23,479 tagged Building agents, measured the same way as everything else here.
Browse within: LLM 208agent 200agentic-ai 197skills 149agents 148openai 86antigravity 83agentic-workflow 79ai-skills 75cli 75agentic-framework 73Autonomous Agents 67ai-assistant 65agent-framework 59
Skill Codex
Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create…
Skill Claude CodeCodex
Analyzing user intent and delegating tasks.
Skill Claude CodeCodex
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Skill Claude CodeCodex
The art of keeping your AI stack small and shaped on purpose. Use when building AI features, selecting models, designing extraction/RAG/agent pipelines, or about to reach for a frontier LLM (GPT-5, Claude Opus, Gemini Pro). Enforces a smallest-tool-first ladder (regex, spaCy NER, small LLM, frontier) and challenges…
Skill Claude CodeCodex
A skill for building reusable agent personas from separate traits, such as personality, speaking style, role, appearance, and hobbies. Several traits can be combined and applied to the current session.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
majiayu000/awesome-goal-prompts
Skill Claude CodeCodex
Create, tighten, or review runnable /goal contracts for coding agents such as Codex, Claude Code, Cursor, and similar agent tools. Use when the user asks to write, make, generate, improve, productize, or critique a goal prompt, rescue contract, GOAL.md-style task, done-when contract, verification prompt, stop-rule…
gvkhosla/compound-engineering-pi
Skill Claude CodeCodex
Reviews code to ensure agent-native parity — any action a user can take, an agent can also take. Use after adding UI features, agent tools, or system prompts.
Skill Claude Code
General-purpose multi-agent orchestrator. TRIGGER when: (1) the task is complex or multi-step — research, analysis, review, planning, debugging, refactoring, or any work that benefits from multiple expert perspectives; (2) the user asks for parallel review or multi-angle analysis; (3) brainstorming, ideation, or…
Skill Claude CodeCodex
Interact with the CAFleet message broker and supervise CAFleet member teams. Use when an agent needs to register as a member, send/receive messages, poll inbox, acknowledge messages, or discover other members; or when a Director is about to spawn, monitor, health-check, or recover a stalled team of CAFleet members…
Skill Claude CodeCodex
Use when analyzing large files (>200 lines), more than 3 files at once, deep git/grep searches, web lookups, or adversarial reviews - delegates to the Antigravity CLI via agy-bridge MCP tools to save context.
Skill Claude CodeCodex
Join Agent Room meeting rooms (agent-room.com) to collaborate live with other AI agents and humans over plain REST. Use when the user asks to create or join an "agent room" / meeting room, shares a 9-character room code like ABC-DEF-GHJ or a link like https://www.agent-room.com/j/CODE, or wants this agent to talk to…
Skill Claude CodeCodex
Connect to remote ACP server and execute commands via imclaw-cli.
Skill Claude CodeCodex
PM Ops — orchestrator of the minions AI subagent team. Single entry point: decomposes requests, delegates to minions- subagents in parallel or sequence, aggregates output.
samwalter2949348803-stack/Openclaw-catch-Claude-Code
Skill Claude Code
Delegate tasks to Claude Code CLI when you need to write/edit code, run shell commands, access files you cannot reach, do multi-step work, or perform git operations. Use this when built-in tools are insufficient or get blocked.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
How to write a new Pincer skill as a SKILL.md directory — frontmatter fields, progressive disclosure, and when to add a script versus pure instructions. Load this when the user asks you to create, package, or explain a Pincer skill.
Skill Claude CodeCodex
Generate a Product Requirements Document (prd.json) for the Ralph autonomous agent loop. Use when planning a feature, starting a new project, or preparing work for Ralph to implement. Triggers on: create a prd, write prd for, plan this feature, generate user stories, set up ralph for, spec out.
Skill Claude CodeCodex
Coordinate independent agents so one leads a group or owns one exact task before side effects.
Skill Claude CodeCodex
Build an OpenClaw-ready public-figure persona package from public materials. Use when the user wants a directly runnable agent that answers as a specific person, with runtime files (SOUL.md, IDENTITY.md, AGENTS.md, MEMORY.md) as the default deliverable. Prioritize hard behavioral controls so the shipped runtime stays…
Skill Claude CodeCodex
A guide for delivering skills, agents, and workflows through capability-runtime, the runtime layer that executes these capabilities and reports their results.
seungmanchoi/react-native-fsd-agent-template
Skill Claude CodeCodex
An automation skill for coordinating the full lifecycle of a React Native and Expo app built with Feature-Sliced Design. It coordinates eight AI agents and eight skills.
rafsilva85/credit-optimizer-v5
Skill Claude CodeCodex
Automatically optimize AI agent credit usage by routing tasks to the most cost-efficient execution path. Use when you want to reduce AI API costs by 30-75% without quality loss, classify task complexity before execution, route simple tasks to free or low-cost models, split complex tasks into optimized sub-tasks, or…
Skill Claude CodeCodex
Create, update, list, and safely maintain evidence-bounded graduate-advisor Skills from comments, meeting notes, chat logs, documents, and user corrections. Use when the user asks to create or evolve a supervisor/advisor Skill, distill a mentor's working style, run /create-supervisor, /update-supervisor…
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: