CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tapd-iteration-report

迭代执行流水线的收尾阶段。当迭代内所有需求 phase 均为 committed 后触发, 扫描 commit.md 生成 changelog,汇总研发效能数据写入 summary.md, 清理临时文件,递增 patch 版本号,最终提交并推送至远程仓库。

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 dense, well-structured operational spec: concrete commands, exact paths, precondition validation, and per-failure exception handling. The main gaps are a missing post-generation verification checkpoint before the irreversible push, and the changelog/aggregation logic living entirely in an unverifiable external reference.

Suggestions

Add a validation step between generation and `git push` — e.g. re-read changelog.md/summary.md and confirm the `${VERSION_TAG}` section and totals rows exist and are non-empty before committing.

Inline a minimal fallback (or a jq one-liner skeleton) for changelog/summary generation in case `../../references/report-scripts.md` is unavailable, and verify that path exists in the published bundle.

De-duplicate the duration_sec/cost semantics (stated in both the data-source table and the 关键语义 blockquote) and consider moving the full three-layer summary.md template into the reference file to trim the main body.

DimensionReasoningScore

Conciseness

The body is table-driven and assumes competence (no explanations of git/jq/JSON concepts), but semantic notes on duration_sec/cost are repeated in both the data-source table and the "关键语义" blockquote, and the three-layer placeholder table template is verbose. Fits the 4 anchor (efficient, minor instances that could be trimmed) rather than the 5 anchor where every token earns its place.

4 / 5

Actionability

Steps 1, 4, 5, 6 give copy-paste-ready bash/PowerShell with exact jq commands and file paths, and the output format is fully specified; however steps 2 and 3 (changelog generation, stats aggregation) delegate to an external reference ("详细脚本实现见 `../../references/report-scripts.md` §1/§2") with no inline fallback. This is 'mostly executable guidance with minor gaps' — the 4 anchor — not the 5 anchor's fully executable coverage.

4 / 5

Workflow Clarity

A clear 6-step sequence with an explicit precondition checklist (all phases committed, commit.md present, status completed) and an exception-handling table with recovery actions, satisfying the validation requirement for this batch/push operation. It falls short of the 5 anchor because there is no checkpoint validating the generated changelog/summary content before the hard-to-reverse `git push`, and no feedback loop for push failure beyond telling the user to check permissions.

4 / 5

Progressive Disclosure

The overview-to-detail split is good: implementation detail for the two heaviest steps is clearly signaled and one level deep ("见 `../../references/report-scripts.md` §1/§2"). However no references/ directory is present in this bundle to verify that path resolves, and the large inline summary.md format template is content that could partly live in the reference. Fits the 4 anchor ('good structure, references mostly clear, minor organization gaps') better than the 5 anchor.

4 / 5

Total

16

/

20

Passed

Description

81%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, dense description that states concrete close-out actions and an explicit trigger condition in third-person voice. Its only weakness is trigger phrasing oriented to a pipeline state rather than natural user language, with no synonyms or variations.

Suggestions

Add a user-facing trigger phrasing alongside the state condition, e.g. "Use when finishing an iteration / generating the iteration summary report after all stories are committed", so the skill is discoverable by natural language as well as orchestration state.

Include common synonyms or file names (e.g. 迭代总结 / iteration report / changelog 汇总) to broaden natural trigger coverage.

Consider naming the artifacts' purpose in user terms (研发效能报告) rather than only file paths (summary.md) to reduce overlap with generic changelog skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "扫描 commit.md 生成 changelog,汇总研发效能数据写入 summary.md,清理临时文件,递增 patch 版本号,最终提交并推送至远程仓库" — covering the full pipeline close-out comprehensively. It matches the 5 anchor (multiple specific concrete actions, comprehensive coverage) and is clearly above the 4 anchor's 'minor gaps in coverage'.

5 / 5

Completeness

It explicitly answers both 'what' (scan commit.md, generate changelog, aggregate efficiency data, clean up, bump patch, commit and push) and 'when' ("当迭代内所有需求 phase 均为 committed 后触发") with a concrete trigger condition. This matches the 5 anchor; it is well above the 4 anchor where the 'when' is only implicit or loosely stated.

5 / 5

Trigger Term Quality

Relevant keywords exist (committed, commit.md, changelog, patch, summary.md) but the trigger is a pipeline state condition ("当迭代内所有需求 phase 均为 committed 后触发") rather than natural user phrasings, and no synonyms or variations are offered. It fits the 3 anchor ('some relevant keywords but missing common variations or synonyms') and not the 4 anchor, which expects broader natural-term coverage.

3 / 5

Distinctiveness Conflict Risk

The niche is clear ("迭代执行流水线的收尾阶段" — the final stage of an iteration execution pipeline) and the committed-phase trigger is distinct, but generic terms like changelog/commit/push create minor overlap risk with general git or changelog skills. Fits the 4 anchor ('mostly distinct; minor overlap risk') better than the 5 anchor's minimal conflict risk.

4 / 5

Total

17

/

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-report/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.