Loading...
Loading...
Found 13,656 Skills
Launch multiple sub-agents in parallel to execute tasks across files or targets with intelligent model selection and quality-focused prompting
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
Universal documentation sync for skills, agents, markdown. Modes - status, init, global, project, file, folder.
Ming Court Code —— Standardize Claude Code development processes using the institutional framework of the Ming Dynasty court. Three-level adaptive modes: Oral Edict (rapid execution), Court Debate (structured solution), Morning Court (multi-agent parallel processing).
Design a goal-oriented agent loop, and review it for the ways loops go wrong — spinning and burning tokens, Goodhart-gaming the verifier, or running a wrong answer to completion. Two actions: (1) WRITE a loop — gate whether to build it, define a machine-decidable goal, pick the loop type, pick a skeleton; (2) REVIEW a loop — run it past five failure modes plus decidability, boundaries, fallback, judge independence, and keep-judgment-with-the-human red lines. Use when designing an autonomous agent loop, or when you already have one and worry it will spin, cheat, or run a wrong answer to the end. Complements the mechanism-layer loop skills (autonomous-loops, continuous-agent-loop) by covering the judgment layer they don't. 中文触发：写 loop、设计 loop、做一个 loop、检查 loop 对不对、loop 体检、loop 会不会跑飞、可判定目标、五个崩法、plan build judge。English triggers: design an agent loop, write a loop, check a loop, loop review, prevent a runaway loop, goal-oriented loop, decidable goal, plan/build/judge.
Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the `query` input, returning a string result, defining an input schema for structured arguments (specifyInputSchema, jsonSchemaExample, DynamicStructuredTool), or troubleshooting errors like "Wrong output type returned", "No execution data available", "The response property should be a string, but it is an object", "Cannot assign to read only property 'name'", or an AI agent that refuses to call the tool. Covers the critical differences between Code node and Code Tool: return format (string vs `[{json:{...}}]`), unavailability of `$fromAI`/`$input`/`$helpers` in the Code Tool sandbox, naming rules for AI invocation, and when to use `toolWorkflow`/HTTP Request Tool instead.
The full lifecycle for agentic loops — recurring, scheduled AI agents packaged as a portable LOOP.md (the agenticloops.dev standard: a trigger + skills + a prompt in one file any harness can install and run on a schedule). Use this whenever the user wants to FIND, INSTALL, RUN, or BUILD a loop: "find a loop for X", "is there a loop that…", "install a recurring agent that does X", "run this loop", as well as "create a loop", "make an agentic loop", "write a LOOP.md", "turn this into a recurring agent", "schedule an agent", "set up a cron job for an agent", or any description of a repeating job they want an agent to do on a timer (a daily digest, a competitor watcher, a triage sweep, a report pipeline, "email me X every morning", "check Y every hour") — even if they never say the word "loop". Always search the directory first and install an existing loop when one fits; author a new LOOP.md only when nothing does. This is the loop-level analogue of skill-creator + find-skills combined. For an ad-hoc in-session multi-agent run (spawn, verify, panel, fan-out) use the `loops` skill instead; for authoring a reusable SKILL.md use skill-creator.
Run bounded, evidence-driven training research through W&B Launch: assess project readiness, establish launchable code and queue capacity, smoke-test real jobs, execute serial trials, compare metrics, and persist resumable research state. Use when a coding agent is asked to autonomously test training hypotheses or tune a real W&B-tracked workload.
Synthesize GitHub delivery context into a concise Basic Memory project update. Use in CI after `bm ci collect` prepares a ProjectUpdateContext; return only structured AgentSynthesis JSON for `bm ci publish`.
Run /code-review, /simplify, /brooks-review, /review, /ask-exemplar, and /zero-tech-debt on a change via parallel subagents, address the meaningful findings, fold the fixes into clean commits, and force-push with lease. Use when the user wants to review-and-fix a change before merge: uncommitted work, the current feature branch, or a GitHub PR / GitLab MR. Triggers include "review-fix", "review and fix this PR/MR", "polish this branch", or "run the reviews, address the suggestions, then force-push".
Connect an AI coding agent to Proxyman MCP. Use this skill when Proxyman is installed but the agent cannot see Proxyman MCP tools, the user asks to set up Proxyman MCP, configure Codex, Claude, Cursor, VS Code, Copilot, or troubleshoot missing Proxyman MCP tools, handshake errors, or "tool not found" issues.