By ddunnock
Run the NASA Phase A concept development lifecycle: ideate system ideas with feasibility checks, define bounded problems via 5W2H analysis, propose black-box architectures with diagrams, drill down functional blocks with domain research and gap analysis, skeptically verify claims, then generate cited concept documents and solution landscapes.
Phase 3 — Define concept at functional level with blocks, relationships, principles, and ASCII diagrams. No implementation details.
Phase 5 — Generate Concept Document and Solution Landscape with section-by-section approval and mandatory assumption review
Phase 4 — Decompose functional blocks, research domains, identify gaps, and list solution approaches with cited sources
Initialize a concept development session, create workspace, and detect available research tools
Phase 2 — Refine viable ideas into a clear, bounded problem statement using adapted 5W2H questioning
Black-box architecture generation agent. Proposes multiple approaches, elaborates functional blocks with ASCII diagrams, and guides section-by-section approval.
Final document composition agent. Produces Concept Document and Solution Landscape with section-by-section approval and source citations.
Research execution agent for drill-down phase. Uses tiered tool strategy with verification protocol and confidence levels. Registers sources via source_tracker.py.
Gap identification agent for drill-down phase. Identifies unknowns per block, lists solution OPTIONS (not recommendations) with citations.
Open-ended questioning agent for spit-ball ideation sessions. Probes feasibility, expands ideas with "what if" questions, and clusters themes.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A collection of plugins that extend Claude's capabilities. Supports two plugin types:
claude-plugins/
├── skills/ # Skill plugins (19 skills)
│ ├── concept-dev/
│ ├── documentation-architect/
│ ├── fault-tree-analysis/
│ ├── fishbone-diagram/
│ ├── five-whys-analysis/
│ ├── fmea-analysis/
│ ├── kepner-tregoe-analysis/
│ ├── pareto-analysis/
│ ├── plugin-creator/
│ ├── problem-definition/
│ ├── rcca-master/
│ ├── requirements-dev/
│ ├── research-opportunity-investigator/
│ ├── skill-tester/
│ ├── specification-refiner/
│ ├── speckit-generator/
│ ├── streaming-output/
│ ├── streaming-output-mcp/
│ └── trade-study-analysis/
├── mcps/ # MCP server plugins
│ ├── knowledge-mcp/
│ └── session-memory/
├── tools/ # Packaging utilities
│ ├── init_plugin.py # Create new plugins
│ ├── validate_plugin.py # Validate plugins
│ ├── package_plugin.py # Package for distribution
│ └── install_mcp.py # Install MCPs to ~/.claude/
└── dist/ # Packaged .plugin files (gitignored)
Skills provide workflows, procedures, and domain knowledge that Claude loads based on context. Each skill has:
MCPs provide tools that are always available in Claude Desktop. Each MCP has:
# Create a skill
python tools/init_plugin.py skill my-skill --path skills
# Create an MCP
python tools/init_plugin.py mcp my-mcp --path mcps
python tools/package_plugin.py skills/my-skill
# Creates: my-skill.plugin
# From packaged file
python tools/install_mcp.py dist/session-memory.plugin
# From directory (symlink for development)
python tools/install_mcp.py mcps/session-memory --symlink
Then add to Claude Desktop config (~/.config/claude/claude_desktop_config.json):
{
"mcpServers": {
"session-memory": {
"command": "python3",
"args": ["~/.claude/session-memory/server.py"]
}
}
}
| Skill | Description |
|---|---|
| rcca-master | Orchestrate RCCA investigations using 8D methodology with integrated tool selection |
| problem-definition | 5W2H and IS/IS NOT analysis for precise problem statements |
| five-whys-analysis | Root cause analysis with guided questioning and quality scoring |
| fishbone-diagram | Ishikawa cause-and-effect diagrams with 6Ms/8Ps/4Ss categories |
| pareto-analysis | 80/20 Rule analysis for prioritizing vital few causes |
| kepner-tregoe-analysis | KT Problem Solving and Decision Making (Situation/Problem/Decision/Potential Problem Analysis) |
| fault-tree-analysis | Boolean logic analysis for system failure pathways and minimal cut sets |
| fmea-analysis | Failure Mode and Effects Analysis (DFMEA/PFMEA) using AIAG-VDA methodology |
| Skill | Description |
|---|---|
| speckit-generator | Project specification and task management with PLANS taxonomy, ADR decisions, SMART criteria, anti-pattern detection |
| specification-refiner | SEAMS framework analysis with sequential clarification and multi-phase workflow |
| documentation-architect | Transform documentation using the Diátaxis framework |
| research-opportunity-investigator | Research and opportunity investigation for protocols |
| Skill | Description |
|---|---|
| concept-dev | NASA Phase A concept development lifecycle: ideation, problem definition, black-box architecture, drill-down with gap analysis, and document generation with cited research |
| requirements-dev | INCOSE-compliant requirements development with hybrid quality checking (16 deterministic + 9 semantic rules), verification planning, bidirectional traceability, assumption lifecycle management, gap analysis, and ReqIF export |
| Skill | Description |
|---|---|
| trade-study-analysis | Systematic trade study using DAU 9-Step Process with sensitivity analysis |
npx claudepluginhub ddunnock/claude-plugins --plugin concept-devTransform concept development artifacts into INCOSE-compliant formal requirements. AI-assisted requirements development with hybrid quality checking (16 deterministic + 9 semantic INCOSE GtWR v4 rules), verification planning, bidirectional traceability, gap analysis against concept architecture, assumption lifecycle management, and ReqIF export. Organized around functional blocks from concept development. Includes cross-cutting notes registry, need/requirement split workflow, gap discovery agent, assumption tracker, 5 specialized agents (quality-checker, tpm-researcher, skeptic, gap-analyst, document-writer), 16 scripts, 10 commands, and hooks for automatic state updates. Use when developing requirements, formalizing needs, writing specifications, building traceability, analyzing coverage gaps, managing assumptions, or preparing for systems engineering reviews.
Stream long-form content to markdown files with resume capability and context preservation
Transform documentation using the Diátaxis framework
Project-focused specification and task management with PLANS taxonomy, ADR-style architecture decisions, SMART acceptance criteria, SEAMS-enhanced clarification, tech-specific designer agents, anti-pattern detection (50 patterns across 5 tech stacks), 4-level verification (stub detection + wiring checks), execution orchestration (deviation rules, checkpoint taxonomy, auth gates, session continuity), specialized analysis agents, git checkpoints, mandatory approval gates, and session-memory hooks. Outputs to speckit/ directory.
Deep test, analyze, and audit Claude skills. Use this skill whenever the user wants to test a skill's behavior, analyze how it uses the Claude API, inspect inputs/outputs from scripts, or run security and code review audits against skill scripts. Trigger on: "test my skill", "analyze this skill", "audit skill scripts", "review skill for security issues", "what does this skill actually do when it runs", "inspect API calls from skill", "run a skill through its paces", "check my skill for bugs or vulnerabilities". Also trigger when the user shows you a SKILL.md and asks you to evaluate, critique, or stress-test it.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification