webmcp-gen
Build and validate experimental WebMCP tools for an existing web page. Use when an agent needs to expose a site's real workflows as page tools, create…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-28 00:17
Agents & models
24,991 results
openviking-skills
Find, use, create, install, share, update, and migrate agent skills stored in OpenViking (viking://~/skills and viking://agent/skills). Use it when a search…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM…
neo-team-claude
Claude Code variant. Orchestrate a specialized software development agent team. Receive user requests, classify task type, select the matching workflow,…
workos-authkit-react
Integrate WorkOS AuthKit with React single-page applications. Client-side only authentication. Use when the project is a React SPA without Next.js or React…
antigravity-vision-proxy
Use when the current agent cannot directly view or analyze images, but frame inspection is needed for video analysis or visual context.
pragmatic-clean-code-reviewer
Strict code review following Clean Code, Clean Architecture, and The Pragmatic Programmer principles. Use when: (1) reviewing code or pull requests, (2)…
light-plan-and-work
Create a 3–7 step plan for a bounded task, execute immediately, verify, and hand it back. Use when the user explicitly requests a lightweight plan-and-work…
setup-agent-skills
Initialize or upgrade the Agent project knowledge infrastructure for a repository. Deploy the CONTEXT/RULE format, on-demand loading scripts, and project-level Hooks for the current host. Run before using the engineering Skill for the first time, or rerun when configuration is missing or drift needs to be checked after an upgrade.
thrifty-brief
Brief-writer subskill for thrifty's split planning mode. Expands ONE terse unit spec (from the architect/director) plus the shared contract into a full,…
thrifty-check
Checker subskill for thrifty. Verifies one completed unit against its acceptance criteria, attempts a surgical fix for small localized defects, and returns a…
thrifty-execute
Executor subskill for thrifty. ONE cached agent that builds an ordered list of units from their briefs in a single session — honoring the shared contract,…
thrifty-plan
Planning discipline for thrifty, run by the architect (Sonnet) itself. Decomposes a task into units, writes CONTRACT.md (cross-unit decisions + dependency…
bindcraft
End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running…
page-decomposition
Analyze content sequences within a section and provide neutral descriptions for AEM Edge Delivery Services. Invoked per section during page import to identify…
ai-infrastructure-litellm
LiteLLM proxy server setup, TypeScript client patterns via OpenAI SDK, model routing, fallbacks, load balancing, spend tracking, virtual keys, and production…
mcp-research
Use when tasks require current, source-backed technical information from MCP tools. Apply for library/API questions, dependency version checks, third-party…
hodlmm-arb-executor
Executes LP-based sBTC/STX arb on Bitflow HODLMM. Detects XYK vs DLMM price spread, enters via swap + add-liquidity-simple, exits on spread reversal or 2h…
maintain-model-list
Maintain the supported LLM model list: add a new model, or run routine maintenance to verify availability and discover new models worth adding. Use when the…
oh-my-opencode-slim
Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or…
cognitive-bias-detection
Apply cognitive bias detection whenever the user (or Claude itself) is making an evaluation, recommendation, or decision that could be silently distorted by…
handover
Create, install, inspect, and boot from local session handover files for AI agent continuity. Writes structured handover.md notes, keeps them private by…
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through…
agent-deck
Managing AI agent sessions via agent-deck CLI. Triggers (RU): "launch agent", "launch sub-agent", "create session", "check session", "check…