What makes Pm Master notable?

3K downloads. Trust evidence available

How should Pm Master be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Claim this agent

agentCLAWHUBUnverified

Pm Master

Project & program management skill for the tech industry (waterfall/agile/iteration/hybrid), producing charter, WBS, Gantt, RAID, status reports, stage-gate reviews, EVM control. Also includes: (a) an outbound email communication gateway with mandatory approval + sponsor co-sign, (b) a pre-publish c Skill: Pm Master Owner: slearnai Summary: Project & program management skill for the tech industry (waterfall/agile/iteration/hybrid), producing charter, WBS, Gantt, RAID, status reports, stage-gate reviews, EVM control. Also includes: (a) an outbound email communication gateway with mandatory approval + sponsor co-sign, (b) a pre-publish c Tags: latest:2.2.17 Version history: v2.2.17 | 2026-09-22T14:08:06.235Z | use

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

3.0k

Updated

Oct 9, 2026

Version

2.2.17

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 3K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 3K downloadsadoption · observed Oct 9, 2026
Latest release: 2.2.17release · observed Sep 22, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s171srzvxc5431ssbjh7vggsvs884354:pm-master-2

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-slearnai-pm-master-2/snapshot"

Documentation

CLAWHUB

117,819 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: pm-master
description: "Project & program management skill for the tech industry (waterfall/agile/iteration/hybrid), producing charter, WBS, Gantt, RAID, status reports, stage-gate reviews, EVM control. Also includes: (a) an outbound email communication gateway with mandatory approval + sponsor co-sign, (b) a pre-publish confidentiality/leak scan over package contents, (c) Markdown-to-DOCX export, and (d) SOW/contract-driven expert-role dispatch. Activates on explicit intent to create, plan, execute, monitor, close, or govern a project/program and its artifacts. Do NOT trigger on casual PM advice, status interpretation only, or unrelated planning language."
license: MIT
allowed-tools: Read,Write,Edit,Bash,Glob,Grep,Agent,TaskCreate,TaskUpdate,TaskList,WebFetch,WebSearch
metadata:
  display_name: "PM Master - Project & Program Management"
  version: "2.2.17"
  category: productivity
---

# PM Master — Project & Program Management (OpenClaw Edition)

You are **PM Master (the orchestrator)**. This skill is an **enforced operating manual** — every step has
explicit input/output/verification and must not be skipped or reduced to advice. It turns project and program
management into a reproducible engineering system built on a single source of truth (`project.yaml`), verifiable
quality gates, enforced lifecycle state transitions, and multi-agent orchestration for building deliverables.

## 0.1 Capability → Script Map (description accurately reflects implementation)

| Claimed capability | Implementing script(s) | Notes |
|---|---|---|
| Charter / WBS / Gantt / schedule generation | `init_project.py`, `parse_sow.py`, `build_schedule.py`, `build_wbs.py`, `render.py` | Spec-driven; `parse_sow.py` requires `--apply` to persist |
| RAID / risk register / status report | `build_subproject.py`, `rerender_docs.py`, `artifact_guard.py` | Drift-detected against `project.yaml` |
| Stage-gate reviews + lifecycle state machine | `gate_engine.py`, `baseline.py`, `project_state.py` | Hard gates need `governance.approver_identities` |
| EVM + operational control / escalation | `control_engine.py`, `evm.py` | Stamps `last_control_check` only after a real inspection |
| Execution driver + control-cadence check | `execution_driver.py` | Reports; never writes `last_control_check` itself (SDI-4) |
| Outbound email gateway **with mandatory approval + sponsor co-sign** | `comm_send.py` | Off by default; authorization is **admin-policy only** (`config.email.approvers`) |
| Pre-publish confidentiality / leak scan | `confidentiality_check.py` | Tokens supplied via `config.yaml` (`confidentiality.*`), never hardcoded |
| Markdown → DOCX export | `render_docx.py` | Optional, separate step |
| SOW/contract-driven expert-role dispatch | `role_catalog.py`, `dispatch.py` | Domain/role inference from SOW text |
| Consistency / quality gate | `consistency_check.py`, `critic_review.py`, `subagent_check.py` | Exit 0 required before delivery |

## 0. Execution Backend (portable a

README.md

# PM Master · Project & Program Management Skill

> A **project + program** management skill for PMs in the tech industry. Builder philosophy, executable, with a built-in template library and multi-Agent orchestration, supporting four delivery methodologies: **waterfall / agile / iteration / hybrid**.

- **Version**: 2.2.17
- **License**: MIT
- **Positioning**: Every project/program request must produce a real artifact (file); advice-only responses are prohibited.
- **Discipline additions since 2.1.0**: SOW/contract parsing pipeline, executable WBS-decomposition Critic (6-factor self-audit), domain-agnostic role catalog, Operational Artifact Guardrail (OAG), bottom-up authoring & rollup, and a penetrating pre-publish confidentiality scan.

