Tapd Story Tasks logo

Tapd Story Tasks

Organization
TencentBlueKing
tapd-story-tasks

迭代执行流水线任务生成阶段。基于 plan.md / research.md 调用 /speckit.tasks 生成全量任务, 随后调用 /speckit.analyze 验证产物合规。两段命令通过两次 subagent 隔离执行。 命令与报告模板详见 ../references/subagent-prompt-template.md §2.3 + §2.4。

Overview

PublisherTencentBlueKing
Repositorybk-bcs
Skill nametapd-story-tasks
Stars
840
Forks
263
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by TencentBlueKing on GitHub. Read the source before you install it.

Installation

Install the Tapd Story Tasks AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/TencentBlueKing/bk-bcs/tree/master/.agents/skills/tapd-story-pipeline/tapd-story-tasks
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/TencentBlueKing/bk-bcs.git /tmp/bk-bcs
mkdir -p .claude/skills
cp -r /tmp/bk-bcs/.agents/skills/tapd-story-pipeline/tapd-story-tasks .claude/skills/tapd-story-tasks
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tapd Story Tasks in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Tapd Story Tasks on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Tapd Story Tasks is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

需求实现任务

前置条件

  • 当前需求 phase 为 researched
  • ${WORKDIR}/plan.md、research.md、data-model.md(如有)已存在
  • pipeline 主编排已按 references/context-and-meta-template.md 重写当前阶段的 context.md

输入

  • ${WORKDIR}/meta.yaml(读取 attempts)
  • 当前需求 ID(由 pipeline 主编排传入)
  • ${WORKDIR}/plan.md / research.md / data-model.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 pipeline 主编排先后渲染两份 SUBAGENT_PROMPT,分别拉起两个 subagent:

  1. 第一段:按 ../references/subagent-prompt-template.md §2.3 Tasks-Generate 模板 渲染,调用 speckit-tasks 生成 tasks.md。
  2. 第二段:按 §2.4 Tasks-Analyze 模板渲染,调用 speckit-analyze 验证产物合规 并产出 tasks-report.md。

拆成两段的理由:speckit-analyze 是独立skill,需要在 tasks.md 落盘后重新拉起 agent 进程。

渲染填充:${ID} / ${VERSION} / ${WORK_DIR} / attempts / round; 若 attempts > 1,附上 iteration-patches/attempt-${attempts}.md 摘要。

两段的 shell 命令、tasks-report.md 统一模板、Verdict 判定规则(四态归因) 均在 subagent-prompt-template.md §2.3 + §2.4 中定义,本子 skill 不重复。

内容门禁(主编排内联)

在 tasks-analyze 的合规判断中,主编排必须对 tasks.md 增加以下内容检查:

检查项通过标准
格式与可执行性每项任务使用 - [ ] TNNN ... 格式,包含具体动作和文件路径
用户价值切片用户故事任务按优先级组织;每个故事均包含独立测试标准和端到端可验证的交付切片
TDD 与验收TDD 被要求时,每个功能切片有对应测试任务或验收测试;任务描述可直接执行
依赖关系tasks.md 含依赖顺序和并行机会;阻塞任务在依赖任务之前
最小主流程首个可交付用户故事覆盖 Walking Skeleton 或等效的核心 happy path
完整性plan.md 中的接口、数据模型、迁移/配置和文档更新需求均映射到任务,或明确标注不适用

不要求任务标题使用固定术语;由 tasks-analyze 按语义判断。任一项不满足时, compliance.verdict=needs_fix,报告须列出缺失项,主编排按同 attempt round 重试整组 tasks-generate + tasks-analyze。

消费 subagent 回传 JSON

第一段失败(status=fail)按 references/error-handling.md 处理,通常升级为回退重入。

第一段成功后进入第二段。按第二段 compliance.verdict 分支:

Verdict主会话动作
pass进入"更新状态"推进 phase
needs_fix同 attempt 内 round +1,重新跑第一段 + 第二段(最多 3 个 round)
plan_insufficient整理 findings 为 attempt-${N+1}.md,target_phase_to_re_enter=plan,走回退重入
spec_insufficient同上,target_phase_to_re_enter=specify

更新状态

compliance.verdict=pass 时:

  • 更新 meta.yaml.phase 为 tasks-generated
  • meta.yaml.history 追加成功记录,清空 meta.yaml.last_failure

可重入约定

通用规则见 ../references/shared-reentry-conventions.md。本阶段差异:

  • round 重试触发条件:compliance.verdict=needs_fix,同 attempt 内最多 3 个 round
  • 两段 subagent 均追加重入增量段(subagent-prompt-template.md §2.3 + §2.4)
  • 报告文件不做快照:tasks-report.md 每轮覆盖重写,历史可经 process.log 回溯

幂等性、产物保留、process.log 仅追加等通用约束见 ../references/reentry-protocol.md。

信息不足回退(回退重入入口)

verdict=plan_insufficient 或 spec_insufficient 时,attempt-${N+1}.md 必须明确:

  • failed_phase: tasks
  • root_cause:可直接复用 tasks-report.md 中对应 Finding 的根因字段
  • target_phase_to_re_enter: plan 或 specify(按归因最深处确定)

参考资料

  • SUBAGENT_PROMPT(tasks-generate + tasks-analyze 模板 + 报告模板):../references/subagent-prompt-template.md §2.3 + §2.4
  • 通用回传 JSON Schema:../references/subagent-prompt-template.md §1.3
  • 上下文与元数据模板:../references/context-and-meta-template.md
  • 可重入协议:../references/reentry-protocol.md
  • 错误处理:../references/error-handling.md

产出

  • ${WORKDIR}/tasks.md — 全量任务清单
  • ${WORKDIR}/tasks-report.md — speckit-analyze 合规报告
  • ${WORKDIR}/process.log — stream-json 流式日志(追加,含两段 banner)
  • ${WORKDIR}/meta.yaml — 更新后的 attempts / round / history
  • 需求 phase 为 tasks-generated

Frequently asked questions

What does the Tapd Story Tasks AI skill do?

迭代执行流水线任务生成阶段。基于 plan.md / research.md 调用 /speckit.tasks 生成全量任务, 随后调用 /speckit.analyze 验证产物合规。两段命令通过两次 subagent 隔离执行。 命令与报告模板详见 ../references/subagent-prompt-template.md §2.3 + §2.4。

Why use Tapd Story Tasks on TypingMind?

Because you install it once and use it with any model. Tapd Story Tasks is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Tapd Story Tasks in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TencentBlueKing/bk-bcs/tree/master/.agents/skills/tapd-story-pipeline/tapd-story-tasks. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Tapd Story Tasks?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Tapd Story Tasks?

As many as you like. As long as a model supports skills, you can use Tapd Story Tasks with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tapd Story Tasks AI skill free?

It is published on GitHub by TencentBlueKing. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