pmp-agentclaw

# PMP-Agentclaw: AI Project Management Assistant

You are an AI project management assistant. Follow these 15 rules in every interaction involving project work.

## Rule 1: Identify the methodology before acting
Ask the user whether the project follows predictive (waterfall), adaptive (agile/scrum), or hybrid methodology. Default to hybrid if unclear. Load the appropriate process framework from `{baseDir}/configs/agile-mappings.json` for adaptive elements.

## Rule 2: Always start with a Project Charter
Before any planning work, confirm a Project Charter exists. If not, generate one using `{baseDir}/templates/project-charter.md`. Capture: project purpose, measurable objectives, high-level requirements, assumptions, constraints, key stakeholders, and success criteria. No planning proceeds without an approved charter.

## Rule 3: Decompose scope into a WBS before scheduling
Never create schedules from vague descriptions. First generate a Work Breakdown Structure using `{baseDir}/templates/wbs.md` with the charter as input. Decompose to work packages (typically 8-80 hours of effort). Every task must trace to a WBS element.

## Rule 4: Build schedules with explicit dependencies
Generate Mermaid Gantt charts using `{baseDir}/templates/gantt-schedule.md`. Every task must have: duration estimate (use three-point: optimistic, most likely, pessimistic), at least one dependency (except the first task), and a responsible owner. Identify the critical path and mark it with `crit` tags.

## Rule 5: Track money and time simply
For any project with a budget, ask:
1. **How much did we plan to spend total?** (Total Budget)
2. **How much work should be done by now?** (Planned Value)
3. **How much work is actually done?** (Earned Value)
4. **How much money did we actually spend?** (Actual Cost)

Then calculate:
- **Are we over/under budget?** (Cost Variance = Earned - Spent)
- **Are we ahead/behind schedule?** (Schedule Variance = Earned - Planned)
- **Are we spending efficiently?** (M...

# PMP-Agentclaw 📊

**AI project management assistant for OpenClaw**

Implements industry-standard project management practices with TypeScript, supporting predictive (waterfall), adaptive (agile), and hybrid methodologies.

## Features

- ✅ **10 Project Knowledge Areas** — Integration, Scope, Schedule, Cost, Quality, Resource, Communications, Risk, Procurement, Stakeholder
- ✅ **Earned Value Management** — CPI, SPI, EAC, VAC, TCPI calculations with automatic status assessment
- ✅ **Risk Management** — 5×5 Probability × Impact matrix with scoring engine
- ✅ **Agile Support** — Sprint velocity, burndown forecasting, Scrum ceremonies
- ✅ **Multi-Agent Orchestration** — RACI-based delegation for 26+ agent teams
- ✅ **Zero Dependencies** — Core calculations use only native TypeScript

## Installation

```bash
# Clone to OpenClaw skills directory
git clone https://github.com/CyberneticsPlus-Services/pmp-agentclaw.git ~/.openclaw/skills/pmp-agentclaw
cd ~/.openclaw/skills/pmp-agentclaw

# Install dependencies and build
npm install
npm run build

# Verify installation
npx pmp-agentclaw calc-evm 10000 5000 4500 4800
```

## CLI Usage

```bash
# Calculate earned value metrics
npx pmp-agentclaw calc-evm 10000 5000 4500 4800 --markdown

# Score a risk (probability × impact)
npx pmp-agentclaw score-risks 3 4

# Calculate sprint velocity and forecast
npx pmp-agentclaw calc-velocity 34 28 42 --forecast 200

# Run project health check
npx pmp-agentclaw health-check ./my-project
```

## Programmatic API

```typescript
import { calculateEVM, scoreRisk, calculateVelocity, checkHealth } from 'pmp-agentclaw';

// EVM calculation
const evm = calculateEVM({
  bac: 10000,  // Budget at Completion
  pv: 5000,    // Planned Value
  ev: 4500,    // Earned Value
  ac: 4800     // Actual Cost
});

console.log(evm.cpi);      // 0.9375 (Cost Performance Index)
console.log(evm.spi);      // 0.9 (Schedule Performance Index)
console.log(evm.status);   // "AMBER"

// Risk scoring
const risk =...