smux-compozy-pairing
Orchestrates an interactive tmux-based pairing workflow where the current agent acts as an autonomous orchestrator, Codex authors the Compozy…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
adversarial-review
Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from…
cy-execute-task
Executes one PRD task end-to-end using a provided task file, PRD directory, tracking file paths, and auto-commit mode. Use when a prompt includes a task…
cy-final-verify
Enforces fresh verification evidence before any completion, fix, or passing claim, and before commits or PR creation. Use when an agent is about to report…
skill-best-practices
Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural…
eval-integrity
Audit an LLM evaluation or benchmark repo for integrity and credibility practices. Use when asked to "audit my benchmark," "is my eval trustworthy," "check my…
reconcile
Tripwire check for multi-session drift. Scans state files, recent commits, and file conflicts caused by parallel Claude Code sessions.
session-management
Structured session lifecycle for Claude Code — start, checkpoint, end, and daily heartbeat commands that maintain project state across conversations.
skill-creator
Generate a new Claude Code skill from a plain-language description — decides invocation control (disable-model-invocation vs user-invocable), arguments…
go-to-production
Pre-deploy checklist for CopilotKit v2 apps — persistent AgentRunner (not InMemory) behind horizontal scaling, CORS, showDevConsole off, debug off,…
scale-to-multi-agent
Upgrade a single-agent CopilotKit v2 app to multi-agent with per-panel useAgent({ agentId }), agent-scoped tools / renderers / context, key-remount when…
jordan-peterson-perspective
Jordan Peterson's (乔丹·彼得森, "Professor Lobster") thinking framework and mode of expression. Based on an in-depth investigation of 6 dimensions and 216 sources (about 48% primary sources), including his works, long interviews/debate transcripts, X posts, external criticism, decision records, and a complete timeline, this distills 6 core mental models, 8 decision heuristics, and a complete expression DNA, with built-in annotations of his externally verified failure modes. Purpose:…
setup
Discover your billing model and configure products, assets, and pricing in Credyt via MCP. Run this after /credyt:init. Can be run multiple times to add…
execution-tracking
Bootstrap, install, and operate an external task-management CLI as the source of truth for agent execution tracking (instead of built-in todos). Provides the…
governance
ALWAYS invoke this skill at the START of every session before doing any other work. This skill ensures the host project has agent governance rules (skill…
add-cursor-ambassador
Adds Cursor Directory ambassador badges by name or email via Supabase. Resolves the person and sets users.is_ambassador. Use when the user asks to add, grant,…
integrations-index
Comprehensive index of 82+ Dagster integrations organized by official tags.yml taxonomy including AI (OpenAI, Anthropic), ETL (dbt, Fivetran, Airbyte,…
nerd-context
Use when the installed Nerd hook activates persisted Context, the user invokes $nerd-context or /nerd-context, or Nerd Smart resumes an exact `context_id`…
agent-memory
Memória persistente da IA no projeto: lê e atualiza decisões, preferências e contexto em arquivos. Use sempre que o usuário pedir para lembrar, gravar decisão,…
prompting
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive…
mlflow-evaluation
MLflow 3 GenAI agent evaluation. Use when writing mlflow.genai.evaluate() code, creating @scorer functions, using built-in scorers (Guidelines, Correctness,…
workorai
WorkorAI talent marketplace skill: candidate job search and employer hiring with white-box match explanations via the WorkorAI MCP server…
nytid-todo
Manages work items via nytid todo subcommands as worker dan-claude. Relevant when the user asks to check, start, or complete tasks, view task details,…
worktree-subagents
Orchestrate parallel fix/implementation subagents in isolated git worktrees without them testing the wrong code or colliding. Use proactively when (1) spawning…