context-compactor
Automatic context summarization for long-running sessions. Use when context is approaching limits, summarizing completed work, preserving critical information,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-27 00:15
Agents & models
24,900 results
ag2-acp
Drive external CLI coding agents (Claude Code, Codex, OpenCode) as first-class AG2 Agents over the Agent Client Protocol (ACP): point an Agent at a…
agent-telegram
Interact with Telegram through TDLib - authenticate, inspect chats, and send messages
agently-knowledge-base
Use when the user wants embeddings, vector indexing, retrieval, or retrieval-backed answers, including embedding-agent setup, Chroma-backed collections,…
agently-migration-playbook
Use when the user wants to migrate an existing LangChain or LangGraph system and the first decision is whether the source problem is agent-side or…
agently-model-response
Use when the user wants to reuse one model result, read text/data/meta without re-requesting, or stream partial updates, including `get_response()`, async…
agently-session-memory
Use when the user needs conversation continuity, memo, or restore-after-restart behavior for a request family, including session ids, chat history,…
goalflow
Route goalflow (wanmol/goal-flow) work — a LangGraph framework that combines workflow graphs with agent loops — into exactly one mode: fit check, transpiling a…
prompt-governance
Use when managing prompts in production at scale: versioning prompts, running A/B tests on prompts, building prompt registries, preventing prompt regressions,…
committee
Multi-model investment committee. Use this skill when the user says "hold a meeting", "investment committee", "multi-model analysis", or "let the three models take a look together".
agent-chat
Agent-to-agent messaging. Use when you see [Agent Chat] messages, need to send/reply to handles (@personal,
academic
Academic writing multi-agent orchestrator. TRIGGER when: user is editing .tex files, reviewing thesis/paper chapters, drafting academic content, checking…
config-guide
Reference guide for configuring @Claude agents — agents, agent scopes, identity profiles, presets, connections, rules, GitHub repositories, and custom…
workshop
Workshop coach for the Research Desk (SEC agents) workshop. Use when the user types /workshop, asks for a workshop act or module ("act 2", "next act", "where…
cs-chatbot-design
Design conversational AI chatbots including intent recognition, slot filling, dialogue flow, and response generation. Use this skill when the user needs to…
upskill
A live, growing registry of agent skills published by Anthropic, OpenAI, Vercel, Microsoft, Cloudflare, Stripe, HashiCorp, Supabase, and many others. Search it…
blink-storage
File upload with progress tracking and public URLs. Download, remove files. CLI for management. Extension auto-detection.
gds-create-story
Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story…
craft-goal
Draft or lint a bounded long-running goal prompt with a finish line and hard limits. Use when: selected by name; one change goes to Plan.
dream
Retired pointer — out-of-session compounding moved to the substrate (NTM + MCP + managed-agents).
bstack
bstack — the Broomva Stack. Twenty irreducible primitives (P1-P20) plus 30 curated skills that turn an agent-driven workspace into a self-operating system.…
browser-use
Always use browser-use for any web interaction: automation, scraping, testing, or site/app work.
boss-agent-cli
BOSS Zhipin job search CLI for AI agents — 32 commands covering search with welfare filtering, greet, apply, pipeline tracking, resume AI…
team-lifecycle
Full lifecycle orchestrator - spec/impl/test. Spawn-wait-close pipeline with inline discuss subagent, shared explore cache, fast-advance, and consensus…