By irfansofyana
Foundational engineering tools for code review, diagram generation, technical documentation, and common development tasks
Use this agent PROACTIVELY when fetching official library documentation, API references, or code examples. MUST BE USED for tech libraries/frameworks, official docs, API references, or library suggestions for development tasks. Use web-research-specialist for debugging or community solutions.
Mermaid diagram specialist. Proactively creates and validates sequence, architecture, or flowchart diagrams using common-engineering:mermaid. Use when users request Mermaid or diagrams. MUST BE USED for diagram requests.
Technical documentation specialist for creating one-pagers, RFCs, TSDs, ADRs, POC/Experiment documents, and other engineering design documents. Routes directly to the appropriate focused skill based on document type. Guides users interactively through context gathering and generates polished documents. Proactively trigger when users mention writing docs, proposals, specs, design documents, or technical documentation.
Use this agent PROACTIVELY when users need comprehensive web research across any topic. MUST BE USED for debugging help, news/current events, business research, general web queries, or community solutions. Use librarian agent for official library documentation instead.
Pi-only web research workflow for environments that have pi-9router-ext and a subagent extension such as @tintinweb/pi-subagents configured. Use this skill when the user explicitly asks to use 9router, pi-9router-ext, ninerouter tools, or a 9router route/combo for web research, or when project/user instructions state that 9router-web-researcher is the preferred research stack. Do NOT use for ordinary web research in standard shared-mcp-only or non-Pi clients; use web-researcher instead. This skill always delegates research lanes to subagents and then synthesizes compact cited findings.
This skill should be used when the user asks to "write an ADR", "create an ADR", "document an architecture decision", "write an Architecture Decision Record", "document a technology choice", "compare database options", "document why we chose X over Y", or needs to record a specific architectural or technology decision with alternatives and trade-offs (1-3 pages). Use when capturing a decision that needs to be justified and preserved for future reference.
This skill should be used when the user asks to "review my code", "review this branch", "review my changes", "check my diff", "review before merge", "code review", or needs a structured code review analyzing correctness, security, reliability, maintainability, and scalability of git diff changes against a base branch. Use this proactively whenever the user is working on a feature branch and mentions wanting feedback on their changes before merging or opening a PR.
Create validated Mermaid diagrams (sequence, architecture, flowchart) with automatic syntax checking and self-healing. Use when users request diagrams, visualizations of API flows, system architecture, or process documentation. All diagrams are validated with mermaid-cli before delivery.
This skill should be used when the user asks to "write a one-pager", "create a one-pager proposal", "draft a one-pager", "write a proposal doc", "create a feature proposal", "write a proposal for sign-off", or needs a concise stakeholder approval document (1-3 pages). Produces focused proposal documents with problem statement, goal, proposed solution, alternatives, and risks.
Requires secrets
Needs API keys or credentials to function
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 skill-first repository for reusable agent workflows, packaged for multiple agent runtimes and installable from Codex via npx skills.
This repository serves as a marketplace for reusable agent workflows across agent runtimes. Claude Code packaging is still supported, but the canonical workflows live in plugins/*/skills/*.
| Plugin | Description | Requirements |
|---|---|---|
| shared-mcp | INSTALL FIRST - MCP infrastructure for web search (Brave, Tavily, Exa) | Node.js, BRAVE_API_KEY, TAVILY_API_KEY, EXA_API_KEY |
| p-assist | Productivity: expenses, RSS, VPS | shared-mcp, N8N_API_TOKEN |
| common-engineering | Engineering tools: code review, Mermaid diagrams, tech docs (RFCs, proposals, ADRs), web research | shared-mcp, optional pi-9router-ext + @tintinweb/pi-subagents, mermaid-cli, CONTEXT7_API_KEY |
| sys-maint | System maintenance: Docker cleanup, disk analysis | macOS only |
| thinking-tools | Thinking tools: pressure-test ideas (idea-refinery) and resolve decision branches (decision-sparring) | None |
| softskills | Office politics coach for navigating workplace dynamics | None |
See individual plugin READMEs for detailed setup instructions.
