multi-host-live-mount
Use when one Relayfile workspace must be mounted on several machines and an agent placed on a remote host inside the live tree without cloning. Covers joining…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,666 results
review-fix-signoff-loop
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically…
subscribing-relay-webhooks-and-writebacks
Subscribe a running Codex or Claude session to inbound provider events (a GitHub pull request, a Slack channel) so they are injected into the session, and…
workspace-layout
Use when an agent is exploring a relayfile mount for the first time or trying to locate a specific resource (Notion page, Linear issue, Slack channel, GitHub…
writeback-as-files
Use when an agent needs to write back to a provider through a relayfile mount (Linear comments, GitHub issues, Slack messages, Notion pages, etc.). Covers the…
choosing-swarm-patterns
Use when coordinating multiple AI agents and need to pick the right orchestration pattern - covers 10 patterns (fan-out, pipeline, hub-spoke, consensus, mesh,…
agnt-prune
Prune AGENTS.md / CLAUDE.md down to only sharp edges and gotchas by removing everything inferable from the codebase.
bootstrap-mcp-oauth
Overlay OAuth 2.1 + PKCE on a Phoenix ExMCP 1.1 server (account-scoped resource, RFC 9728 metadata, DCR, consent, token-resource binding). Use when the user…
ai-skills
Best practices for designing, writing, testing, and packaging AI skills (SKILL.md-based). Use when creating new skills, reviewing or updating existing skills,…
agent-guardrails
General agent safety and workflow guardrails that prevent high-impact mistakes across tooling, verification, versions, integration layers, environment/config,…
paddleocr-doc-parsing
Use the native DeepSeek Harness PaddleOCR tool to parse document layout and Markdown.
creative-production-offer-explorer
Use when a product, digital product, service, venue, experience, or campaign brief needs 25-family offer-led prompt exploration, contact sheets, review…
protocol-standardization
Standardize fragmented experimental steps into reproducible protocol documents when you need method organization, lab SOP drafting, or cross-operator…
customize
Use when the user wants to create or manage a Specialist agent or create, revise, publish, or delete a Skill through the conversational `/Customize` entry.…
self-awareness
Inspect Open-Science's JavaScript control REPL, discover managed Project files, Sessions, and Agent Frames, and safely feature-gate host.* calls with…
skill-creator
Create, revise, evaluate, publish, and improve Open-Science Skills through the native JavaScript host.skills composer. Use when the user wants a reusable…
agent-memory
Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss…
audio-transcriber
Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration
canton-network-repos
Canton Network open-source ecosystem guide covering DAML SDK, Canton runtime, and Splice applications. Use when working with Canton Network, DAML smart…
decision-mapping
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
ui-ux-polish
Iterative UI/UX polishing workflow for web applications. The exact prompt and methodology for achieving Stripe-level visual polish through multiple passes.
when-gathering-requirements-use-interactive-planner
Use Claude Code's AskUserQuestion tool to gather comprehensive requirements through structured multi-select questions.
aiz-infographic
An infographic skill for AI agents — works inside Claude Code, Codex, Hermes, OpenClaw, Cursor, and any agent host that loads skills. Create professional…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…