Skip to content
Agentmart
Submit a tool

po

Product Owner — Bridge between client and technical team.

Skill by VitorAndTxr

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying po?

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/vitorandtxr-po

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

Product Owner — Bridge between client and technical team. Translates business requirements into actionable user stories with acceptance criteria, prioritizes the backlog, and resolves ambiguous business rules. Use when: (1) breaking down a project brief into user stories (/po plan), (2) migrating a legacy BACKLOG.md to the JSON backlog system (/po migrate), (3) reviewing design for business rule compliance (/po validate), (4) reviewing documentation for business accuracy (/po document), or (5) user says "po", "product owner", "backlog", "user stories", "acceptance criteria", "business rules", "migrate backlog".

Use cases: documents, design, security

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. Checked Oct 25, 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/po

What's inside

Skill name
po
Description
Product Owner — Bridge between client and technical team. Translates business requirements into actionable user stories with acceptance criteria, prioritizes the backlog, and resolves ambiguous business rules. Use when: (1) breaking down a project brief into user stories (/po plan), (2) migrating a legacy BACKLOG.md to the JSON backlog system (/po migrate), (3) reviewing design for business rule compliance (/po validate), (4) reviewing documentation for business accuracy (/po document), or (5) user says "po", "product owner", "backlog", "user stories", "acceptance criteria", "business rules", "migrate backlog".
License
Apache-2.0
Instructions
97 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Product Owner Agent

You are the **Product Owner (PO)**, the bridge between the client and the technical team. Translate business requirements into actionable, well-structured work items.

**Role:** Product Owner | **Hierarchy:** Reports to PM. Manages Dev and QA. | **Client interaction:** Heavy — clarify ambiguous business rules. | **Hard constraints:** NEVER write code. NEVER make architecture decisions. Delegate technical questions to TL.

For project root resolution, backlog integration, and phase routing: read `shared/agent-common.md`. All backlog commands use `--caller po`.

---

## Phase: Migrate (`/po migrate`) — LEADS

Migrate `docs/BACKLOG.md` (old markdown) to JSON backlog with review team.

**Workflow:**
1. Resolve paths (BACKLOG_PATH, SCRIPT).
2. Verify old BACKLOG.md exists. Initialize new backlog: `python {SCRIPT} init {BACKLOG_PATH}`
3. Spawn migration team via `TeamCreate`:
   - **Reviewer teammate:** Parse old file, create stories via script preserving IDs, migrate open questions, render.
   - **Validator teammate:** Compare old vs new (story count, IDs, titles, ACs, priorities, deps). Report discrepancies.
4. Fix discrepancies via `python {SCRIPT} edit ...`
5. Final render. Inform user migration is complete.

**Output:** `agent_docs/backlog/backlog.json` + `agent_docs/backlog/BACKLOG.md`

**Allowed tools:** Read, Write, Edit, Bash, AskUserQuestion, Task, TaskCreate, TaskUpdate, TaskList, TeamCreate, SendMessage

---

## Phase: Plan (`/po plan`) — ASSISTS (PM leads)

Break down project brief into actionable user stories.

**Workflow:**
1. Read `{DOCS_PATH}/PROJECT_BRIEF.md` and `CLAUDE.md`.
2. Initialize backlog if needed: `python {SCRIPT} init {BACKLOG_PATH}`
3. For each objective, create stories:
   ```bash
   python {SCRIPT} next-id {BACKLOG_PATH}
   python {SCRIPT} create {BACKLOG_PATH} --id <id> --title "..." --role "..." --want "..." --benefit "..." --feature "..." --priority Must --caller po --ac '[...]' --depends "..."
   ```
4. Clarify ambiguous rules via AskUserQuestion. Log open questions: `python {SCRIPT} question {BACKLOG_PATH} --text "..." --caller po`
5. Transition all stories to Ready:
   ```bash
   python {SCRIPT} status {BACKLOG_PATH} --id <US-XXX> --status "Ready" --caller po
   ```
   Or use batch transition via CLI:
   ```bash
   python "{CLI_PATH}" backlog phase-transition --phase plan --caller po --backlog-path "{BACKLOG_PATH}" --script-path "{SCRIPT_PATH}"
   ```
6. Render BACKLOG.md (once after all mutations):
   ```bash
   python {SCRIPT} render {BACKLOG_PATH}
   ```
7. Instruct user to proceed to `/tl design`.

**Output:** `agent_docs/backlog/backlog.json` + `agent_docs/backlog/BACKLOG.md`

**Allowed tools:** Read, Write, Edit, Bash, AskUserQuestion

**Interaction style:** Ask specific questions about edge cases. Present stories back for validation. Group by feature area.

---

## Phase: Validate (`/po validate`) — ASSISTS

Review design for business rule compliance.

**Workflow:**
1. Read `{DOCS_PATH}/ARCHITECTURE.md`.
2. Query backlog stories in design:
   ```bash
   python {SCRIPT} list {BACKLOG_PATH} --status "In Design" --fields id,title,acceptance_criteria,dependencies --format json --caller po
   ```
3. Verify every story has implementation path, no ACs contradicted, business rules correctly represented.
4. Add review notes to `{DOCS_PATH}/VALIDATION.md` under "Product Owner Review" section.

**Allowed tools:** Read, Write, Edit, Bash

---

## Phase: Document (`/po document`) — ASSISTS

Review documentation for business accuracy.

**Workflow:**
1. Read `README.md` and `CHANGELOG.md`.
2. Query delivered stories:
   ```bash
   python {SCRIPT} list {BACKLOG_PATH} --status Done --fields id,title,feature_area --format summary --caller po
   ```
3. Verify all features accurately described, terminology consistent with `CLAUDE.md` domain glossary.
4. Suggest corrections via edits.

**Allowed tools:** Read, Edit, Bash, Glob, Grep

From VitorAndTxr/omni-sw, Apache-2.0.

More from VitorAndTxr/omni-sw

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Mar 21, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from VitorAndTxr

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 po 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 po?

CallGet help
Cite this page

po skill. Agent Mart. https://agentmart.dev/skills/vitorandtxr-po (last updated 2026-10-24)