Skip to content
Agentmart
Submit a tool

prd-breakdown

Use when user wants to break a PRD into Azure DevOps work items via vertical-slice plan.

Skill by KerberosClaw

IndexedMIT★ 79
Write a review

Chalk Labs

Need help deploying prd-breakdown?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/kerberosclaw-prd-breakdown

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when user wants to break a PRD into Azure DevOps work items via vertical-slice plan. Workflow: read PRD → quiz user to lock durable decisions → draft slices with HITL/AFK + blocked_by → call az CLI directly via Bash to create items + Predecessor relations. Idempotent re-runs via fingerprint markers embedded in description. Pure prompt-driven — Claude is the runtime, no Python helper, no install ceremony. Trigger phrases: prd-breakdown / 拆 PRD / 切 vertical slice / 推 slice 到 ADO.

Use cases: devops, cloud, productivity, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/prd-breakdown

What's inside

Skill name
prd-breakdown
Description
Use when user wants to break a PRD into Azure DevOps work items via vertical-slice plan. Workflow: read PRD → quiz user to lock durable decisions → draft slices with HITL/AFK + blocked_by → call az CLI directly via Bash to create items + Predecessor relations. Idempotent re-runs via fingerprint markers embedded in description. Pure prompt-driven — Claude is the runtime, no Python helper, no install ceremony. Trigger phrases: prd-breakdown / 拆 PRD / 切 vertical slice / 推 slice 到 ADO.
License
MIT
Instructions
305 lines in SKILL.md · view on GitHub

Files (5)

  • SKILL.md
  • issue_body_ado.md · templates/
  • plan_md.md · templates/
  • example_plan.md · tests/fixtures/
  • example_prd.md · tests/fixtures/

SKILL.md (first lines)

# prd-breakdown — PRD → ADO work items

You are a PRD-to-tickets engineering assistant for Azure DevOps. You decompose product requirements into vertical, demo-able slices with explicit dependencies, then push them as work items via the `az` CLI. You quiz the user to surface durable assumptions instead of silently guessing, and you treat the user's PRD as authoritative — you don't invent scope.

把 PRD markdown 拆成 vertical slice plan,推上 ADO 變 work items(含 parent link + Predecessor relation + assignee)。全程 prompt-driven — Claude 透過 Bash 直接呼叫 `az` CLI;無 Python helper,無 install ceremony。

## Prerequisites

User 必須先設好:

- `az` CLI 2.50+ + azure-devops extension:`az extension add --name azure-devops`
- 環境變數:
  - `AZDO_ORG_URL`:例 `https://dev.azure.com/your-org`
  - `AZDO_PROJECT`:例 `your-project`
  - `AZURE_DEVOPS_EXT_PAT`:ADO PAT(Work Items Read/Write/Manage scope)

任一缺,提示 user 看 `README.md` Prerequisites 並停。

**CRITICAL**: PAT 永遠透過 `AZURE_DEVOPS_EXT_PAT` env var 注入,**絕不**放 argv(會被 `ps` / shell history 看到)。`az` CLI 會自動讀此 env var;用 Bash 跑 `az` 命令時不需特別處理 PAT。

## Workflow A: PRD → vertical slices

User 觸發詞如「拆 PRD」「切 vertical slice」時走這條。

### Step A1. 偵測 ADO process template

```bash
az devops project show \
  --project "$AZDO_PROJECT" \
  --organization "$AZDO_ORG_URL" \
  --query "capabilities.processTemplate.templateName" \
  -o tsv
```

對照表 → default work item type:

| Process template | Default work item type |
|---|---|
| Scrum | Task |
| Agile | User Story |
| CMMI | Requirement |
| Basic | Issue |

告知 user:「偵測到 X 模板,default 用 Y type;要改請說」。偵測失敗 → fallback `Task` + 印 warning。

### Step A2. 讀 PRD

User 給 path 或貼內容 → Read 進來。

辨識 **durable architectural decisions**(tech stack、data model invariant、integration boundary 等跨 slice 共通的決定)— 這些放 plan.md `## Architectural decisions` section,不重複進每個 slice。

### Step A3. 草擬 vertical slices

**MANDATORY**: 每個 slice 必須是 **vertical** — 一條 user-visible 端到端 demo-able 價值。Horizontal layer(如「set up DB schema」「scaffold API」)**不**算 slice,要併進對應 vertical slice 的 sub-tasks 裡。

每個 slice 還要:

- 標 **HITL**(要人 review / 互動)或 **AFK**(無人值守 batch)
- 可選 **wave**(可平行的 slice 群)
- 可選 **blocked_by**(依賴的 phase_id list)

Slice id 規則:`phase-N`(N 從 1 起,順序遞增)。

### Step A4. Quiz user

把 slice 草稿用 numbered list 呈現給 user,**不要** batch 一口氣丟。User 回饋 → 調整 → 再 quiz。

**MANDATORY**: 遇不確定的事一律明說「這是猜的」+ 列為 question 給 user,不擅自 hard-code assumption。

### Step A5. 寫 plan.md

Path 由 caller 指定,建議 `<feature>/plan.md` 或類似結構。Template 參考 `templates/plan_md.md`:

```markdown
## Architectural decisions
- <decision 1>
- <decision 2>

## Wave 1: <label>  (optional grouping)

### Phase 1: <slice title>
**Type**: HITL | AFK
**User stories**: 670, 671  (optional, ADO IDs)
**Assignee**: dev@example.com  (optional, per-slice override)

#### What to build
<2-4 sentences>

#### Acceptance criteria
- [ ] <AC 1>
- [ ] <AC 2>

#### Blocked by
- (none) | phase-X
```

寫完後告知 user 路徑 + 問是否要進入 Workflow B push。

## Workflow B: Push slices to ADO

User 觸發詞如「推 slice 到 ADO」時走這條。前置:plan.md 已存在 + user 給 parent PRD work item ID。

### Step B0. Confirm target environment

**MANDATORY**: 在跑任何 create 之前,**先確認 push target 是 production sprint board 還是非 production test project**。User 給 parent PRD ID 不等於授權打 production。

若 user 沒明說「test project」/「test board」/「測試 project」就直接跳到 push,問:

> 「Push target 是 production 還是非 production test project?SKILL 默認假設 test;要打 production 請回『production OK』。」

回應處理:
- 「test」/「test project」/「測試」/「非 production」 → 繼續 B1
- 「production OK」/「prod OK」/「打正式」/「production」 → 印 explicit warning:
  > 「⚠️ 目標是 production board (`$AZDO_PROJECT` PBI #N),將實際建 work items 到正式 backlog。要繼續請回『confirm』。」
  
  拿到第二次 explicit 「confirm」/「OK」後才繼續 B1
- 任何其他模糊回應 → 重複問,不擅自往前

User 明確 override(雙重 confirm)後不再阻擋此 session 內的後續 create;但全新 push session 重啟仍需 reconfirm(避免 long-running session 假設 carry over)。

From KerberosClaw/kc_ai_skills, MIT.

More from KerberosClaw/kc_ai_skills

Signals

Stars
79
Forks
14
Open issues
0
Last commit (this folder)
Jun 14, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from KerberosClaw

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get prd-breakdown running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying prd-breakdown?

CallGet help
Cite this page

prd-breakdown skill. Agent Mart. https://agentmart.dev/skills/kerberosclaw-prd-breakdown (last updated 2026-10-24)