tech-divergence
Evaluate technical options with scoring matrix, trigger Gate 4 for significant decisions
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-07 00:13
Agents & models
25,860 results
bioagents-guide
AI scientist framework for autonomous biological research workflows
llm-from-scratch-guide
Build a ChatGPT-like LLM from scratch using PyTorch step by step
mle-agent-guide
Intelligent companion for ML engineering with arXiv integration
transformer-architecture-guide
Guide to Transformer architectures for NLP and computer vision
unity-mcp
Expert guide for MCP for Unity tools. Resource-first workflow, domain-organized reference, and practical patterns for Unity automation through MCP.
replit-claude-code-prompting
Transforms vague coding requests into optimized Claude Code prompts for Replit projects. Use when helping users craft better prompts for Claude Code, improving…
agent-gen-audio
Give agents music and sound effect generation abilities using `rawgenai` — create music from prompts or lyrics, and generate sound effects from text…
agent-speak
Give agents voice abilities using `rawgenai` — text-to-speech, multi-speaker dialogue, and voice management (design, clone, create voices). Use this skill when…
estack
Entry point for eStack, the AI operator stack from explainx.ai. Reads the task and routes it to the right eStack skill (explain, quiz-me, catch-up, pick-model,…
glif-workflow-builder
Design and build Glif AI workflows. Use when creating new glifs, planning workflow structure, or understanding block types.
llm-wiki
Maintain a persistent research knowledge base at ~/wiki/llm-wiki using Karpathy's LLM Wiki pattern — interlinked markdown files for AI/LLM research,…
workos-migrate-stytch
Migrate to WorkOS from Stytch.
product-manager-skill
Turn analytics and customer signals into prioritized product decisions, PRD drafts, experiment plans, and implementation-ready GitHub backlog issues.
codex-canvas
Install, update, and use Codex-Canvas. After obtaining this Skill through Red SkillHub or another Skill channel, continue by installing the latest stable version of Codex-Canvas as a Codex personal plugin; installing the Skill is not the end state. Applies when the user requests to install or upgrade codex-canvas, enter…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
claude-agent-sdk
Build autonomous AI agents with Claude Agent SDK. TypeScript v0.2.141 | Python v0.2.82. Covers: query(), hooks, subagents, MCP, permissions,…
tech-hub-mcp
MCP Manager for Model Context Protocol server lifecycle, token optimization, and context-efficient external data access. Use this skill to activate MCP servers…
smalltv-mcp-tools
This skill should be used when the SmallTV Local MCP server tools are available and the user asks to "control SmallTV", "read SmallTV status", "upload image to…
agent-orchestrate
Analyze the user's task and propose the optimal orchestration pattern, then execute it. 4 patterns: Sequential Pipeline, Parallel Subagent, Team Mode, Ralph…
agent-usage-analyzer
Analyze local AI-agent session histories and report usage counts for agent skills, tools, commands, or MCP actions across sessions. Use for requests about…
mcp-cli
Comprehensive MCP server verification and debugging with mcp-cli. Use when Codex needs to configure MCP servers, inspect tool schemas, run end-to-end tool…
audit-agentic-mcp
Use skill if you are auditing an existing MCP server for agent-readiness, designing a new MCP server before any code, or deciding framework, security, and…
audit-skill-by-derailment
Use skill if you are testing or hardening an existing SKILL.md by running a fresh subagent on a real task and editing the skill where the trace shows friction.