00 Meta Initialization logo

00 Meta Initialization

Community
peterbamuhigire
00-meta-initialization

Use when initialising documentation and a methodology roadmap for a brand-new project by detecting project type, selecting Waterfall, Agile, or Hybrid delivery, and generating the governed document sequence.

Overview

Publisherpeterbamuhigire
Repositorychwezi-dev-engine
Skill name00-meta-initialization
Stars
29
Forks
6
Bundled files
159
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 159 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by peterbamuhigire on GitHub. Read the source before you install it.

Installation

Install the 00 Meta Initialization AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/peterbamuhigire/chwezi-dev-engine/tree/main/00-meta-initialization
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/peterbamuhigire/chwezi-dev-engine.git /tmp/chwezi-dev-engine
mkdir -p .claude/skills
cp -r /tmp/chwezi-dev-engine/00-meta-initialization .claude/skills/00-meta-initialization
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 00 Meta Initialization in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads 00 Meta Initialization on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so 00 Meta Initialization is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Meta-Initialization Skill

Evidence Produced

CategoryArtifactFormatExample
Release evidenceMethodology selection and initialisation recordMarkdownproject context, decision criteria, selected route, rejected options, generated artefacts, and validation

Inputs

ArtefactRequired?Purpose
Project objective, stakeholders, constraints, and delivery contextyesClassify project and method
Existing documents and standardsconditionalAvoid duplicate or conflicting scaffolds

Outputs

ArtefactConsumerAcceptance condition
Project profile and documentation roadmapProject teamMethod justified, phases ordered, owners and gates explicit

Capability contract

Read/search are required. Creating directories or documents requires explicit project-initialisation scope; never overwrite existing artefacts without inspection.

Degraded mode

Fallback with incomplete context: produce a provisional profile and question register, not a falsely definitive methodology.

Decision rules

ConditionMethodFailure avoided
Stable regulated scope and formal approvalsWaterfallMissing governance evidence
Evolving product with iterative discoveryAgilePremature specification lock-in
Formal gates plus iterative deliveryHybridFalse either/or method choice

Domain anti-patterns

  • Selecting Agile because requirements are missing. Fix: gather minimum project facts first.
  • Generating every possible document. Fix: justify each artefact by risk and audience.
  • Overwriting an existing roadmap. Fix: inspect and propose a merge.
  • Treating the method as a label. Fix: define gates, cadence, owners, and evidence.
  • Marking provisional assumptions as decisions. Fix: keep an explicit question register.

Process Workflow

Step-by-Step Instructions

Step 1: Scan Project Directory

Scan ../ (parent project root) for indicators:

Project Type Indicators:

  • package.json → Node.js/JavaScript project
  • composer.json → PHP project
  • requirements.txt / pyproject.toml → Python project
  • .sln / .csproj → C# .NET project
  • pom.xml / build.gradle → Java project
  • Cargo.toml → Rust project
  • go.mod → Go project

Existing Documentation:

  • README.md → Check for methodology mentions
  • ARCHITECTURE.md → Check for design approach
  • projects//_context/methodology.md → Previous methodology selection

Development Artifacts:

  • .git/ → Git repository (check for branch strategy)
  • docker-compose.yml → Containerized deployment
  • .github/workflows/ → CI/CD setup

Log all findings:

[Scan Report]
- Project Type: PHP (composer.json detected)
- Framework: Laravel (composer.json dependencies)
- Database: MySQL (migrations/ directory)
- Deployment: Docker (docker-compose.yml)
- Version Control: Git
- CI/CD: GitHub Actions
- Existing Docs: README.md, ARCHITECTURE.md
- Existing Context: None (first-time setup)

Step 2: Detect Project Characteristics

Based on scan results, determine:

Regulatory/Compliance Indicators

Check for keywords in README.md, documentation:

  • "FDA", "FAA", "DOD", "medical device", "aerospace" → Regulated project
  • "HIPAA", "GDPR", "SOC2", "PCI-DSS" → Compliance required
  • "safety-critical", "life-safety" → Formal V&V needed
Project Maturity
  • Greenfield (no existing code): Need comprehensive upfront planning
  • Brownfield (existing codebase): Need documentation for existing system
  • Startup/MVP: Fast iteration, evolving requirements
  • Enterprise: Established processes, likely Waterfall or SAFe
Team Structure

