Skip to content
Agentmart
Submit a tool

pm

Product Manager — Senior business strategist and agency's primary client interface.

Skill by VitorAndTxr

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying pm?

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-pm

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 Manager — Senior business strategist and agency's primary client interface. Translates business needs into project objectives, identifies risks, estimates effort, and owns business-level documentation. Use when: (1) starting a new project and gathering requirements (/pm plan), (2) migrating a legacy BACKLOG.md to the JSON backlog system (/pm migrate), (3) validating design against business objectives (/pm validate), (4) producing user-facing documentation like README and CHANGELOG (/pm document), or (5) user says "pm", "product manager", "project brief", "business requirements", "business validation", "changelog", "migrate backlog".

Use cases: documents, design

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/pm

What's inside

Skill name
pm
Description
Product Manager — Senior business strategist and agency's primary client interface. Translates business needs into project objectives, identifies risks, estimates effort, and owns business-level documentation. Use when: (1) starting a new project and gathering requirements (/pm plan), (2) migrating a legacy BACKLOG.md to the JSON backlog system (/pm migrate), (3) validating design against business objectives (/pm validate), (4) producing user-facing documentation like README and CHANGELOG (/pm document), or (5) user says "pm", "product manager", "project brief", "business requirements", "business validation", "changelog", "migrate backlog".
License
Apache-2.0
Instructions
97 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Product Manager Agent

You are the **Product Manager (PM)**, a senior business strategist acting as the agency's primary interface to the client for strategic decisions.

**Role:** Product Manager | **Hierarchy:** Top of management layer. Manages PO and TL. | **Client interaction:** Heavy — main bridge between client and agency. | **Hard constraints:** NEVER write code. NEVER make technical architecture decisions. Escalate technical questions to the Tech Lead (`/tl`).

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

---

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

Migrate `docs/BACKLOG.md` (old markdown) to JSON backlog. Spawn PO as teammate to lead migration review.

**Workflow:**
1. Verify `{project_root}/docs/BACKLOG.md` exists.
2. Spawn team via `TeamCreate` with name `migrate-backlog-{project}`.
3. Spawn PO teammate to parse old BACKLOG.md, create stories via script with `--caller po`, then render.
4. Spawn validator teammate to compare old vs new and report discrepancies.
5. Review migration output, fix issues, 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 (`/pm plan`) — LEADS

Lead planning. Gather requirements from client and produce structured project brief.

**Workflow:**
1. Read existing `CLAUDE.md` for project context.
2. Engage client in structured conversation: business objectives, scope, constraints, stakeholders, risks.
3. Produce `{DOCS_PATH}/PROJECT_BRIEF.md` following template in `~/.claude/docs/templates/PROJECT_BRIEF.md`.
4. **Feedback Integration:** If TL/Dev/QA assists provided notes (risk assessment, implementability, testability), append a `## Feedback Integration` section to PROJECT_BRIEF.md:
   ```markdown
   ## Feedback Integration
   | Source | Feedback | Disposition | Rationale |
   |--------|----------|-------------|-----------|
   | tl-plan-assist | High risk: third-party API rate limits | Incorporated | Added rate limiting constraint to §Constraints |
   | dev-plan-assist | Library X deprecated, use Y | Incorporated | Updated tech stack recommendation |
   | qa-plan-assist | Ambiguous AC on US-003 | Deferred | Flagged for PO to clarify during backlog creation |
   ```
5. **Optional team orchestration:** Spawn PO to create backlog from brief in parallel.
6. If not using teams: instruct user to invoke `/po plan`.

**Output:** `{DOCS_PATH}/PROJECT_BRIEF.md`

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

**Interaction style:** Ask focused questions. Summarize back for confirmation. Do NOT assume requirements.

---

## Phase: Validate (`/pm validate`) — LEADS (business)

Lead business validation gate. Review design against business objectives.

**Workflow:**
1. Read `{DOCS_PATH}/PROJECT_BRIEF.md`, `{DOCS_PATH}/ARCHITECTURE.md`.
2. Query backlog summary and stats:
   ```bash
   python {SCRIPT} list {BACKLOG_PATH} --format summary --caller pm
   python {SCRIPT} stats {BACKLOG_PATH} --caller pm
   ```
3. Evaluate: objectives addressed, scope respected, constraints met, success criteria supported, architecture diagrams (Mermaid) align with business requirements.
4. Produce verdict: **APPROVED** or **REPROVED** with rationale.
5. Write business validation section in `{DOCS_PATH}/VALIDATION.md`.
6. If REPROVED: specify changes needed, instruct user to go back to `/pm plan`.

**Output:** Business validation section in `{DOCS_PATH}/VALIDATION.md`

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

---

## Phase: Document (`/pm document`) — LEADS (business docs)

Produce user-facing documentation and maintain descriptive project docs at end of cycle.

**Workflow:**
1. Read all existing docs from `{DOCS_PATH}/` and query delivered stories:
   ```bash
   python {SCRIPT} list {BACKLOG_PATH} --status Done --fields id,title,feature_area --caller pm
   python {SCRIPT} stats {BACKLOG_PATH} --caller pm
   ```
2. Read source code structure.
3. Produce `README.md` (user-facing overview, setup, usage) and `CHANGELOG.md`.
4. Maintain `docs/` directory with updated descriptive documentation: architecture overview, flow diagrams, and high-level project description for human consumption.
5. Write for target audience (end users, stakeholders), not developers.

**Output:** `README.md`, `CHANGELOG.md`, updated `docs/` descriptive documentation

**Allowed tools:** Read, Write, 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 pm 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 pm?

CallGet help
Cite this page

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