CtrlK
BlogDocsLog inGet started
Tessl Logo

repository-module-architecture

处理 BK-CI 代码库接入、代码库授权、Webhook、SCM 集成、PAC 开关与仓库类型差异时使用。当用户提到 Git/SVN/GitHub/TGit、Webhook、仓库认证、PAC 代码库或提交记录时优先使用。

70

Quality

85%

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

71%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.

The body is concise and well-structured with clear routing and a sensible triage workflow, but its actionability is undermined because the reference files it points to are absent from the bundle, breaking the progressive-disclosure promise.

Suggestions

Add the referenced files (reference/1-repository-foundation.md, reference/2-webhook-pac-auth.md) to a references/ directory so the navigation links resolve, or inline the essential content they would hold.

Add at least one concrete, executable artifact (e.g. a sample API call, a config snippet, or a diagnostic command) so the guidance is actionable rather than purely navigational.

Make the 快速指导 triage sequence explicit with numbered validation/checkpoint language (e.g. 'after reading the reference, confirm the repository type before changing auth logic') to strengthen the workflow.

DimensionReasoningScore

Conciseness

Lean bullet structure with no padding and no explanation of concepts Claude already knows; every line carries routing or rule information, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Routing guidance is specific ('看 reference/1-repository-foundation.md') but the actions are 'read this file' rather than executable steps, and the referenced files do not actually exist in the bundle, leaving gaps — between 'some concrete guidance but incomplete' and 'mostly executable'.

3 / 5

Workflow Clarity

The 快速指导 section gives a clear triage sequence (judge mainline → read matching reference → switch skill) with a routing checkpoint to yaml-pipeline-transfer; no destructive/batch operations so no validation cap applies, with only minor gaps.

4 / 5

Progressive Disclosure

Sections are well-organized and references are one level deep and clearly signaled, but the referenced files ('reference/1-...md', 'reference/2-...md') do not exist in the bundle, so the structure is promised but not delivered — between 'some structure' and 'good structure'.

3 / 5

Total

15

/

20

Passed

Description

100%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.

The description is excellent: it uses third person, lists concrete actions, provides comprehensive trigger terms, and explicitly covers both what the skill does and when to use it. It occupies a distinct niche with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '代码库接入、代码库授权、Webhook、SCM 集成、PAC 开关与仓库类型差异' — covering the module comprehensively, matching the 'multiple specific concrete actions' anchor.

5 / 5

Completeness

Explicitly answers both 'what' (处理接入/授权/Webhook/SCM/PAC/类型差异) and 'when' ('当用户提到...时优先使用'), matching the anchor for clearly answering both with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural terms including synonyms and platform names — 'Git/SVN/GitHub/TGit、Webhook、仓库认证、PAC 代码库或提交记录' — exactly what a user would say, matching the 'comprehensive coverage including synonyms' anchor.

5 / 5

Distinctiveness Conflict Risk

A clear BK-CI repository-module niche with distinct platform-specific triggers (TGit, PAC 代码库) and minimal overlap with other skills, matching the 'clear niche with distinct triggers' anchor.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
TencentBlueKing/bk-ci
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.