CtrlK
BlogDocsLog inGet started
Tessl Logo

pipeline-plugin-development

开发 BK-CI 流水线插件时使用,例如新增 Atom、编写 `task.json`、定义输入输出、处理多语言运行时、调试和发布插件。当用户要做插件本体而不是执行器或流水线模型时优先使用。

62

Quality

78%

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-plugin-development/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 a well-organized, concise router-style overview with clear scope boundaries and good signaling toward per-topic reference files, but it offers little directly executable guidance and its progressive disclosure breaks down because the referenced files do not exist in the bundle. Its structure and scoping are strengths; actionability and verifiable references are the weaknesses.

Suggestions

Add a minimal concrete example to the body — e.g., a short task.json snippet showing input field definition, sensitive-field marking, and an error code — so the 'task.json 是插件契约' guidance is actionable without the reference files.

Include an explicit validation checkpoint in the workflow, such as 'test/debug the plugin locally before publishing, and confirm backward compatibility of existing inputs/outputs before releasing'.

Fix the reference paths so they resolve in the actual bundle: create the reference files under the bundle's references directory (or correct the 'reference/' prefix) and verify each cited path (1-plugin-foundation.md, 2-task-json-io.md, 3-debug-publish-practice.md) exists.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — terse bullets like '插件开发的核心对象是 task.json 和插件执行入口' with no padding or explanation of concepts Claude already knows — but the three reference paths are listed twice (in 快速指导 and again in 延伸阅读) and 快速指导 item 1 restates the 不适用场景 section, so it is efficient with minor instances that could be trimmed, matching anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

It gives concrete routing ('task.json、输入输出与错误码:reference/2-task-json-io.md') and actionable principles ('字段设计、运行时配置、敏感信息标记都应先在这里定清楚'), but contains no code, commands, field-level examples, or specific steps a developer could execute directly — 'some concrete guidance but incomplete; missing key details' — and as an instruction-only skill its guidance is directional rather than the mostly-executable level of anchor 4.

3 / 5

Workflow Clarity

快速指导 provides a numbered orientation sequence (confirm you are developing an Atom, route to the three reference files, define the contract first), but it is guidance for choosing what to read rather than an operational workflow; there are no validation checkpoints (e.g., test/debug before publish) — 'sequence present but checkpoints missing or implicit' — and it is not a destructive or batch skill so no cap applies, but it does not reach the clear-sequence-with-checkpoints level of anchor 4.

3 / 5

Progressive Disclosure

References are clearly signaled, one level deep, and topic-labeled ('插件基础与目录:reference/1-plugin-foundation.md'), but scored against the actual bundle structure none of the referenced files exist — no references/, scripts/, or assets/ directories are present, and the body uses a 'reference/' path that resolves to nothing — so the otherwise good navigation dead-ends, placing it at anchor 3 rather than the appropriately-placed-content level of anchor 4.

3 / 5

Total

13

/

20

Passed

Description

87%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 specific, concrete, and explicitly states both what the skill does and when to use it, including exclusion guidance that sharply distinguishes it from executor- and pipeline-model-related skills. Keyword coverage is good though not exhaustive of common synonyms. It is a strong, well-structured description.

DimensionReasoningScore

Specificity

Lists several concrete actions — '新增 Atom、编写 `task.json`、定义输入输出、调试和发布插件' — covering the plugin lifecycle, but coverage has minor gaps (error codes, sensitive-field marking, versioning are not named) and '处理多语言运行时' is comparatively generic, matching the anchor 'several specific actions; minor gaps' rather than the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both 'what' (新增 Atom、编写 task.json、定义输入输出、处理多语言运行时、调试和发布) and 'when' with concrete trigger phrases — '开发 BK-CI 流水线插件时使用…当用户要做插件本体而不是执行器或流水线模型时优先使用' — matching the anchor for clearly and explicitly answering both what AND when.

5 / 5

Trigger Term Quality

Contains natural terms users would actually say in this domain — '流水线插件', 'task.json', 'Atom', '调试和发布插件' — which is good keyword coverage, but misses common variations and synonyms (e.g., 插件市场/上架/打包, .json file extension), so it sits at anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (BK-CI pipeline plugin development) and actively disambiguates against adjacent skills — '当用户要做插件本体而不是执行器或流水线模型时优先使用' — giving it distinct triggers with minimal conflict risk, matching anchor 5.

5 / 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.

Validation — 16 / 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.