23,540 tagged Building agents, measured the same way as everything else here.
Browse within: LLM 213agent 202agentic-ai 195skills 149agents 145openai 86antigravity 80agentic-workflow 79cli 74agentic-framework 73ai-skills 73Autonomous Agents 67agent-framework 65ai-assistant 65
Skill Claude CodeCodex
Delegate an explicitly approved local coding task from Codex to Kimi Code, monitor it, return review feedback to the same Kimi session, and independently verify the result. Use only when the user explicitly asks to try Kimi or has approved a Codex suggestion to use Kimi for the current task.
Skill Claude CodeCodex
Use when an AI agent needs a repeatable workflow to get a real answer or compare providers through agentic-mcp, with discovery, proof, and CLI fallback steps.
Skill Claude CodeCodex
Analyze repeated EvoPilot observations and compile proven workflows into portable, versioned Agent Skills or other reviewed extensions. Use when improving or extending the agent itself.
Skill Claude CodeCodex
Skill "codex-channels" from cafitac/codex-channels, covering codex-channels, execution-first rule, fastest shortcuts, codex operator mode and fastest operator check.
Skill Claude Code
Measure what a change to an AI coding setup actually saved, in dollars. Compares recorded before/after usage from the AI Insights MCP server — either two specific sessions by id, or everything in one period against another — and attributes the cost difference to the factor that moved it: fewer API calls, less context…
Skill Claude CodeCodex
Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.
Skill Claude Code
Scaffold a new custom SKILL.md file interactively. Use when asked to create a new skill or slash command.
Skill Claude CodeCodex
Delegate bounded coding work to a Codex worker, including an explicitly configured alternate model/provider through the official Codex SDK and App Server, or diagnose worker readiness. Use when the user asks to delegate, use a worker/custom model/provider, steer or interrupt delegated work, or run Ferry doctor. Do not…
tonytanglab/deepseek-harness-relay-mcp
Skill Codex
Dispatch and monitor an explicitly scoped, simple or medium-complexity local subtask through models available in DeepSeek Harness, including read-only review and user-authorized workspace implementation. Use when the user says “调用 Harness”, asks Harness to analyze or review, or delegates a fix, edit, refactor, test…
Skill Claude Code
Run a long-lived, headless per-project GOAL orchestrator on hyperpanes — hold a project's goal list, spawn a fable/opus spec agent per goal, have it fan work out to sonnet impl agents via the durable work queue, watchdog wedged agents, rotate across Claude accounts on limits, and loop 24/7. Use when the user wants a…
Skill Claude Code
Lint and improve AI agent context files (CLAUDE.md, AGENTS.md, .cursorrules, COPILOT.md) based on empirical research. Use when reviewing, auditing, or creating context files.
Skill Claude CodeCodex
Generate production-ready AI steering documents — CLAUDE.md, AGENTS.md, GEMINI.md, SKILL.md, rules.md, .cursor/rules/, .kiro/steering/, copilot-instructions.md — for any AI coding system. Use when asked to write, improve, or review project instructions, agent rules, or steering docs for Claude, Copilot, Cursor, Kiro…
Skill OpenCode
Auto-route natural-language requests to existing ai-kb command workflows with full command parity and multi-workflow composition. Use by default when user does not explicitly call a slash command.
Kim-FengLei/multi-perspective-meeting
Skill Claude CodeCodex
Turn a single Agent into a full multi-perspective meeting. The Agent auto-generates one role-played participant per perspective, runs a structured debate with cross-examination, converges to a conclusion, and outputs an HTML meeting-minutes file. Trigger on any research / analysis / discussion / decision request.
Skill Claude CodeCodex
Use the blockrun CLI to pay-per-request AI (chat/image/video/music/speech), live data (web/X search, prediction markets, Pyth prices, 40+ chain RPC), and any x402-paid endpoint — all billed from a local USDC wallet, no API keys. Use when the user asks to run a model, generate media, query crypto/prediction/web data…
thomasthzh/full-agent-takeover
Skill Codex
A task-delegation skill that hands an entire job to the coding agent after you choose its permission level.
Skill Claude CodeCodex
Automatically use klayer for grounding, codebase indexing, session memory, and episode logging during software development tasks unless the user explicitly opts out.
fyzycyst/Agentic_Loop_Notation
Skill Claude CodeCodex
Design, audit, repair, and export AI-agent loops using Agentic Loop Notation v0.3. Use for loop design, prose-to-ALN translation, Loop Doctor safety reviews, and exports to Claude Code or Codex — scoped task prompts, Codex goals, skills, hooks, scheduled tasks, automations, and reusable loop examples.
ybx-stack/rich-brain-clean-hands
Skill Claude CodeCodex
This is the production-grade SKILL file that the rich brain loads when it needs to delegate. It covers the complete decision tree: when to delegate, who pulls data, how to launch, how to wait, how to read results. Paths use / placeholders — adapt to your layout.
Skill Claude CodeCodex
Risk-gated MoA escalation and model auto-tuning.
Skill Claude CodeCodex
Use AgentReceipt CLI as a local evidence sidecar for AI coding sessions. Use when an agent needs compact replay/focus reports, patch-equivalence checks, schema outputs, or deterministic JSON workflows.
Skill Codex
Run Colla Agent, a traceable bounded collaboration loop in which the current Codex session implements a project and Antigravity plans and reviews it read-only. Use for complex or high-risk coding, design, refactoring, debugging, document, media, data, or multi-file project work when the user asks for Colla Agent…
jlldavies/go4-llm-design-patterns
Skill Claude CodeCodex
Use when designing, architecting, planning, or debugging any system with an LLM in it — agents, agent loops, RAG and retrieval, prompt pipelines, multi-agent or subagent orchestration, tool use and MCP, memory and context management, evals, or production guardrails. Trigger BEFORE committing to an approach — choosing…
Skill Claude CodeCodex
A Chinese-language guide for finding, evaluating, creating, improving, testing, and packaging Agent Skills, which are reusable instructions that guide an AI coding or task agent.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: