CtrlK
BlogDocsLog inGet started
Tessl Logo

tapd-iteration-plan

TAPD 迭代规划技能。基于"approved"状态的需求池,结合需求依赖关系、size 规模、 优先级进行全局编排,将合适规模的需求规划进入指定迭代。支持新建迭代和已有迭代 重入两种模式,自动控制迭代总规模上限(默认 1000),通过有向无环图(DAG)分析 保证依赖需求优先入迭代。 Use this skill whenever the user mentions 迭代规划, 规划迭代, 编排迭代, iteration planning, 迭代编排, 需求入迭代, 排迭代, 拉迭代, 创建迭代, plan iteration, sprint planning, organize sprint, or any workflow involving TAPD iteration scheduling and story assignment.

72

Quality

90%

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

81%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 dense, highly actionable runbook with concrete MCP calls, validation checkpoints, and feedback loops for a batch operation. Its main weaknesses are moderate redundancy (repeated filter conditions and examples that restate the flow) and minor inline/reference duplication in progressive disclosure.

Suggestions

De-duplicate the candidate filter rules: state the children_id=='|' and iteration_id=='' conditions once in §3 and reference them from §4.2 instead of restating them.

Replace the two full worked examples (which restate 执行流程) with brief input→outcome vignettes that highlight only the branch-specific behavior (new vs. reentry, auto vs. user-specified).

Move the detailed naming rules and DAG ordering rules fully into references/iteration-naming.md and references/dependency-analysis.md, keeping only a one-line summary inline to remove the inline/reference overlap.

DimensionReasoningScore

Conciseness

Mostly efficient procedural prose with no padding of concepts Claude already knows, but it repeats the candidate filter conditions (children_id=='|' / iteration_id=='') across §3.1, §3.2 and §4.2, and the two worked examples restate the entire 执行流程, which could be tightened.

3 / 5

Actionability

Fully executable guidance: exact MCP tool calls (iterations_get/create, stories_get/update) with parameter blocks, precise field names (v_status, children_id, iteration_id), concrete thresholds (size_limit 1000, top 20, limit 200/100), and worked examples covering the common new-iteration and specified-stories cases.

5 / 5

Workflow Clarity

A clearly sequenced five-step process with explicit branch logic (A/B), validation checkpoints (name format, total_size<=0), retry-then-fallback feedback loops for batch operations, and a comprehensive error-handling table satisfying the batch-operation validation requirement.

5 / 5

Progressive Disclosure

Good structure with a 参考文件 table signaling one-level-deep references (dependency-analysis.md, iteration-naming.md) and when to read them, but naming rules and DAG ordering rules are duplicated both inline and in the reference files, a minor organization gap.

4 / 5

Total

17

/

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 a strong, well-modeled trigger statement: concrete capabilities, comprehensive bilingual trigger terms, explicit what-and-when guidance, and a distinct niche. It is written in third person with no over-claims or padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — orchestrating approved stories by dependency/size/priority, planning into an iteration, supporting new-build and reentry modes, capping total size (default 1000), and DAG-based dependency ordering — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (the orchestration/planning behavior and constraints) and 'when' (a 'Use this skill whenever...' clause with concrete trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage in both Chinese and English including synonyms and colloquial forms (迭代规划, 规划迭代, 排迭代, 拉迭代, iteration planning, sprint planning, plan iteration, organize sprint) that users would genuinely say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (TAPD iteration planning with MCP-bound triggers) so it is unlikely to fire for unrelated skills; minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
TencentBlueKing/bk-bcs
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.