PM Master - Project & Program Management for Openclaw

PM Master turns project and program management into a governed, repeatable workflow that generates verified planning, execution, monitoring, and closeout artifacts.

slearnai
v2.2.17
Sep 22, 2026
0
3.1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install pm-master-2

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install pm-master-2 using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is PM Master - Project & Program Management?

PM Master is an enforced project and program management operating system for OpenClaw. It supports waterfall, agile, iteration, and hybrid methodologies while using project.yaml as the single source of truth for project state, deliverables, metrics, governance, and checkpoints.

Unlike advisory-only Openclaw Skills, PM Master produces files, applies lifecycle gates, validates artifacts, dispatches domain experts, and blocks delivery when quality, approval, confidentiality, or consistency requirements are not met. It can generate charters, WBS structures, schedules, RAID logs, status reports, EVM metrics, stage-gate reviews, DOCX documents, and program rollups.

PM Master - Project & Program Management Use Cases

  • Initialize a new technical project or program with a schema-versioned project.yaml source of truth.
  • Create charters, stakeholder plans, RACI matrices, communication plans, requirements, quality plans, and kickoff materials.
  • Build waterfall or hybrid WBS structures, schedules, Gantt views, critical-path analysis, and SOW-level plans.
  • Generate agile backlogs, sprint plans, definitions of done, burndown-oriented reports, and iteration plans.
  • Manage risks, assumptions, issues, dependencies, changes, RAID logs, and calibrated 5x5 risk registers.
  • Monitor operational delivery with control patrols, earned value management, CPI/SPI metrics, and escalation workflows.
  • Govern stage transitions from planning through review, baseline, operational execution, and closeout.
  • Coordinate multiple sub-agents and domain experts for SOW-driven WBS decomposition.
  • Produce formal Markdown or DOCX project documents for internal and external stakeholders.
  • Prepare outbound email communications with mandatory human approval, sponsor co-signing, allowlists, audit records, and confidentiality scanning.

How PM Master - Project & Program Management Works

  1. Locate or create the project.yaml source of truth, migrate legacy schemas when necessary, and confirm the current checkpoint.
  2. Classify the request across project or program type, methodology, lifecycle phase, and intent, then persist those dimensions in project.yaml.
  3. Load the applicable methodology and phase references, including program or hybrid guidance where relevant.
  4. Dispatch planner and domain-expert agents to decompose SOW-level work into compliant leaf packages with roles, owners, estimates, dependencies, and definitions of done.
  5. Select a direct, parallel team, or fork execution mode based on task complexity, independence, and context requirements.
  6. Prepare structured data files and render each deliverable through the appropriate template and script rather than hand-writing final artifacts.
  7. Run forced analysis such as WBS and schedule generation, schedule health, EVM, control-engine checks, or execution-driver patrols according to the methodology and phase.
  8. Persist artifact references, metrics, and checkpoints back into project.yaml while maintaining bottom-up authoring for sub-projects and read-only rollups for programs.
  9. Validate every sub-agent report and run consistency_check.py before delivery; failures block completion until corrected.
  10. Apply lifecycle and stage gates, freeze baselines before execution, and require explicit approval for hard transitions and formal external communications.
  11. Consolidate the final artifact index, optionally export Markdown to DOCX, run confidentiality controls, and report deliverables with key metrics.

PM Master - Project & Program Management Setup

  1. Install or copy the PM Master skill directory into the OpenClaw skills location and ensure its scripts, templates, references, and config.yaml are available.
  2. Confirm Python and the required YAML dependency are available. The implementation uses its maintained source scripts first, then the renderer directly, with PyYAML as the dependency fallback.
python --version
python -m pip install pyyaml
  1. Review config.yaml before use. Configure execution.subagent_mode as team, agent, or fork; set methodology and quality-gate options; and define stage-gate behavior.
  2. Keep outbound email disabled unless an administrator has configured a trusted backend, email.approvers, and email.sponsor_approvers. Do not enable external communication without an approval policy.
  3. Configure confidentiality tokens and scanning rules under confidentiality.* in config.yaml. Sensitive values must be supplied through configuration and must not be hardcoded in scripts.
  4. Initialize a project or program from the skill directory:
python scripts/init_project.py "Example Platform Program" --type project --methodology hybrid
python scripts/project_state.py show --project /workspace/example-platform/project.yaml
  1. For an existing project, migrate and inspect the state before generating artifacts:
python scripts/project_state.py migrate --project /workspace/example-platform/project.yaml
python scripts/project_state.py show --project /workspace/example-platform/project.yaml
  1. Run the relevant workflow scripts from the skill directory and finish with the mandatory quality gate:
python scripts/consistency_check.py --project /workspace/example-platform/project.yaml
  1. For formal documents, render the validated Markdown output separately with render_docx.py. For email, create a draft first and send only through comm_send.py after an authorized approval and sponsor co-sign are recorded.