---

## 1. What Problems It Solves

Project delivery in the tech industry often gets stuck on three things: **inconsistent methodologies** (waterfall/agile/iteration/hybrid mixed arbitrarily), **no standard deliverables** (charter/WBS/risk/status reports each done their own way), and **unsustainable governance** (plans disconnected from execution, missing baselines, no periodic inspection). PM Master turns these three problems into a **executable engineering system**:

- Every request → a real file (Markdown, exportable to DOCX);
- Every project → a single source of truth `project.yaml`, continuous across sessions/Agents;
- Every discipline → a verifiable quality gate (consistency gate, baselining, operational control).

---

## 2. Core Capabilities

| Capability | Description | Applies To |
|------|------|------|
| Project Initiation / Planning | Charter, stakeholders, RACI, WBS, schedule, risk, RAID | Any methodology |
| Agile Delivery | Product Backlog, Sprint Plan, DoD, burndown, retrospective | agile |
| Iteration Delivery | Iteration Plan / Backlog / Review | iteration |
| Waterfall Delivery | Requirements Spec, WBS, Gantt, stage gates, quality plan | waterfall |
| Hybrid Governance | Governance map, macro-micro mapping | hybrid |
| Program Governance | Portfolio charter, portfolio dashboard, dependency map, benefits realization | program |
| Metrics Analysis | Earned value (EVM), schedule critical path, consistency check | Analysis scenarios |
| Multi-Agent Parallelism | Team up to produce mutually independent artifacts | Complex initiation / review |
| Dual-track Docs | Markdown source → DOCX formal document | Delivery / reporting |
| Phased Delivery | P0+P1 initiation & planning / P2 execution / P3 monitoring / P4 closeout phase modules; each phase defines activities/deliverables/criteria | Full lifecycle |
| Stage Gate Approval | `gate_engine` evaluates entry criteria + hard gates (execution/closeout) enforce approval, flipping the state machine | Phase transitions |
| Operational Dual-track Parallel | P2 execution track (domain experts) + P3 monitoring track (`monitoring-agent`) multi-Agent parallel, sharing the source of truth with zero field conflicts | Execution/Monitoring |
| External Communicati

_meta.json

{
  "ownerId": "kn70217mcwqf7ya07qzw4xv5rd8014q7",
  "slug": "pm-master-2",
  "version": "2.2.17",
  "publishedAt": 1790086086235
}

references/activity-expert-map.md

# Activity → Expert Dispatch Map · Activity-to-Expert Map

This file is the "routing table" for PM Master's second-layer dispatch: given the **domain, product, and task keywords** of a WBS activity/deliverable,
it determines which **expert role** should produce it. Works together with `references/expert-roles.md` (role definitions and prompts)
and `scripts/dispatch.py` (auto-generates the dispatch plan).

> **Single source of truth = `scripts/role_catalog.py`.** The domain catalogue, keyword maps, and
> specialization naming all live there. `dispatch.py` and `consistency_check.py` import it; this document
> is the human-readable mirror. **The pack is domain-agnostic** — it ships no data-domain bias and applies
> to any tech project (software / cloud / data / AI / security / product / QA / integration / ERP / BI).

## 1. Tech Domains (inferred from contract/SOW extract)

`infer_domain(text)` scans the SOW/contract objective+scope+assumptions and picks the best-matching domain.
When no signal is found, domain = `generic` and roles fall back to cross-cutting / neutral defaults.

| domain key | covers |
|------------|--------|
| `data-platform` | data lake / warehouse / ETL / modeling / governance |
| `software-dev` | application / backend / frontend / microservice / mobile |
| `cloud-infra` | cloud / k8s / terraform / SRE / platform / DevOps / network |
| `ai-ml` | LLM / GenAI / ML / model training / MLOps |
| `cybersecurity` | security / privacy / AppSec / SecOps |
| `product` | product management / ownership / UX |
| `qa` | test engineering / automation / performance |
| `integration` | ESB / middleware / API gateway |
| `erp` | ERP implementation / finance-HR modules |
| `biz-analytics` | BI / reporting / metrics layer |

> `project.domain` may also be set explicitly (e.g. via `init_project.py --domain <domain>`); an explicit
> domain overrides inference. Legacy project domains (`insurance-data-lake` / `payments` / `ecommerce` /
> `fintech-core`) still resolve via a backward-compat map in `role_catalog.py` so existing programs keep
> their specialization labels.

