Generate concise CLAUDE.md files and agent documentation following best practices. Use when setting up a new project for Claude Code, auditing existing CLAUDE.md, or creating progressive disclosure documentation structure.
Claude Code-optimized context transfer for development workflows. Preserves code context, git state, running services, and development environment when moving work between sessions. Works seamlessly with peer review skills (Codex/Gemini). Use when transferring development work to a new Claude Code session.
Manage PR review feedback loops with Gemini Code Assist. Use when pushing changes to a PR, iterating on review feedback, or monitoring CI/review status. Automatically falls back to Claude when Gemini is rate-limited.
[CLAUDE CODE ONLY] Leverage Codex CLI for AI peer review, second opinions on architecture and design decisions, cross-validation of implementations, security analysis, and alternative approach generation. Requires terminal access to execute Codex CLI commands. Use when making high-stakes decisions, reviewing complex architecture, or when explicitly requested for a second AI perspective. Must be explicitly invoked using skill syntax.
FAST code generation via Z.ai glm-4.6 model. Use for rapid test generation, boilerplate code, repetitive patterns, and bulk file creation. Ideal when speed matters more than nuance. Do NOT use for complex architectural decisions or security-critical code.
Persistent memory for AI coding agents. USE WHEN user says "save context", "remember this", "checkpoint", "resume session", "prepare for compaction", "wrap up", OR when starting work on a project that may span sessions.
High-fidelity context transfer protocol for moving conversations between AI agents. Preserves decision tempo, open loops, and critical context with graceful degradation. Use when the user says "transfer," "handoff," "continue this in another chat," or needs to work around context window limits. Produces structured artifacts (Minimal ~200 words, Full ~1000 words). DO NOT trigger on simple "summarize our conversation" requests—only when transfer intent is explicit.
Organizational learning from CFN Loop execution - workflow codification and playbooks. Use when you need to store successful patterns, query past learnings, track edge cases and failures, or retrieve agent configurations and iteration strategies from previous tasks.
Hybrid AISP epic creation with formal API contracts and natural language user content. Uses AISP (AI Symbolic Protocol) for type definitions and agent binding contracts while preserving human-readable descriptions.
Extract and structure claims from discourse into analyzable argument maps with logical relationships and assumptions. Use when analyzing arguments, red-teaming reasoning, synthesizing debates, or transforming conversations into structured claim networks. Triggers include "what are the claims," "analyze this argument," "map the logic," or "find contradictions."
Review technical recommendations before presenting them to the user. Use BEFORE suggesting config changes, optimizations, refactors, or architecture decisions. Spawns a subagent to challenge assumptions and filter out generic advice that doesn't apply to the user's context.
Personal intelligence system for capturing thoughts, managing knowledge, and surfacing insights. Use when user wants to capture an idea, task, or note during conversation; query their knowledge base; check their inbox; review digests; or update task status. Triggers include "remember this," "add a task," "what did I say about," "show my inbox," or "mark complete."
Autonomous agent-based web search fallback for when WebSearch API fails or hits limits
CLI tools for Are.na: export blocks, enrich with vision AI, generate views. Use when: (1) exporting Are.na blocks incrementally, (2) enriching images with AI-generated titles/tags/patterns, (3) generating browsable HTML views, (4) searching blocks by UI patterns or tags, (5) visual search results when terminal output is insufficient. Triggers: "export arena", "enrich arena", "sync arena", "arena view", "search arena for [pattern]", "show me [pattern]".
Unified agent management from selection through completion - spawning, execution, output processing. Use when selecting agents for tasks, spawning agents with dependency validation, processing agent outputs, or tracking agent lifecycle events with audit trails.
Build psychometrically accurate personal proxy agents for the PAIRL Conductor system. Extracts personality, decision heuristics, and values into portable schemas that enable AI agents to negotiate, filter, and act on a principal's behalf.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
[CLAUDE CODE ONLY] Leverage Gemini CLI for AI peer review, second opinions on architecture and design decisions, cross-validation of implementations, security analysis, alternative approaches, and holistic codebase analysis. Requires terminal access to execute Gemini CLI commands. Use when making high-stakes decisions, reviewing complex architecture, analyzing large codebases (1M token context window), or when explicitly requested for a second AI perspective. Must be explicitly invoked using skill syntax.
