CtrlK
BlogDocsLog inGet started
Tessl Logo

pipeline-template-module

处理 BK-CI 流水线模板的创建、版本管理、实例化、权限控制、PAC 模板和商店集成时使用。当用户提到模板复用、模板版本、批量实例化、模板迁移、商店模板或 PAC 模板时优先使用。

64

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./ai/skills/pipeline-template-module/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 admirably concise and well-structured as a conceptual routing guide, but it lacks executable detail and, critically, references four reference files that do not exist in the bundle, breaking progressive disclosure for a skill that governs batch and version operations needing validation checkpoints.

Suggestions

Add the four referenced reference/*.md files to the bundle (or correct the paths) so the signaled progressive-disclosure navigation resolves to real content.

Include concrete, executable guidance — e.g. actual API/endpoint names, CLI commands, or minimal code snippets for instantiation and version operations — to raise actionability beyond routing hints.

Add explicit validation checkpoints for batch instantiation, batch update, and version-switch workflows (e.g. 'verify instance impact before applying', 're-validate after template change') to satisfy the batch/destructive feedback-loop requirement.

DimensionReasoningScore

Conciseness

Lean and efficient: the body assumes Claude's competence, uses short bulletted heuristics and rules with no padding or explanation of basic concepts, so every token earns its place per the score-5 anchor.

5 / 5

Actionability

Provides high-level routing guidance and conceptual decision rules (分清 V1/V2, 检查实例影响面) but no executable code, commands, API names, or concrete step-by-step procedures, matching the score-3 anchor of guidance that is concrete in intent but incomplete in execution detail.

3 / 5

Workflow Clarity

The '快速指导' section gives a numbered sequence for routing and change-checking, but the skill explicitly governs batch operations (批量实例化/批量更新) and template version changes with no validation/verification checkpoints, which caps this dimension at 3 per the destructive/batch feedback-loop rule.

3 / 5

Progressive Disclosure

The body references four reference files (reference/1..4.md) as one-level-deep navigation, but no references/ or reference/ bundle directory exists in the skill, so the signaled references point to non-existent files and the actual detail content is missing, fitting the score-2 anchor of references that are buried/broken rather than a clean overview-to-detail split.

2 / 5

Total

13

/

20

Passed

Description

88%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 description that clearly states the skill's purpose and provides rich natural trigger phrases covering the main use cases. Minor room for improvement in making individual actions more concrete and sharpening distinctiveness from sibling pipeline skills.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions (创建、版本管理、实例化、权限控制、PAC 模板、商店集成); coverage is broad but the actions are stated at a category level rather than fully concrete operations, leaving minor gaps versus the score-5 anchor.

4 / 5

Completeness

Explicitly answers both 'what' (处理...创建、版本管理、实例化、权限控制、PAC 模板和商店集成) and 'when' (当用户提到...时优先使用) with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Provides comprehensive natural trigger phrases users would say ('模板复用、模板版本、批量实例化、模板迁移、商店模板或 PAC 模板'), covering synonyms and common variations matching the score-5 anchor.

5 / 5

Distinctiveness Conflict Risk

Targets a clear BK-CI pipeline-template niche with distinct triggers, but terms like '模板' and '版本' could marginally overlap with adjacent skills (e.g. pipeline-model-architecture), so it sits just below the minimal-conflict score-5 anchor.

4 / 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.

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.