Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Tapd Iteration Report · tencentblueking | DecimalAI

devopsby tencentblueking

Tapd Iteration Report

tencentblueking/tapd-iteration-report

Source tencentblueking/bk-bcs ↗License NOASSERTION

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。

SkillScore77Maintained

Automatic

Project Management pack

Last verified 9/26/2026

What it changes

Passed 13 of 17 test cases with the skill, and 9 of 17 without it.

Without skill55%

With skill77%

Checks it passed that the model alone missed

Delete directory path specs/v2.0.x/.tmp/.
Format git commit title line as docs(迭代): v0.9.3 变更日志与效能报告.
Write header # Changelog as the first line of new changelog files.

and 4 more in the full report

7 fixed10 passed either way3 still failing2 broke

Pass-rate lift: +23 pp
Tokens: +139%
Agent turns: 0%
Response time: -40%

Model gemini-3.6-flashMeasured 9/26/2026v117 of 22 cases passed with skill · 17 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/tencentblueking-tapd-iteration-report/SKILL.md https://app.decimal.ai/s/tencentblueking-tapd-iteration-report/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add tencentblueking-tapd-iteration-report, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/tencentblueking-tapd-iteration-report/ and pins it in .decimal/skills.lock

decimalai skills add tencentblueking-tapd-iteration-report

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/tencentblueking-tapd-iteration-report/SKILL.md https://app.decimal.ai/s/tencentblueking-tapd-iteration-report/SKILL.md

Raw file: /s/tencentblueking-tapd-iteration-report/SKILL.md ↗ · machine-readable summary at /s/tencentblueking-tapd-iteration-report.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

Specify the exact path that should be cleaned up when purging temporary files for iteration `v2.0.x`.

What was checked, without and with the skill
Checked	Without skill	With skill
Delete directory path specs/v2.0.x/.tmp/.	Missed	Passed

case-19 · gemini-3.6-flash · 9/26/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md241 linessingle file

迭代信息汇总

定位

本子 skill 是迭代执行流水线的最后一环——在所有需求完成开发并提交后，对整个迭代进行总结性收尾：构建版本 changelog、汇总研发效能数据、清理临时文件、递增 patch 版本号，并将汇总结果提交推送至远程仓库。

前置条件

编排层在调用本子 skill 前需确认以下条件全部满足：

所有需求 phase 为 committed：iteration-state.json 中 sequence 列出的所有需求，其 phase 字段必须全部为 committed
所有需求目录存在 commit.md：specs/${VERSION}/${ID}/commit.md 文件必须全部存在
迭代 status 为 completed：iteration-state.json.status 为 completed

如果任一条件不满足，输出明确的错误信息并终止执行，由编排层决定后续处理。

状态文件

从 specs/${VERSION}/iteration-state.json 读取以下关键信息：

字段	用途
`patch`	当前 patch 版本号，用于构建版本标题（如 v0.9.3）
`iter_branch`	迭代分支名（如 v0.9.x），用于推送
`started_at`	迭代开始时间
`end_at`	迭代结束时间
`stories`	所有需求及其统计字段
`sequence`	需求执行顺序列表

版本号构成规则：

迭代目录名即为版本前缀（如 v0.9.x → v0.9.）
完整版本号 = 版本前缀去掉末尾的 x + patch 值（如 v0.9. + 3 → v0.9.3）

执行流程

1. 读取迭代状态

Track record

Benchmark

13 / 17

test cases passed, vs 9 / 17 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/25/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

tencentblueking / bk-bcs

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

View on GitHub ↗

License NOASSERTIONImported 8/25/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.