ingest
Ingest source material into an LLM Wiki vault. Use whenever the user invokes `/ingest`, asks to turn documents, notes, chats, or URLs into durable wiki…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,665 results
lint
Audit and safely maintain an LLM Wiki vault. Use whenever the user invokes `/lint`, asks to check wiki quality or health, or asks to find and optionally repair…
watercooler
Where agents meet and talk. Send messages, findings, reviews, and work handoffs between Claude Code and Codex; request one reply or establish a persistent…
voicebox
Voicebox voice I/O: when to speak aloud, pick voices, recall dictated Captures via MCP.
docs
Execute the Claude Code Docs helper script at ~/.claude-code-docs/claude-docs-helper.sh
keepass
The English introduction is being prepared.
conventions
Code style, naming, and workflow preferences for agents in the Surge codebase.
jh-create-skill
Guides users through creating effective Agent Skills for Cursor. Use when you want to create, write, or author a new skill, or asks about skill structure, best…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
tinyworld-mesh-terrain
Use when changing the Mesh Terrain sculptor — the opt-in voxel-block landscape designer that paints per-voxel materials and pull/push-sculpts flat-topped…
using-personal-os
Use when starting a Personal OS or life-vault agent session — loads the secretary stance and routes to the matching personal skill before any vault write.
create-spec
Turn a settled shared understanding into a spec an agent implements unattended, with ordered AFK and HITL sub-issues when the work needs them.
link-skills
Symlink one or more skills in skills/ into every agent skills directory in this repo.
setup-project-context
One-time bootstrap of this repo's agent context — CONTRIBUTING.md, a /project-context router skill, and one reference file per domain — drafted from the code…
unslop
Cut AI tells from a piece of writing. Use when the user asks to unslop, de-AI, or humanize text, or before shipping prose longer than a paragraph.
alchemy-core-workflow-b
Build an NFT discovery workflow with Alchemy NFT API v3 and isolate typed on-chain reads through viem. Use when creating collection explorers or ownership…
castai-common-errors
Diagnose CAST AI connection, agent, node autoscaling, and workload autoscaling failures without making speculative changes. Use when a cluster is disconnected,…
clade-prod-checklist
Production readiness checklist for Claude-powered applications — Use when working with prod-checklist patterns. error handling, monitoring, fallbacks, cost…
cohere-hello-world
Run bounded Cohere v2 Chat, Embed, or Rerank requests with current model discovery and explicit validation. Use when proving a new Cohere setup. Trigger with…
langchain-deep-agents
Build a LangGraph 1.0 Deep Agent — planner + subagents + virtual filesystem + reflection loop — without the state-growth and prompt-inheritance traps. Use when…
mistral-hello-world
Validate one minimal Mistral chat request with pinned inputs, usage evidence, and zero sensitive data. Use when proving a new integration path. Trigger with…
openrouter-function-calling
Implement function/tool calling with OpenRouter models. Use when building agents, structured output, or tool-augmented LLM workflows. Triggers: 'openrouter…
prompt-improver
Analyze and improve plugin prompts, skill definitions, and command instructions for clarity, safety, and effectiveness. Use when the user asks to "improve a…
retellai-hello-world
Retell AI hello world — AI voice agent and phone call automation. Use when working with Retell AI for voice agents, phone calls, or telephony. Trigger with…