agent
Add an AI agent / chatbot / RAG backend on Convex with @convex-dev/agent (durable threads, messages, tools, vector search). TRIGGER when the user wants an AI…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,657 results
labs-quickstart
LABS — scaffold a running Next.js + shadcn Convex app with passkey sign-in and a live Chef feedback panel, then build and verify it locally. TRIGGER for the…
castmate
When you want to pull in the right AI model for the right job: hand a task to another agent CLI (Codex, Claude, Gemini, Amp, OpenCode, Cursor, Kiro,…
loom-orchestration
Load before spawning subagents or running a loom stage as its main agent; skip for single-agent work. Delegation cost, briefs, waits, commits.
loom-skills
Loads a catalogued loom domain skill on demand; the argument is the full skill name, e.g. loom-rust, or omit it to browse the catalog table below.
creativeclaw-chatterbox
Create a one-off Chatterbox voice match from consented reference audio, with safe reference handling and model-specific expressive controls. Use after a…
creativeclaw-xai-tts
Apply xAI TTS voice casting, expressive speech-tag prompting, multilingual delivery, and telephony output after Creative Claw selects speech/xai-tts. Use when…
ai-brag-document
Engineering brag document
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…
iterate
Agent-to-agent pass loop — iterative blind review subagent passes until a bounded code or plan section holds together. Orchestrator for slice cohesion.…
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…
4-step-program
Coordinator workflow for orchestrating dockeragents through fix-review-iterate-present loop. Use when delegating any task that produces code changes. Ensures…
the-oracle
This skill should be used when the user asks to "use the oracle" or "ask the oracle" for deep research, analysis, or architectural questions. The oracle excels…
do-memory-mcp
Use and troubleshoot the Memory MCP server for episodic memory retrieval and pattern analysis. Use when working with MCP server tools, validating the MCP…
browse
Browser control with mode routing. /browse = auto-detect, /browse here = foreground (operate on the page user is looking at), /browse bg = background (CDP, no…
humanize-korean
Polishes Korean text written by AI (ChatGPT·Claude·Gemini) so it reads like human writing. It detects and classifies 40+ AI-tell patterns across 10 major categories—translationese, excessive English quotation, mechanical parallelism, idioms, overuse of passive voice, overuse of conjunctions, uniform rhythm, excessive emoji/bullets, etc.—and without touching a single character of the content…
oh-my-wiki
Installation guide for the Karpathy-style LLM wiki skill oh-my-wiki (omw). It ingests sources to build a structured wiki, and queries it with answers that carry citations. Multi-vault sqlite registry, memo vault, autoresearch,…
ai-ops-daily-summary
Generate a concise leadership-facing AI operations daily summary and business-value analysis from DaoCloud Enterprise DCE / LLM Studio / Hydra data. Use when…
llm-gross-margin-attribution
Attribute why LLM gross margin got worse using live DCE and Crane data. Use when the user asks whether today's/this week's LLM gross margin decline is caused…
dd-docs
Datadog docs lookup using docs.datadoghq.com/llms.txt and linked Markdown pages.
onnx_runtime
Runtime de inferencia ONNX optimizado para modelos faciales y de documento con aceleración CPU/GPU
doordash-order-ledger
Accountability layer for agent-driven DoorDash ordering. Works with the doordash-audit-log hook (which appends every dd-cli invocation to an append-only audit…
doordash-spend-guard
Hard spending policy for agent-driven DoorDash ordering through the DoorDash CLI (dd-cli). Per-order ceiling, daily/weekly/monthly caps, cooldown between…
rex-claude
Open other Claude Code sessions in Rex terminal panes or tabs and drive them: launch claude in a directory, answer the workspace trust dialog, send prompts,…