Ready to supercharge your AI agents?

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

Tapd Story Validate · tencentblueking | DecimalAI

code reviewby tencentblueking

Tapd Story Validate

tencentblueking/tapd-story-validate

Source tencentblueking/bk-bcs ↗License NOASSERTION

迭代执行流水线校验阶段。对 implement 产出的代码做四维度并行校验（架构 / 安全 / CodeReview / 测试覆盖），再按汇总结果原地修复（fullstack 需求按受影响文件路径分派 backend-developer / frontend-developer）。每个维度通过独立 subagent 执行，日志写入独立 process-validate-*.log。命令与报告模板详见 ../references/subagent-prompt-template.md §2.6~§2.10。回退默认保留代码（携带 unresolved_findings 回上游修订规范）。

SkillScore73Maintained

Automatic

QA & Test Engineering pack

Last verified 9/26/2026

What it changes

Passed 12 of 16 test cases with the skill, and 6 of 16 without it.

Without skill36%

With skill73%

Checks it passed that the model alone missed

Prohibits git reset commands.
Updates story phase to validated.
Sets code_preserved flag to true.

and 13 more in the full report

9 fixed7 passed either way5 still failing1 broke

Pass-rate lift: +36 pp
Tokens: +131%
Agent turns: 0%
Response time: -43%

Model gemini-3.6-flashMeasured 9/26/2026v116 of 22 cases passed with skill · 16 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-story-validate/SKILL.md https://app.decimal.ai/s/tencentblueking-tapd-story-validate/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add tencentblueking-tapd-story-validate, 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-story-validate/ and pins it in .decimal/skills.lock

decimalai skills add tencentblueking-tapd-story-validate

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

For story #5013 validation, which agent role is responsible for verifying standard architecture compliance in validate-arch-report.md?

What was checked, without and with the skill
Checked	Without skill	With skill
Assigns tech-lead agent to run architecture validation.	Missed	Passed

case-12 · 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.md168 linessingle file

需求实现校验

前置条件

当前需求 phase 为 implemented
代码实现已完成（迭代分支上），本子 skill 不创建分支、不切分支
pipeline 主编排已按 references/context-and-meta-template.md 重写当前阶段的 context.md （白名单含：spec.md / plan.md / tasks.md + 项目宪章 + 架构/安全/编码规范文档 + 项目根 AGENTS.md（项目定位与关键规范索引）+ Code scope + 可复用 skill 入口 skills/bk-security-redlines/； CodeReview 维度由 code-reviewer agent 经 use_skill("code-review") 加载统一后的 CR 方法论驱动）
本子 skill 不维护代码回滚锚点：回退默认保留代码

输入

${WORKDIR}/meta.yaml（读取 attempts）
当前需求 ID（由 pipeline 主编排传入）
${WORKDIR}/spec.md / plan.md / tasks.md
${WORKDIR}/context.md
${WORKDIR}/iteration-patches/attempt-${N}.md（若为回退重入，必读）

执行流程

本阶段由四段并行校验 subagent + 一段原地修复 subagent（仅当需要）组成。

                  ┌── subagent #1 ── validate-arch-report.md
attempt ${N}      ├── subagent #2 ── validate-security-report.md
round ${R}  ──────┤                                              ── 汇总 ── subagent #5 (修复) ── round +1
                  ├── subagent #3 ── validate-codereview-report.md
                  └── subagent #4 ── validate-test-report.md

1. 四段并行校验（subagent #1 / #2 / #3 / #4）

pipeline 主编排按 ../references/subagent-prompt-template.md 中的四份模板分别渲染， 同一轮次内四次 Task() 并行发起：

subagent	执行 agent	template 段	产出	日志

Track record

Benchmark

12 / 16

test cases passed, vs 6 / 16 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-story-pipeline/tapd-story-validate/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.