vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-11 00:16
Agents & models
26,088 results
writing-fragments
Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to…
kehwar-skills
Expert guidance for managing the kehwar skills repository including agent workflows, sync commands, and skills installation procedures. Use when working with…
agy-lead
Orchestrate an ongoing task with AGY while the current agent owns key decisions, review, and delivery. Use when the user invokes /agy-lead or asks you to…
agy-staffer
Delegate a general-purpose task to Google's Antigravity CLI (agy staffer, fast Gemini) with a minimal, unopinionated prompt. Use when the user says…
finance-cli
Drive the finance-cli (github.com/kelvin6365/finance-cli) — a local, offline, single-binary terminal finance tracker built for AI-agent use. Trigger when the…
drain-tickets
Drain ready-for-agent GitHub tickets via do-work subagents — parallel or sequential, one PR or PR-per-ticket.
setup-work-skills
Install the project-level do-work and do-seo-work delivery suite.
hooks-builder
Create and configure Cursor Agent Hooks to automate, observe, and control the agent loop. Use when setting up auto-formatters, security gates, audit logging,…
mcp-builder
Create high-quality MCP (Model Context Protocol) servers for LLM tool integration. Use when building MCP servers, integrating external APIs for AI agents, or…
parallel-agents
Run multiple AI agents in parallel using git worktrees and cloud agents. Use when working on multiple tasks simultaneously, comparing approaches across models,…
skill-creator
Guide for creating effective AI agent skills. Use when user wants to create, update, or improve a skill, or asks about SKILL.md format, skill structure, skill…
github-mcp
Set up project-level GitHub MCP when GitHub operations (PRs, issues, repo access) are needed and no project GitHub MCP is configured. Automatically triggers…
kernel-mcp
use KERNEL cloud browsers through the KERNEL mcp server. create stealth browser sessions, automate pages with playwright, the browser repl, or computer-use…
jev-compaction
Use when shrinking a conversation you already have — a handoff, a session summary, a compaction capsule. Jev marks each turn keep, summarize or drop; you write…
agentmail
Programmatic email for AI agents via AgentMail API. Create inboxes, send/receive messages, manage threads, webhooks, pods, and custom domains. Use when you…
state-trees
Create, inspect, and edit StateTree assets — states, tasks, transitions, conditions, considerations, and property bindings for AI behavior and game logic…
freesearch
Zero-token research using Argus search broker. Saves Claude tokens.
conducta
Run Khoa's engineering program from one long-lived thread. Tracks every work item in the ledger, dispatches each bounded step to a background worker, verifies…
lead
Run Khoa's engineering program from one long-lived thread. Tracks every work item in the ledger, dispatches each bounded step to a background worker, verifies…
mine
Mine recent OpenCode sessions for recurring corrections and repeated manual effort, then shortlist the strongest fixes to route to /correct, /adapt, or tooling.
automate-me
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the…
poteto-agent
Routing target for `/poteto-mode` and any request for poteto's style. Resume an existing `poteto-agent` for the conversation (`send_agent_prompt` to the agent…
principle-guard-the-context-window
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not…