miracle-infrastructure

Dynamic expert team assembly for planning. Selects 3-5 real-world expert personas tailored to the task, runs parallel analysis, facilitates a debate round on key contradictions, then synthesizes into a plan with explicit tradeoffs. Use when: (1) planning a new feature or project, (2) user says "/dream-team", "assemble a dream team", "pick experts for X", (3) need diverse perspectives before committing to an approach.

Use when you need to validate the health of your Claude Code skills library. Checks for broken file references, missing dependencies, frontmatter issues, duplicate triggers, and dependency drift. Runs structural and semantic audits across all installed skills. Invoke via '/checkup', '/review-skills', or 'check my skills'.

Virtual board of directors. Five expert lenses evaluate a project in parallel (Murati, Sutskever, Cherny, Karpathy, Ive), each through their unique lens. Use when: (1) evaluating a project idea or architecture, (2) user says "/directors", "call the board", "what would directors say about X", (3) need multi-perspective review of a decision or strategy.

Accumulates knowledge from solved problems. Activates automatically after web search or MCP tools are used to solve technical problems. Also activates during debugging to check the knowledge base first. Invoke explicitly via "/til" to record a lesson manually. Triggers: "/til", "record a lesson", "what lessons do we have".

Security review with two modes: (1) code review — 5 parallel agents scan for OWASP Top 10, secrets leaks, auth issues, dependency risks, logic flaws; (2) enterprise assessment — 4 agents evaluate product through CISO lens (data handling, access control, compliance, resilience). Threat model calibration adjusts severity to deployment context. Use when: (1) Before deploy — security audit, (2) Enterprise sales — readiness assessment, (3) New project — baseline security posture, (4) After major changes — regression check. Triggers: "/security review", "/security assess", "/security", "security check".

Agent orchestrator. Analyzes tasks and launches 2-4 specialized agents in parallel, then synthesizes results. 12 agents built from analysis of real usage patterns. Use when: (1) user says "/orchestrate", "run orchestrator", (2) task benefits from parallel analysis by multiple specialists, (3) complex task needs research + implementation or analysis + verification simultaneously.

Verifies information through multiple independent sources with transparent confidence scoring. Classifies claim type (fact/opinion/prediction), shows where confidence comes from, flags bias. Use when: (1) "Verify this", (2) "Triangulate", (3) "Confirm from different sources". Triggers: "/triangulate", "verify this", "triangulate", "confirm from multiple sources".

Transforms client call transcripts into commercial proposals with system architecture and clickable HTML prototypes. Use when: (1) User has a transcript from a client call/meeting, (2) User wants to create a proposal or quote, (3) User needs to map client pains to product features, (4) User asks for a prototype based on a conversation. Triggers: "/proposal", "transcript", "proposal", "client call", "commercial offer", "prototype from conversation".

Saves session context to project memory. Run at end of work or when switching projects. Use when: (1) Ending a work session, (2) Switching projects, (3) Before a long break. Triggers: "/session-save", "save session", "remember context".

Search project memory: observations, decisions, problems. Query by type, file, concept, date. Use when: (1) "What decisions did we make about auth?", (2) "All bugs in project X", (3) "What do we know about caching?", (4) "Open problems across all projects". Triggers: "/search-memory", "search memory", "what do we know about".

Researches questions using web search and generates reports with confidence scores and sources. Use when: (1) User asks a question requiring current information, (2) User says "find out about X", (3) User gives URL to extract data from, (4) Question about code/API/library, (5) Comparing options. Triggers: "/research", "find out about", "research this".

Quick project status in 30 seconds: dossier from memory + live data from git/GitHub. Use when: (1) "Give me project status", (2) GitHub URL + "status/commits/what's left", (3) "When was the last deploy", (4) "What broke", (5) "What's left to do". Triggers: "/project-status", "project status", "what's left", "latest commits".

Adaptive deep interview that extracts what you need but can't articulate, then acts on it. Use when: (1) User is stuck and can't formulate what they want, (2) User says "I don't know", (3) User gives contradictory requirements, (4) User keeps changing direction, (5) Brainstorm feels unfocused. Triggers: "/unstuck", "I'm stuck", "I don't know what to do", "I can't decide", "help me figure this out", "I can't formulate what I need".

First-run setup wizard for the memory system. Creates directory structure, config, and starter files. Use when: (1) First time using Miracle Infrastructure, (2) "Initialize memory", (3) Setting up on new machine. Triggers: "/memory-init", "initialize memory", "setup memory".

Validates memory system integrity: file consistency, observation counts, format correctness. Use when: (1) Suspecting data desync, (2) After bulk edits, (3) Periodic health check. Triggers: "/memory-health", "check memory", "memory health check".

Library of 50 engineering, product, design, and thinking frameworks organized by project stage. Determines stage, activates the right set, delivers specific recommendations with conflict resolution. Use when: (1) user says "/frameworks", "run through frameworks", "which principles apply here", (2) evaluating a project against engineering best practices, (3) need structured analysis by project stage.

Weekly development review through the AQAL integral model. Evaluates progress across 4 quadrants (I/WE/IT/ITS) and 5 development lines. Use when: (1) it is Friday and user wants a weekly review, (2) user says "/aqal-review", (3) user wants to assess progress holistically across personal and professional dimensions.

Extracts tasks, commitments, and deadlines from transcripts, chats, and documents. Use when: (1) Audio transcript + "what needs to be done", (2) Chat export + "tasks for the meeting", (3) Multiple files for batch processing, (4) Any text that needs action items extracted. Triggers: "/action-items", "what needs to be done", "action items", "extract tasks".