Loading...
Loading...
Found 6,591 Skills
Agent Session Visualization / Session Timeline: Execution maps for Cursor, Codex, Claude Code, Workbuddy, kimi-code threads (by ID or name); includes skills/tools/sub-agents, retries/forks/waits, layered internationalization + session health. Triggers (English): agent thread visualizer, agent-thread-visualizer, agent session timeline, session report, session log analyzer, agent flow visualization, execution map, conversation visualizer, subagent timeline, debug agent session, visualize the run, Cursor session, Claude Code session, Workbuddy session, kimi-code session. (Chinese): agent session visualization, session visualization, agent timeline, sub-agent visualization, session report, session analysis, execution map, agent execution flow, debug agent session, Cursor session, Claude Code session, Workbuddy session, kimi-code session. (Japanese): agent session visualization, session visualization, agent timeline, sub-agent visualization, session report, execution map, agent execution flow, Cursor session, Claude Code session, Workbuddy session, kimi-code session.
Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate harsh critic on each, compare blind against the bar, and loop until it wins. Works for builds, writing, code, research, or design. Triggers on "/gauntlet-loop", "gauntlet loop", "gauntlet this", "make a gauntlet prompt", "loop until it beats X".
Help users interact with probabilistic models by designing interfaces that manage fluidity, intent, and agency while maintaining trust and control.
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
Mechanics library for running AI coding CLIs as managed tmux workers via agent-tmux <cli> <command> (plus tmux-agent-sessions and the other bundled tools). Entry point is the using-tmux-agent-tools router skill — route through it first; read this skill for wrapper mechanics it defers to. Covers start/send-wait/status/result/stop, structured result.json completion, multi-worker watch, profiles for custom CLIs, and bounded dialogue/fanout. Not for general tmux config, theming, non-tmux headless CLI use, or human team debate.
Render independent questions in an Agent workflow into a local interactive form, mark recommended answers, collect optional supplementary notes for each question, save responses as portable JSON, and return the submitted results directly to the waiting Agent command. Suitable for grill-me, grill-with-docs, brainstorming, requirement clarification, configuration, planning, and any workflow requiring user confirmation or question collection; explicitly call Ask UI when a round contains more than two questions. When a user says "submitted", "done submitting", or "finished answering" during an Ask UI round, follow this skill's manual recovery path.
Set up, adopt, refresh, or audit a repository's agent instructions (the AGENTS.md block) so AI agents work well in that repo. Also records observed agent mistakes as pitfalls. Use when invoked by name
Build, test, publish, invoke, schedule, and update Railcode managed agents with the Railcode CLI. Use when creating an organization or personal managed agent, editing an agent manifest (JSON or YAML), running a draft or saved agent, investigating a run, managing its cron schedule, running it from Slack (@Railcode $agent), pairing it with a companion app, processing files in its sandbox, or using personal connectors (Gmail, Slack, ...) on behalf of one owner. Do not use for static Railcode apps, in-app LLM tool loops (llm.generate({ tools }) — see create-railcode-app), or general organization administration.
Delegate bounded domain analysis, research, independent review, or specialist execution to a focused sub-agent when the user requests a specialist or a specialized perspective, method, or evidence base would materially improve a separable subtask and current policy permits delegation. Do not use for ordinary work, vague expert role-play, tightly coupled tasks, or to transfer the parent agent's responsibility for verification.
MagicPay handles first-time setup, exact balance checks, crypto transfers and reconciliation, plus approved login, identity, checkout, donation, subscription, and payment workflows. It applies when a task needs protected Memory, payment operations, or approval; an open-ended purchase or booking without a checkout URL routes through MagicSearch before browser navigation or generic web search. For browser work, it uses the current agent's native page-control when available. MagicBrowse is fallback page-control.
Create or complete missing repository-level Codex guidance, especially AGENTS.md, using verified project evidence and the narrowest useful scope. Use for new or substantially incomplete guidance. Use kf-maintain-guidance to reduce, reorganize, or update established guidance. Do not use merely because work begins in a repository, or for ordinary feature implementation or bug fixing.
Update an existing AI agent on a live LiteLLM proxy. Ask for the agent_id and what to change (model, description, MCP servers), then call PATCH /v1/agents/{agent_id}.