Skills are model-invoked capabilities that agent runtimes can activate when triggered by natural language. They are organized by plugin:
| Skill | Trigger Phrases | Output |
|---|---|---|
code-review | "review my code", "review this branch", "check my diff" | Structured review report with severity-classified findings |
mermaid | "create a diagram", "draw architecture", "sequence diagram for..." | Validated Mermaid diagrams (sequence, architecture, flowchart) |
one-pager | "write a one-pager", "create a proposal", "draft a one-pager" | 1-3 page stakeholder approval document |
adr | "write an ADR", "document architecture decision", "compare X vs Y" | 1-3 page Architecture Decision Record |
rfc | "write an RFC", "design proposal for cross-team review" | 5-15 page Request for Comments |
tsd | "write a TSD", "document an API", "API spec" | 5-20 page Technical Specification Document |
poc-experiment | "write a POC document", "Go/No-Go recommendation" | 3-8 page proof of concept with decision |
project-management-plan | "project plan excel", "Gantt chart", "project tracker" | Excel workbook with 4 tabs (plan, charters, budget, RAID) |
web-researcher | "search the web", "find online", "research", "look up", "debug error", "latest news about", "investigate company" | Findings with inline citations, recommendations, and source links. Routes via Brave (discovery) → Tavily (extraction) → Exa (semantic/technical) |
9router-web-researcher | explicit 9router/Pi research requests, or projects where 9router is configured as the preferred research stack | Parallel subagent research with 9router-first search/fetch, direct-tool fallback inside subagents, inline citations, and research coverage. Requires Pi with pi-9router-ext and @tintinweb/pi-subagents; use web-researcher for ordinary shared-mcp web research |
| Skill | Trigger Phrases | Output |
|---|---|---|
idea-refinery | "pressure-test my idea", "sparring partner", "gut-check this idea", "is this worth doing" | Concise Idea Brief with problem, MVP, risks, next actions |
decision-sparring | "decision sparring", "spar with this decision", "interrogate my idea/plan", "stress-test this", "drill into this", "poke holes in it", "help me think through whether to pursue this" | Decision Summary — every branch resolved, whether viability or execution |
| Skill | Trigger Phrases | Output |
|---|---|---|
office-politics-coach | "office politics", "navigate this situation", "difficult coworker" | Reframe, options, and word-for-word scripts for workplace dynamics |
/plugin marketplace add https://github.com/irfansofyana/ai-marketplace
Add to ~/.zshrc (macOS) or ~/.bashrc (Linux):
export TAVILY_API_KEY="your-tavily-api-key" # https://tavily.com
export EXA_API_KEY="your-exa-api-key" # https://exa.ai
export N8N_API_TOKEN="your-n8n-token" # https://n8n.io (for p-assist)
Reload: source ~/.zshrc or source ~/.bashrc
npx claudepluginhub irfansofyana/ai-marketplace --plugin common-engineeringSystem maintenance and cleanup utilities for Docker, disk space, and developer environments
Shared MCP infrastructure providing common web search, content extraction, and research tools for other plugins
⚠️ FOR PERSONAL USE ONLY - Productivity plugin for expense tracking, RSS feeds, and VPS management
On-demand coaching for navigating life with AI
Thinking tools for pressure-testing ideas, exploring assumptions, and sharpening decisions
Cross-cutting utilities: technical writing, git workflow, code review, pair programming, on-call runbooks, incident response.
Generate architecture diagrams and technical design documents
Engineering & tech skills: Code Review Checklist, Incident Postmortem, API Docs Writer, Architecture Decision Record, Debugging Log Analyser, PR Description Writer, System Design Interview, Changelog Generator, Test Strategy Doc, Runbook Writer, CI/CD Playbook, SLO & Error Budget, Developer Onboarding Doc, On-Call Runbook, Security Threat Model, Performance Budget, Database Schema Design, Database Migration Plan, Technical Debt Register, RFC Writer, Capacity Planning, Load Testing Plan, Disaster Recovery Plan, Feature Flag Guide, Dependency Audit, Service Catalog Entry, Monitoring Setup Guide, Local Dev Setup, API Versioning Strategy, Infra-as-Code Review, Engineering Weekly Report, Tech Radar, Sprint Velocity Analysis, Microservices Decomposition, Engineering Hiring Rubric. 35 structured skills for engineering teams, SREs, and technical PMs.
Core knowledge management, documentation generation, and strategic analysis for Claude Code
Spec-driven development workflow system with structured phases: Requirements → Design → Tasks → Implementation
Personal Claude Code plugin for dwmkerr with repo management and custom workflows