extract-agent-sessions
Recover, export, or summarize recent human and assistant conversations from local agent session stores while excluding tool calls, reasoning, system injection,…
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
agent-fathom
Search and read Fathom meeting recordings: transcripts, AI summaries, action items, highlights, attendees, CRM matches, meeting types, teams, and users. Also…
agent-mcp-host
One-origin MCP host for the agent-* CLI family: serve several family CLIs' MCP servers behind a single https origin (typically a Tailscale funnel) with one…
use-claude
For non-Claude agents (e.g. Codex) delegating to Claude Code headless mode: long-horizon bug fixing, implementation where first-pass completeness beats token…
a-share-strategy-allmarket-multi-swing-defensive
Within the A-share whole-market high-liquidity pool, generate buy candidates and position sell signals based on trend pullback (trend_pullback); additionally, realtime_quotes batch-fetches current price snapshots. For pre-order decision-making; does not run backtests and does not place orders automatically. Use when the user wants to select stocks, view real-time quotes, judge buy/sell signals, or check whether positions have triggered exit conditions.
create-project
Create a new project on the Karma protocol. Use when user says "create a project", "new project", "register project", or "start a project on Karma".
agent-qa-debug-fix
Debug, patch, and verify failed Agent QA runs from MCP evidence, artifacts, logs, and local code without hiding product or infrastructure defects.
aws-agentic-ai
Aws Agentic Ai
browser-act
Use BrowserAct for authenticated browser automation, JS-rendered extraction, screenshots, parallel sessions, verification handling, and human handoff.
llm-security
Authorized security assessment of LLM applications and AI agents: prompt injection, tool abuse, RAG exposure, memory poisoning, system-prompt extraction, and…
lookdev
Human-in-the-loop web studio to tune AI-generated output by eye. Stand up a local interactive studio (sliders, pickers, drag handles) or an inline…
odw
Dynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon. Use when the user asks for…
polis-protocol
Coordinate multi-vendor AI agents as a self-improving team — a learning router assigns work by track record and citizens can amend the protocol's own rules.
prompt-injection-defense
Defend AI systems against prompt injection and indirect prompt attacks using input controls, tool permissions, output validation, and isolation boundaries.
using-agent-skills
Meta-skill for discovering and invoking the right agent skill for the work at hand, applied at session start.
workorai
WorkorAI talent-marketplace skill: candidates search jobs and manage applications; employers run the job lifecycle and get ranked candidate matches with…
chao-rag-wiki
Use when building or querying a RAG knowledge base over the local raw/ document corpus using turbovec vector search. Triggers: 'build rag', 'rag query',…
fishjam-js-server-sdk
Node.js / TypeScript server SDK for Fishjam — backends that create rooms, mint peer tokens, listen to server notifications, and run agents. Use when writing a…
fishjam-platform
Fishjam platform fundamentals — domain model and auth shared by all SDKs. Covers glossary (room, peer, track, agent, streamer, viewer), the four room types…
fishjam-python-server-sdk
Python server SDK for Fishjam — backends that create rooms, mint peer tokens, receive server notifications, and run voice agents. Use when writing a Python…
fleet
Deep fleet census — discover all oracles across all nodes, collect versions, skills, status. Use when user says "fleet", "census", "all oracles", "fleet…
team-agents
Spin up coordinated agent teams for any task. Reusable framework for TeamCreate/SendMessage/TaskList patterns. Use when user says "team-agents", "spin up a…
pm-advisor-torres
Teresa Torres perspective advisor. Using Torres's Continuous Discovery method and decision-making approach, analyze product managers' user discovery, opportunity mapping, solution generation, and assumption validation issues. Distilled from "Continuous Discovery Habits" and Product Talk long-form articles, including 4 mental models, 7...
pm-advisory-board
Product Manager Expert Advisory Group master control. Members: Marty Cagan, Teresa Torres, Yu Jun (expert perspective) + 《The Mom Test》《User Story Mapping》《Escaping the Build Trap》(methodologies). Capabilities: (1) Automatically recommend suitable experts/methodologies based on the problem…