CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tapd-iteration-runner

TAPD 迭代调度器——批量开发一个迭代中的全部需求。自动完成环境初始化、 需求依赖分析、逐需求调度 pipeline 实现、迭代汇总报告四段编排。 Use this skill whenever the user mentions 迭代执行, 开发迭代, 批量需求实现, TDD 迭代, dry run, batch requirement implementation, TAPD iteration development, speckit-based iteration, 迭代开发, or any workflow involving batch TAPD story processing with iteration-level coordination — even if the user only says "帮我开发这个迭代" or "跑一下迭代".

Quality

87%

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

78%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.

A well-structured orchestration skill body with clear sequencing, explicit feedback loops, strong progressive disclosure, and concrete operational details. The main weaknesses are mild redundancy of a few governing principles and reliance on justified pseudocode plus delegated report-stage validation rather than inline executable steps.

Suggestions

Consolidate the 'runner does not modify meta.yaml' principle to a single authoritative statement to remove the §5/§7/§8.2 repetition.

Show an inline validation/verification step for the report stage (e.g. verify changelog/summary before git push) rather than fully delegating it to report-scripts.md.

Tighten the '派生缓存' explanation, which is restated across §5 and §9, into one definition.

DimensionReasoningScore

Conciseness

The body is operationally lean with no padding of concepts Claude already knows, but repeats a few principles ("runner 不修改 meta.yaml" appears in §5, §7, §8.2; "派生缓存" explained twice) that could be tightened.

4 / 5

Actionability

Concrete, specific guidance throughout (exact field names, file paths, MCP calls like stories_get/iterations_get, an ACTION enum, decision branches); the core loop is explicitly-justified pseudocode rather than copy-paste code, which fits an instruction-only coordination skill but stops short of fully executable examples.

4 / 5

Workflow Clarity

A clearly sequenced four-stage process with a state-flow diagram, a sub-skill ordering table, explicit phase-based validation, and rich feedback loops (retry/approve/reject/answer/abort) plus a recovery mechanism and worked example; the report/push stage's validation is delegated to a reference rather than shown inline, a minor gap.

4 / 5

Progressive Disclosure

Clear overview with a §12 reference table mapping each file to purpose and load timing; all five local references exist as real files and are one level deep, well-signaled, and appropriately split out of the main body.

5 / 5

Total

17

/

20

Passed

Description

95%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, third-person description that clearly states the skill's four-stage orchestration purpose and provides comprehensive, natural trigger terms in both Chinese and English including colloquial phrasings. The only minor weakness is that one of the four named actions is moderately abstract.

DimensionReasoningScore

Specificity

Names four concrete orchestration actions ("环境初始化、需求依赖分析、逐需求调度 pipeline 实现、迭代汇总报告"), covering the full lifecycle comprehensively, though "逐需求调度 pipeline 实现" is moderately abstract, leaving a minor gap versus a fully concrete action list.

4 / 5

Completeness

Explicitly answers both what ("批量开发一个迭代中的全部需求…四段编排") and when ("Use this skill whenever the user mentions…even if the user only says…") with concrete trigger phrases and example utterances.

5 / 5

Trigger Term Quality

Comprehensive bilingual trigger coverage with synonyms and natural variations ("迭代执行, 开发迭代, 批量需求实现, TDD 迭代, dry run, batch requirement implementation, TAPD iteration development, speckit-based iteration, 迭代开发") plus colloquial phrases users would actually say ("帮我开发这个迭代", "跑一下迭代").

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (TAPD iteration-level batch orchestration) with highly specific triggers (TAPD, speckit, iteration coordination) that are unlikely to fire for unrelated skills, minimizing conflict risk.

5 / 5

Total

19

/

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.

Validation — 13 / 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

Path

.agents/skills/tapd-iteration-runner/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.