PM Master - Project & Program Management Data Schema & Taxonomy

The skill uses a file-centered, schema-driven model with project.yaml as the authoritative record.

Data area Organization and purpose
project.yaml Single source of truth containing project or program identity, methodology, phase, intent, lifecycle checkpoint, artifacts, WBS, metrics, governance, and configuration references. Schema version 2 adds _checkpoint.
Four dimensions type, methodology, phase, and intent determine which references, templates, scripts, and deliverables are required.
_checkpoint Records workflow progress and prevents illegal lifecycle skips. States progress through planning, review, baselined, operational, and closed.
wbs Expert-decomposed work packages with IDs, domains, roles, owners, numeric estimates, dependencies, and definitions of done. Leaf packages must respect control.granularity_threshold, normally 10 person-days.
artifacts Index of generated deliverables and their paths, including charters, schedules, RAID logs, reports, plans, closure documents, and rollups.
metrics Operational and earned-value data such as planned value, earned value, actual cost, CPI, SPI, baseline information, and control timestamps.
governance Stage-gate settings, approver identities, communications audit records, approvals, and lifecycle controls. Self-approval is forbidden.
config.yaml Runtime policies for execution backends, quality gates, stage gates, email, confidentiality scanning, and control cadence.
<slug>_data.yaml Intermediate structured data prepared for each rendered deliverable.
Markdown outputs Template-rendered project documents generated by render.py; final delivery requires consistency_check.py exit 0.
DOCX outputs Optional formal documents generated from validated Markdown by render_docx.py.
Dispatch and reports dispatch.py creates an idempotent expert dispatch plan; sub-agents return contract-based JSON reports validated by subagent_check.py.
Program rollups Program views consolidate sub-project milestones, health, blockers, benefits, and dependencies through scripted rollup tools rather than hand-edited parallel sources.
Communication audit Approved outbound messages are recorded under governance.communications; email remains off by default.
Confidentiality results confidentiality_check.py scans text and binary content for configured sensitive tokens before publication.

The taxonomy separates project versus program scope, waterfall versus agile or hybrid methodology, lifecycle phase, and user intent. This prevents incompatible templates, such as mixing waterfall WBS and stage gates with agile-only backlog structures.

PM Master - Project & Program Management Advanced Features

  • Enforced lifecycle state machine with hard and soft stage gates, baseline freezing, approval identities, and rejection of illegal transitions.
  • SOW- and contract-driven expert-role dispatch using domain and role inference, idempotent dispatch plans, and configurable granularity thresholds.
  • Multi-agent execution through team, agent, or fork backends with a common abstract dispatch vocabulary.
  • Contract-based sub-agent JSON reports, automated validation, issue feedback, and retry handling before consolidation.
  • Bottom-up project and sub-project authoring with scripted program rollups to prevent governance drift and false status.
  • Earned value management with CPI and SPI metrics, baseline comparisons, control cadence checks, and operational escalation.
  • Schedule health analysis covering critical path and float, plus separate program-level and SOW-level schedule views.
  • Mandatory consistency and critic reviews that validate scope, milestones, payment assumptions, constraints, dependencies, roles, and estimates.
  • Secure outbound communication gateway that is disabled by default and requires allowlisted approval, sponsor co-signing, requester separation, and audit logging.
  • Pre-publish confidentiality and leak scanning across text and binary package contents using configurable tokens.
  • Template-based Markdown rendering and optional Markdown-to-DOCX export for formal stakeholder documentation.
  • Checkpointed execution and artifact indexing so every request produces a traceable file and every delivery can be reproduced.
  • Methodology-aware routing for initiation, planning, execution, monitoring, risk, change control, and closeout deliverables.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*