Back to Skills

planning-doc-generator

matteocervelli
Updated 2 days ago
61 views
10
10
View on GitHub
Metaworddata

About

This skill generates structured project assessment markdown documents from JSON input data. It automatically creates WHY/WHO/WHAT sections and includes a GO/NO-GO decision matrix for project evaluation. Developers should use it when they need to quickly generate planning documentation from structured project data.

Quick Install

Claude Code

Recommended
Plugin CommandRecommended
/plugin add https://github.com/matteocervelli/llms
Git CloneAlternative
git clone https://github.com/matteocervelli/llms.git ~/.claude/skills/planning-doc-generator

Copy and paste this command in Claude Code to install this skill

Documentation

Planning Document Generator Skill

Purpose

Generate structured assessment documents from JSON configuration. Converts project planning data into markdown assessment reports with purpose, stakeholder, and scope analysis plus a GO/NO-GO decision framework.

When to Use

  • Creating project assessment documents
  • Generating planning documentation from structured data
  • Building evaluation reports with decision matrices
  • Documenting project vision and scope
  • Creating stakeholder alignment assessments
  • Generating baseline project documentation

Input: JSON Format

The skill expects JSON input with the following structure:

{
  "project_name": "Project Name",
  "date": "2025-11-03",
  "why": {
    "exists": "Why does this project exist?",
    "problem": "What problem does it solve?",
    "vision": "What is the desired outcome?"
  },
  "who": {
    "stakeholders": "List of key stakeholders",
    "decision_makers": "Who decides",
    "executors": "Who does the work",
    "concerns": "Their priorities and concerns"
  },
  "what": {
    "building": "What are we building/changing?",
    "features": "Key features and components",
    "out_of_scope": "What is out of scope",
    "success_criteria": "Definition of success"
  },
  "go_no_go": {
    "purpose_clarity": "✓|⚠|✗",
    "stakeholder_alignment": "✓|⚠|✗",
    "scope_definition": "✓|⚠|✗",
    "resource_availability": "✓|⚠|✗",
    "timeline_feasibility": "✓|⚠|✗",
    "risk_assessment": "✓|⚠|✗",
    "success_metrics": "✓|⚠|✗"
  },
  "decision": "GO|CONDITIONAL|NO-GO",
  "rationale": "Explanation of decision"
}

Template Filling Process

  1. Load templates/assessment-template.md
  2. Replace all {PLACEHOLDER} values with JSON data
  3. Calculate coverage: Count non-empty answers ÷ 17 questions
  4. Insert status indicators (✓/⚠/✗) from GO/NO-GO section
  5. Generate markdown with formatted decision matrix
  6. Validate all sections populated with content (no {ANSWER} remaining)

Coverage Calculation

Total question count: 17

Breakdown:

  • WHY section: 3 questions
  • WHO section: 4 questions
  • WHAT section: 4 questions
  • GO/NO-GO section: 7 assessment items
  • Other: 1 additional (missing info summary)

Formula:

Coverage = (Number of answered/populated fields ÷ 17) × 100
Percentage = Round to nearest whole number

Output Location

Generated documents save to:

~/docs/planning/{project_slug}/assessment-{date}.md

Example:

~/docs/planning/project-name/assessment-2025-11-03.md

Workflow

JSON Input
    ↓
Load Template
    ↓
Replace Placeholders
    ↓
Calculate Coverage
    ↓
Format Decision Matrix
    ↓
Validate Completeness
    ↓
Write to ~/docs/planning/
    ↓
Markdown Output

Key Features

Status Indicators

  • Green: Ready to proceed
  • Yellow: Proceed with caution / clarification needed
  • Red: Blocker / do not proceed

Decision Framework

  • GO: All indicators green, proceed immediately
  • CONDITIONAL GO: Some yellow flags, proceed with mitigation
  • NO-GO: Red flags present, do not proceed without resolution

Coverage Tracking

Automatically calculates and displays:

  • Number of questions answered (X/17)
  • Percentage coverage
  • List of missing information

Best Practices

  1. Complete All Fields: Aim for 100% coverage (17/17)
  2. Be Specific: Use concrete details, not generic placeholders
  3. Stakeholder Buy-in: Ensure WHO section reflects actual decision-makers
  4. Realistic Assessment: Be honest in GO/NO-GO evaluation
  5. Document Decisions: Clear rationale essential for tracking

Example Usage

# Command-line usage
planning-doc-generator \
  --input project-plan.json \
  --output ~/docs/planning/myproject/

# Result
~/docs/planning/myproject/assessment-2025-11-03.md

Integration Points

Input Sources

  • Project planning worksheets (converted to JSON)
  • Kickoff meeting notes (structured into JSON)
  • Requirements documents (parsed to JSON format)
  • Stakeholder surveys (aggregated to JSON)

Output Consumers

  • Project stakeholders (for review/approval)
  • Project managers (for tracking)
  • Decision makers (for GO/NO-GO calls)
  • Documentation archives (for reference)

Validation Rules

Before writing output file:

  • All {PLACEHOLDER} values replaced
  • No {ANSWER} tokens remaining
  • Project name populated
  • Date populated (YYYY-MM-DD format)
  • Decision field contains valid value (GO, CONDITIONAL, NO-GO)
  • Coverage calculated and accurate

Version: 1.0.0 Created: 2025-11-03 Scope: Global utility skill

GitHub Repository

matteocervelli/llms
Path: .claude/skills/planning-doc-generator

Related Skills

content-collections

Meta

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

View skill

hybrid-cloud-networking

Meta

This skill configures secure hybrid cloud networking between on-premises infrastructure and cloud platforms like AWS, Azure, and GCP. Use it when connecting data centers to the cloud, building hybrid architectures, or implementing secure cross-premises connectivity. It supports key capabilities such as VPNs and dedicated connections like AWS Direct Connect for high-performance, reliable setups.

View skill

llamaindex

Meta

LlamaIndex is a data framework for building RAG-powered LLM applications, specializing in document ingestion, indexing, and querying. It provides key features like vector indices, query engines, and agents, and supports over 300 data connectors. Use it for document Q&A, chatbots, and knowledge retrieval when building data-centric applications.

View skill

csv-data-summarizer

Meta

This skill automatically analyzes CSV files to generate comprehensive statistical summaries and visualizations using Python's pandas and matplotlib/seaborn. It should be triggered whenever a user uploads or references CSV data without prompting for analysis preferences. The tool provides immediate insights into data structure, quality, and patterns through automated analysis and visualization.

View skill