test-coverage-analyzer
Find the gaps between what was required and what was actually tested. Use when a lead says "where are our coverage gaps", "what isn't tested", or wants…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-07 00:13
Agents & models
25,827 results
godmode
Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.
skill-generator
Meta-skill for creating new Claude Code skills with configurable execution modes. Supports sequential (fixed order) and autonomous (stateless) phase patterns.…
ai-gateway
Two primitives of the Nutrient AI Gateway. Chat models (`nutrient-s`/`nutrient-m`/`nutrient-l` via `POST /responses` or `POST /chat/completions`) are…
dapp-composer
This skill should be used when the user asks about on-chain earning opportunities, 'how to make money on-chain', 'any profitable strategies', 'arbitrage…
dapp-hyperliquid
This skill should be used when the user asks about Hyperliquid, perpetual futures, 'open a long position', 'short BTC', 'check my perp positions', 'funding…
dapp-polymarket
This skill should be used when the user asks about prediction markets, event betting, 'what are the odds of...', 'bet on...', 'buy Yes/No shares', 'Polymarket…
pushary-hermes
Push notifications and human-in-the-loop for Hermes Agent. Use this whenever a running agent needs a human and no chat session is active, such as before an…
instrumenting-pydantic-ai
Set up observability for Pydantic AI, so every model request and tool call is visible with its cost and latency. Use when the user asks to instrument, trace,…
dlab-cli
Complete reference for decision-lab (dlab). Use when the user asks about creating decision-packs, designing data science agents, running sessions, analyzing…
prompt-enhancement-skill
Creates, critiques, repairs, and adapts prompts for AI tools. Use when the user asks to write or improve a prompt, convert requirements into instructions for…
interview-harness
Run Socrates, Evolve-step, and Ontology as a semi-automatic convergence loop. If a complete Seed already exists, skip Socrates. Iterate evolve-step and…
ontology
Add a semantic boundary layer on top of a closed Seed. Use Seed.goal as idea, ask for boundary and exactly three properties, and replace the top-level ##…
restate
Restate the shared meaning from Refine as one executable goal sentence. In the Socrates loop, Restate writes only the current cycle's ### Restate…
socrates
Run Wonder, Reflect, Refine, and Restate as a Ralph-style loop to turn one vague request into a closed Seed with goal, constraints, and acceptance_criteria.…
discuss
Use when the user explicitly invokes $discuss, needs to save the discussion state to the current repository, and continue the discussion across sessions, tools, or agents.
qoder-cloud-agents-cn
Run and manage Qoder Cloud Agents CN tasks, conversations and schedules from third-party agents. Use available QCA MCP tools or the HTTP API.
hire_team
Scaffold a bilingual Scout/Writer/Producer OpenClaw team when the user asks to hire a team, create a multi-agent content pipeline, build Scout Writer Producer…
openai-ai-integration
Use when integrating an OpenAI-compatible LLM API into an app, CLI, tool, or service: choosing the SDK, shaping chat-completion requests, configuring base…
opencode-memory
Give an OpenCode setup long-term memory and a learning loop, following Anthropic's context-engineering practice. Puts the global config under git, slims the…
finish-setup
Finish provisioning a freshly scaffolded SaaS project using the MCP servers wired by agent.json (Neon, Stripe, Resend, PostHog, GitHub). Verifies env vars,…
t3-fork
Fork, branch, or duplicate a T3 Code conversation into a new thread that keeps the full context, with an option to keep only the first or last N turns, or hand…
skill-creation-walkthrough
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference…
advanced-evaluation
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or…