By ddunnock
Enforces a structured specification and task management workflow using PLANS taxonomy, ADR-style architecture decisions, SMART acceptance criteria, and SEAMS clarification. Generates language-specific implementation designs (React/Next.js, Python, Rust, TypeScript), detects anti-patterns across 5 tech stacks, validates code against project rules, and maintains traceability from requirements to tasks.
Use this agent when validating Architecture Decision Records (ADRs) for completeness and compliance with MADR template requirements. <example> Context: User just completed /plan command which generated ADRs user: "[Plan generation complete with 4 ADRs]" assistant: "The plan is complete. I'll validate the ADRs to ensure they meet the required standards." <commentary> Proactive validation after plan generation to catch incomplete ADRs early. </commentary> </example> <example> Context: User wants to verify architecture decisions are properly documented user: "Validate the architecture decisions in my plan file" assistant: "I'll use the adr-validator agent to check all ADRs against MADR template requirements." <commentary> Explicit request to validate ADR documentation quality. </commentary> </example> <example> Context: Plan file exists with ADRs that may be incomplete user: "Check if the ADRs in speckit/plan.md are ready for implementation" assistant: "I'll validate the ADRs to ensure they have all required fields for their designated levels." <commentary> Pre-implementation validation to ensure ADRs are complete before task execution. </commentary> </example>
Use this agent when scanning specifications for unclear, vague, or conflicting requirements. Detects ambiguities across 13 SEAMS taxonomy categories and prioritizes by impact. <example> Context: User just completed /analyze and has a spec document user: "The spec is ready, can you check if anything is unclear?" assistant: "I'll scan the specification for ambiguities." <commentary> After analysis phase, proactively scan for specification gaps before moving to implementation. </commentary> </example> <example> Context: User has a requirements document that needs review user: "Find all the unclear requirements in this spec" assistant: "I'll use the ambiguity scanner to identify vague or conflicting requirements." <commentary> Explicit request to find unclear requirements triggers the scanner. </commentary> </example> <example> Context: Spec document exists but has quality concerns user: "This spec feels incomplete, what's missing?" assistant: "I'll scan for specification gaps and prioritize what needs clarification." <commentary> When spec clarity is questioned, scan across all 13 categories to find gaps. </commentary> </example>
Use this agent to scan code for anti-patterns before code review or after implementation. Detects common mistakes that indicate inexperience and provides remediation guidance. <example> Context: User completed implementing a feature user: "I've finished the user authentication module" assistant: "Let me scan for anti-patterns in the implementation." <commentary> Proactive trigger: After significant implementation work, check for common mistakes </commentary> </example> <example> Context: User wants to review code quality user: "Check this code for anti-patterns" assistant: "I'll scan your code against known anti-patterns for your tech stack." <commentary> Explicit trigger: User directly asks to check for anti-patterns </commentary> </example> <example> Context: PR review or code review request user: "Review my PR for issues" assistant: "Let me run anti-pattern detection to identify common code smells." <commentary> Context trigger: Code review requests should include anti-pattern scanning </commentary> </example>
Use this agent when validating code and artifacts against directive rules from constitution.md and technology-specific memory files. Triggers when checking compliance with MUST/MUST NOT rules, verifying implementation against project requirements, or ensuring artifacts follow security and testing directives. <example> Context: User just completed an implementation task with /implement user: "Check if my implementation complies with the project requirements" assistant: "I'll use the compliance-checker agent to validate your implementation against the project directives." <commentary> Proactive triggering after implementation to verify compliance with spec and project rules. </commentary> </example> <example> Context: User wants to verify code follows security requirements user: "Does my auth code follow the security rules in constitution.md?" assistant: "I'll run the compliance-checker agent to validate your auth code against the security directives." <commentary> Explicit request to verify implementation against specific directive files. </commentary> </example> <example> Context: Pre-merge review needs compliance verification user: "Before merging, make sure this follows all our MUST rules" assistant: "I'll use the compliance-checker agent to scan for any MUST/MUST NOT violations before merge." <commentary> Critical compliance gate check before code integration. </commentary> </example>
Use this agent when mapping requirements to implementation coverage, checking traceability between specs and tasks, or identifying orphan requirements and tasks. <example> Context: User just ran /tasks and wants to verify all requirements are covered user: "Check that all requirements from the spec have corresponding tasks" assistant: "I'll use the coverage-mapper agent to analyze traceability between your spec and tasks." <commentary> After task generation, coverage mapping ensures no requirements were missed. </commentary> </example> <example> Context: User is reviewing the implementation plan user: "Are there any orphan tasks that don't trace back to requirements?" assistant: "I'll use the coverage-mapper agent to identify any tasks without requirement traceability." <commentary> Explicit request to check requirements traceability and find orphan items. </commentary> </example> <example> Context: User wants to verify spec coverage before starting implementation user: "Show me which spec sections don't have any planned tasks yet" assistant: "I'll use the coverage-mapper agent to build a traceability matrix and identify uncovered spec sections." <commentary> Proactive coverage analysis to find gaps before implementation begins. </commentary> </example>
This skill should be used when writing Architecture Decision Records (ADRs), documenting technical decisions, or reviewing architecture choices. Triggers on phrases like "document this decision", "create ADR", "architecture decision", "why did we choose", "record the decision", "MADR template", or when the user is working on plan files that contain ADR sections.
This skill should be used when writing requirements, specifications, or user stories. Triggers on phrases like "write requirements", "create spec", "define user stories", "document feature", "specify behavior", "what should the system do", or when reviewing specification quality. Provides patterns for clear, testable, unambiguous requirements.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Has parse errors
Some configuration could not be fully parsed
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 speckit-generatorTransform 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
Walk through the NASA Phase A concept development lifecycle: ideation, problem definition, black-box architecture, drill-down with gap analysis, and document generation. Produces concept documents and solution landscape summaries with cited research. Includes 7 specialized agents (ideation, problem analysis, architecture, domain research, gap analysis, skeptic verification, document writing), 6 scripts (session management, source/assumption tracking, web research with crawl4ai), 9 commands, hooks for automatic state updates, and tiered research tool detection. Use when developing a concept, exploring a new idea, brainstorming a system concept, running Phase A, creating a concept document, or conducting feasibility studies.
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 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.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
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.