CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tapd-iteration-analysis

迭代执行流水线需求分析阶段。通过 TAPD MCP stories_get 拉取迭代中所有需求详情, 将 description 字段(完整 Markdown 内容)直接保存为需求文档,基于 parent_id 字段自动识别父子关系和独立需求,从需求文档的"依赖关系"章节提取显式依赖进行 拓扑排序,确定实现顺序,更新迭代状态。

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/tapd-iteration-runner/tapd-iteration-analysis/SKILL.md
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 content is a well-structured, actionable multi-step workflow with concrete commands and validation checkpoints for a batch requirement-analysis operation. Its weaknesses are a dangling reference to a non-existent dependency-types file and some duplicated tree-diagram content that could be trimmed.

Suggestions

Either supply the referenced ../../references/dependency-types.md file or inline the dependency-type judgment conditions directly in the body, since the current reference resolves to a missing file.

Remove the duplicated requirement hierarchy tree — keep it only in the final output block (section 5) or only in the structural illustration (section 2.4), not both verbatim.

Add an explicit validation step after saving .tmp/{ID}.md files (e.g. confirm each description was written non-empty) before proceeding to dependency extraction and DAG construction.

DimensionReasoningScore

Conciseness

The body is largely procedural and domain-specific rather than explaining concepts Claude already knows, but repeats the requirement hierarchy tree verbatim (the spec block at lines 82-91 and the output block at 167-186) and restates the 'description is already Markdown, no conversion needed' point, which are trimmable.

4 / 5

Actionability

Provides concrete, executable guidance — cross-platform mkdir commands, the exact stories_get call with workspace_id/iteration_id/limit=200, the {ID}.md naming rule, and a classification table — but offloads the core dependency-type judgment conditions to ../../references/dependency-types.md, leaving a gap in the executable path.

4 / 5

Workflow Clarity

A clearly sequenced five-step process with real validation checkpoints — '检测是否存在环依赖,如有则提示用户确认并协助解除' (cycle feedback loop) and '验证依赖有效性' (dependency validation) — though there is no validation that the saved .tmp/*.md files are complete/well-formed before building the DAG.

4 / 5

Progressive Disclosure

Sections are reasonably organized and one reference is explicitly signaled ('具体的依赖类型判定条件见 ../../references/dependency-types.md'), but that referenced file does not exist (no references/ directory is present), so the navigation path leads to a missing file and the dependency-type detail is neither inline nor reachable.

3 / 5

Total

15

/

20

Passed

Description

67%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 and distinctive, clearly conveying what the skill does through concrete actions anchored to TAPD-specific artifacts. Its main weaknesses are the absence of an explicit 'Use when...' trigger clause and reliance on technical jargon over natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g. 'Use when analyzing iteration requirement dependencies, ordering stories for implementation, or when the user asks to plan an iteration's implementation sequence').

Soften the jargon by adding natural trigger synonyms users would actually say, such as '需求依赖排序' or '迭代实现顺序' alongside the technical TAPD MCP terms.

Lead with the user-facing intent (analyzing and ordering iteration requirements) before the mechanical MCP/API details, so the trigger reads naturally.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '通过 TAPD MCP stories_get 拉取迭代中所有需求详情', '将 description 字段...直接保存为需求文档', '基于 parent_id 字段自动识别父子关系', '提取显式依赖进行拓扑排序', '更新迭代状态' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

The 'what' is clearly and concretely stated, but there is no 'Use when...' clause or equivalent explicit 'when' guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant domain keywords exist ('迭代', '需求分析', '依赖关系', '拓扑排序') but the description leans on technical jargon (TAPD MCP, stories_get, parent_id) and lacks natural user-facing trigger phrases or synonyms a person would spontaneously say.

3 / 5

Distinctiveness Conflict Risk

The description carves a clear niche tied to TAPD iteration requirement analysis (stories_get, parent_id, 依赖关系章节, 拓扑排序) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

16

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

TencentBlueKing/bk-bcs

Path

.agents/skills/tapd-iteration-runner/tapd-iteration-analysis/SKILL.md

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.