## 2. Activity Type → Role (keyword routing, by domain)

Routing is **two-tier**: (1) if a domain is known, its domain-specific role keywords win; (2) otherwise
cross-cutting keywords apply; (3) ambiguous words fall back to a neutral role (e.g. "model/design" → `solution-architect`).
Representative mappings (full set in `role_catalog.py`):

| Activity / deliverable keywords (EN) | domain | dispatch role role_id |
|------------------------------|--------|------------------|
| modeling / model / schema / ERD / subject-domain | data-platform | `data-architect` |
| migration / ETL / load / data-pipeline | data-platform | `etl-engineer` |
| governance / metadata / lineage / audit | data-platform | `data-governance-lead` |
| desensitization / privacy / PII / encryption / compliance | data-platform / cybersecurity | `data-security-engineer` / `privacy-engineer` |
| architecture-design / module

references/agents.md

# Dedicated Sub-Agent Role Definitions

Dedicated sub-Agents dispatched by the master controller in team mode. Each role has a single responsibility and clear inputs/outputs, making them easy to run in parallel without conflicts.
Sub-Agents **never reach the user directly**; they only produce files and report back to the master controller.

> Common constraint: all roles use `project_state.py` to read/write `<project>/project.yaml`, and use `render.py` to produce files;
> fill unknown fields with "(TBD)" and annotate them to avoid consistency-check failures.

## 1. planner-agent
- **Responsibility**: decompose scope → WBS / product Backlog / iteration plan; produce milestones and schedule.
- **Input**: `project.yaml`; methodology-specific plan templates (waterfall/wbs, agile/product_backlog, iteration/iteration_plan).
- **Output**: `plans/wbs.md` or `plans/product_backlog.md` etc.; write back `artifacts.wbs` / `artifacts.backlog`; `project.scope` / `metrics.burndown` (if applicable) in `project.yaml`.
- **brief essentials**: the WBS must cover all scope; each item has a unique ID, deliverable, owner, and effort estimate.

## 2. scheduler-agent
- **Responsibility**: turn the WBS/Backlog into a dependency-aware schedule, marking the critical path and milestone dates.
- **Input**: planner artifacts; `templates/waterfall/schedule_gantt.md`.
- **Output**: schedule data `plans/schedule.yaml` (for validation by `schedule_health.py`) + rendered Gantt notes.
- **brief essentials**: tasks include id/name/duration/deps; dependencies must point to existing task IDs.

## 3. risk-agent
- **Responsibility**: identify risks/assumptions/issues/dependencies (RAID), rate each risk by probability × impact, assign an owner, and write mitigation measures.
- **Input**: `project.yaml`; `templates/common/risk_register.md`, `templates/common/raid_log.md`.
- **Output**: `risks/risk_register.md`, `risks/raid_log.md`; write back `raid.risks[]` (with owner, mitigation), `artifacts.risk`.
- **brief essentials**: every risk must have an owner and mitigation, otherwise the consistency check fails.

## 4. stakeholder-agent
- **Responsibility**: map stakeholders, build the RACI, and define the communication plan.
- **Input**: `project.yaml`; `templates/common/stakeholder_register.md`, `templates/common/raci.md`, `templates/common/communication_plan.md`.
- **Output**: `docs/stakeholder_register.md`, `docs/raci.md`, `docs/communication_plan.md`; write back `project.sponsor` / `project.pm` / `project.team[]`.
- **brief essentials**: sponsor and pm must be explicit (mandatory quality gate item).
- **Contact-book sync (critical)**: after finalizing the "stakeholder contact book" in `communication_plan.md`, you **must sync every row into `communication.contacts[]` in `project.yaml`** (using `project_state.py set communication.contacts '<yaml>'`). This is the machine-readable recipient library for email communication—`communication-agent` / `comm_send.py` only reads `project.yaml`, not M

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/slearnai/skills/pm-master-2",
      "sourceUrl": "https://clawhub.ai/slearnai/skills/pm-master-2",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T10:11:23.232Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-slearnai-pm-master-2/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-slearnai-pm-master-2/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T10:11:23.232Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "3K downloads",
      "href": "https://clawhub.ai/slearnai/pm-master-2",
      "sourceUrl": "https://clawhub.ai/slearnai/pm-master-2",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T10:11:23.232Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "2.2.17",
      "href": "https://clawhub.ai/slearnai/pm-master-2",
      "sourceUrl": "https://clawhub.ai/slearnai/pm-master-2",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-09-22T14:08:06.235Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-slearnai-pm-master-2/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-slearnai-pm-master-2/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 2.2.17",
      "description": "pm-master-2 v2.2.17 changelog - Removed the .gitignore and skill-card.md files from the repository. - Updated SKILL.md to clarify capability–script mapping, ensuring the description accurately reflects actual implementation. - Improved documentation: streamlined and consolidated the enforced operating manual, removing version-specific legacy notes. - No changes to workflow or underlying logic; all platform capabilities and iron rules remain enforced as before.",
      "href": "https://clawhub.ai/slearnai/pm-master-2",
      "sourceUrl": "https://clawhub.ai/slearnai/pm-master-2",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-09-22T14:08:06.235Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 9, 2026.

About

Avoid when

Public facts

Install and run

Documentation

Extracted files

SKILL.md

README.md

_meta.json

references/activity-expert-map.md

references/agents.md

Related agents

activepieces

cherry-studio

AionUi

CopilotKit

Machine-readable data