Infer from repository activity (if Git history exists):

  • Multiple contributors, PR workflow → Team environment
  • Single contributor → Solo developer
  • Frequent commits → Agile/iterative
  • Infrequent, large commits → Waterfall/milestone-based

Step 3: Recommend Methodology

Based on detected characteristics, recommend:

Recommend Waterfall if:
  • ✅ Regulatory/compliance keywords detected
  • ✅ Project type: Medical, aerospace, government, automotive
  • ✅ Fixed-scope contract language in docs
  • ✅ Formal signoff processes mentioned
  • ✅ Safety-critical system

Confidence Score: Calculate based on indicators (0-100%)

Example:

[Recommendation: Waterfall] (Confidence: 85%)

Reasons:
1. "FDA" and "medical device" detected in README.md
2. Formal compliance requirements (HIPAA)
3. Fixed-scope project (contract.pdf found)
4. Safety-critical indicators present

Recommended Pipeline:
- 02-requirements-engineering/waterfall/ (Full IEEE 830 SRS)
- 03-design-documentation/ (HLD + LLD for traceability)
- 09-governance-compliance/ (Traceability matrix, audit reports)
Recommend Agile if:
  • ✅ Startup/MVP keywords in README
  • ✅ Frequent commits (>10/week average)
  • ✅ Sprint-based branch naming (feature/, sprint/)
  • ✅ User-centric language ("user stories", "epics")
  • ✅ No regulatory constraints

Example:

[Recommendation: Agile] (Confidence: 90%)

Reasons:
1. Startup project (package.json: version 0.3.2)
2. Frequent commits (average 15/week)
3. Feature branch workflow detected
4. No regulatory constraints detected
5. README mentions "MVP" and "rapid iteration"

Recommended Pipeline:
- 02-requirements-engineering/agile/ (User stories, backlog)
- 07-agile-artifacts/ (Sprint planning, DoD, DoR)
- Lightweight design docs (HLD only, no LLD)
Recommend Hybrid if:
  • ✅ Mixed indicators (regulatory backend + agile frontend)
  • ✅ Microservices architecture (some services regulated, others not)
  • ✅ SAFe framework indicators
  • ✅ Enterprise with agile teams

Example:

[Recommendation: Hybrid] (Confidence: 70%)

Reasons:
1. Microservices architecture detected (docker-compose.yml: 8 services)
2. Backend mentions "payment processing" (regulated)
3. Frontend is React SPA (rapid iteration)
4. Mix of waterfall (API) and agile (UI) branches

Recommended Pipeline:
- Backend: 02-requirements-engineering/waterfall/ (IEEE 830 SRS for payment service)
- Frontend: 02-requirements-engineering/agile/ (User stories for UI)
- Shared: 03-design-documentation/ (Unified HLD)

Step 4: User Selection

Present recommendation and allow user to confirm or override:

==================================================
SDLC-Docs-Engine: Methodology Selection
==================================================

Based on analysis of your project, we recommend:

📋 WATERFALL METHODOLOGY (Confidence: 85%)

Reasons:
- Regulated industry detected (FDA, medical device)
- Fixed-scope project indicators
- Safety-critical system

This recommendation suggests:
✅ Comprehensive upfront requirements (IEEE 830 SRS)
✅ Formal design documentation (HLD + LLD)
✅ Traceability matrix and audit reports
✅ Verification & Validation per IEEE 1012

==================================================

Do you want to:
[1] Accept recommendation (Waterfall)
[2] Choose Agile instead
[3] Choose Hybrid approach
[4] Show detailed comparison
[5] Skip methodology selection (manual setup)

Your choice:

Step 5: Generate Documentation Roadmap

Based on selected methodology, create doc_roadmap.md:

For Waterfall Projects:
markdown
# Documentation Roadmap: [Project Name]

