR/local branch), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly states both what ('分析...需求变更、影响范围、代码质量与代码风格') and when ('仅当用户显式调用 $pr-change-analysis 时使用;不用于自动审查触发'), matching the 'clearly answers both what AND when' anchor.

3 / 3

Trigger Term Quality

Relevant keywords (PR, 分支变更, 梳理) appear, but the trigger is framed around the explicit invocation token '$pr-change-analysis' ('仅当用户显式调用') rather than the natural phrases a user would say, missing common variations — matching 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

Narrow FastGPT PR/local-branch reviewer niche with explicit '不用于自动审查触发' disambiguation gives a clear distinct trigger unlikely to conflict, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

11

/

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
labring/FastGPT
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.