**Methodology:** Waterfall
**Selected:** [Date]
**Rationale:** [Brief explanation from detection]

## Active Documentation Pipelines

### Phase 01: Strategic Vision (Optional but Recommended)
- [ ] 01-prd-generation → Product Requirements Document

### Phase 02: Requirements Engineering (MANDATORY)
- [ ] 02-requirements-engineering/waterfall/01-initialize-srs
- [ ] 02-requirements-engineering/waterfall/02-context-engineering
- [ ] 02-requirements-engineering/waterfall/03-descriptive-modeling
- [ ] 02-requirements-engineering/waterfall/04-interface-specification
- [ ] 02-requirements-engineering/waterfall/05-feature-decomposition
- [ ] 02-requirements-engineering/waterfall/06-logic-modeling
- [ ] 02-requirements-engineering/waterfall/07-attribute-mapping
- [ ] 02-requirements-engineering/waterfall/08-semantic-auditing

### Phase 03: Design Documentation (MANDATORY)
- [ ] 03-design-documentation/01-high-level-design
- [ ] 03-design-documentation/02-low-level-design
- [ ] 03-design-documentation/03-api-specification

### Phase 05: Testing Documentation (MANDATORY)
- [ ] 05-testing-documentation/01-test-strategy
- [ ] 05-testing-documentation/02-test-plans

### Phase 09: Governance & Compliance (MANDATORY)
- [ ] 09-governance-compliance/01-traceability-matrix
- [ ] 09-governance-compliance/02-audit-reports
- [ ] 09-governance-compliance/03-compliance-docs (if HIPAA/GDPR/SOC2)

## Disabled Pipelines

❌ **Phase 07: Agile Artifacts** (Not applicable for Waterfall)
❌ **Phase 02: Agile Requirements** (Using Waterfall SRS instead)

## Execution Order

1. **Week 1-2:** Phase 02 (Requirements) - Generate IEEE 830 SRS
2. **Week 3-4:** Phase 03 (Design) - HLD and LLD
3. **Week 5:** Phase 05 (Testing) - Test strategy and plans
4. **Week 6:** Phase 09 (Governance) - Traceability and audits

**Total Estimated Time:** 6 weeks for complete documentation suite

## Next Steps

Run: 02-requirements-engineering/waterfall/01-initialize-srs
For Agile Projects:
markdown
# Documentation Roadmap: [Project Name]

**Methodology:** Agile (Scrum)
**Selected:** [Date]
**Rationale:** [Brief explanation]

## Active Documentation Pipelines

### Phase 01: Strategic Vision (MANDATORY for Agile)
- [ ] 01-strategic-vision/01-prd-generation → Lightweight PRD

### Phase 02: Requirements Engineering (MANDATORY)
- [ ] 02-requirements-engineering/agile/01-user-story-generation
- [ ] 02-requirements-engineering/agile/02-acceptance-criteria
- [ ] 02-requirements-engineering/agile/03-story-mapping
- [ ] 02-requirements-engineering/agile/04-backlog-prioritization

### Phase 03: Design Documentation (Lightweight)
- [ ] 03-design-documentation/01-high-level-design (HLD only, skip LLD)

### Phase 07: Agile Artifacts (MANDATORY)
- [ ] 07-agile-artifacts/01-sprint-planning
- [ ] 07-agile-artifacts/02-definition-of-done
- [ ] 07-agile-artifacts/03-definition-of-ready

### Phase 08: End-User Documentation (Post-MVP)
- [ ] 08-end-user-documentation/01-user-manual

## Disabled Pipelines

❌ **Phase 02: Waterfall SRS** (Using Agile user stories instead)
❌ **Phase 09: Formal Governance** (Lightweight traceability via story tags)

## Execution Order

1. **Sprint 0:** Phase 01 (Vision) + Phase 02 (User Stories)
2. **Sprint 0:** Phase 03 (HLD) - Architectural overview
3. **Sprint 1-N:** Phase 07 (Agile Artifacts) - Ongoing per sprint
4. **Post-MVP:** Phase 08 (User Docs)

**Total Estimated Time:** 1-2 sprints for initial setup, then continuous

## Next Steps

Run: 01-strategic-vision/01-prd-generation
Then: 02-requirements-engineering/agile/01-user-story-generation

Step 6: Initialize Project Context

Check if projects/<ProjectName>/_context/ exists:

If missing:

bash
mkdir -p projects/<ProjectName>/_context
echo "Project context directory created."

If exists:

[INFO] Project context directory already exists.
Checking for existing files...

Found:
- vision.md (last modified: 2026-01-15)
- features.md (last modified: 2026-01-20)

Missing:
- methodology.md (will be created)
- doc_roadmap.md (will be created)

Step 7: Write Output Files

File 1: projects/<ProjectName>/_context/methodology.md

Use template from templates/methodology.md.template (populated with detection results).

File 2: projects/<ProjectName>/_context/doc_roadmap.md

Use template from templates/doc_roadmap.md.template (populated based on methodology).

File 3: projects/<ProjectName>/_context/project_profile.md
markdown
# Project Profile

**Generated:** [Date]
**Project Type:** [Detected type]
**Framework:** [Detected framework]
**Database:** [Detected database]
**Deployment:** [Detected deployment]

## Characteristics

- **Regulatory Constraints:** [Yes/No - list standards]
- **Team Size:** [Inferred from git history]
- **Development Pace:** [Rapid/Moderate/Methodical]
- **Maturity:** [Greenfield/Brownfield/Startup/Enterprise]

## Recommended Methodology

**Selected:** [Waterfall/Agile/Hybrid]
**Confidence:** [XX%]

See `methodology.md` for full rationale.

Resources

Common Pitfalls

❌ Skipping this skill

  • Jumping directly to Phase 02 without methodology selection leads to wrong documentation approach

❌ Overriding recommendation without justification

  • If you choose Agile for a regulated project, document WHY (e.g., regulatory approval already obtained)

❌ Not updating roadmap when project changes

  • Re-run this skill if project characteristics change (e.g., startup gets FDA approval)

❌ Ignoring hybrid recommendations

  • If recommended Hybrid, don't force pure Waterfall or Agile

Verification Checklist

Before proceeding to Phase 01/02:

  • projects/<ProjectName>/_context/methodology.md exists and is populated
  • projects/<ProjectName>/_context/doc_roadmap.md exists with checklist
  • projects/<ProjectName>/_context/project_profile.md exists
  • Methodology selection is documented with rationale
  • Next steps are clear (which skill to run next)
  • Team agrees with methodology choice (if applicable)

Integration with Other Phases

This skill enables:

  • Phase 01 (Strategic Vision): Knows whether to generate PRD (Agile) or skip (Waterfall starts with SRS)
  • Phase 02 (Requirements): Activates correct pipeline (waterfall/ or agile/)
  • Phase 03 (Design): Determines depth (full HLD+LLD for Waterfall, lightweight HLD for Agile)
  • Phase 07 (Agile Artifacts): Only activates if methodology is Agile or Hybrid
  • Phase 09 (Governance): Determines formality level (full RTM for Waterfall, lightweight for Agile)

Upstream Dependencies:

  • None (this is the first skill to run)

Downstream Consumers:

  • All other phases read methodology.md to determine their execution mode

Example Output

See templates/ directory for complete examples:

  • methodology.md.example - Waterfall selection for medical device
  • methodology.md.example-agile - Agile selection for startup
  • methodology.md.example-hybrid - Hybrid for enterprise SaaS

Maintenance & Updates

When to re-run this skill:

  • Project characteristics change significantly (e.g., startup becomes enterprise)
  • Regulatory status changes (e.g., FDA approval required mid-project)
  • Team decides to switch methodologies
  • Major pivot in product direction

Safe to re-run: Yes, this skill will prompt before overwriting existing files.


Last Updated: 2026-02-07 Skill Version: 1.0.0 Maintained by: Peter Bamuhigire

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 99 more files.

Frequently asked questions

What does the 00 Meta Initialization AI skill do?

Use when initialising documentation and a methodology roadmap for a brand-new project by detecting project type, selecting Waterfall, Agile, or Hybrid delivery, and generating the governed document sequence.

Why use 00 Meta Initialization on TypingMind?

Because you install it once and use it with any model. 00 Meta Initialization is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install 00 Meta Initialization in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/peterbamuhigire/chwezi-dev-engine/tree/main/00-meta-initialization. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use 00 Meta Initialization?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with 00 Meta Initialization?

As many as you like. As long as a model supports skills, you can use 00 Meta Initialization with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the 00 Meta Initialization AI skill free?

Yes. It is published on GitHub by peterbamuhigire under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