23,556 tagged Building agents, measured the same way as everything else here.
Browse within: agentic-ai 233LLM 217agent 200agents 151skills 145agentic-workflow 110agent-orchestration 86openai 86antigravity 79agentic-framework 73cli 73ai-skills 71Autonomous Agents 67agent-framework 63
jaywavfeng/tiered-agent-orchestrator
Skill Codex
Orchestrate large, multi-stage engineering work with a decision-focused Lead, reusable economy Workers, repository-backed handoffs, and optional host task messaging. Activate only for an explicit $tao command. Do not orchestrate simple local edits or activate merely because this skill is being maintained.
Skill Claude CodeCodex
A guide for using CodexMCP, a service that lets you delegate coding tasks to the Codex command-line tool. It covers both tasks that wait for a result and tasks that run in the background.
rhettcarillo/claude-code-direct-skill
Skill Claude Code
Work autonomously to a finished, verified result instead of narrating options or stopping for permission; spend the cheapest model that cannot get it wrong; report in a short scannable form; and get measurably better each run by recording what actually went wrong. Use when the owner says /direct, "do wonderful…
Skill Claude CodeCodex
Autonomous worker for openbridge pools. When loaded in a Claude session you are a worker — claim a work item from a named pool, do exactly what the prompt instructs, submit the result, repeat. Operates fully autonomously: never asks the user for direction, never voluntarily stops, never summarises mid-loop, resumes…
Skill Claude CodeCodex
Generate bespoke, stack-aware Claude Code agent files for tech teams. Creates specialized AI agent personas (backend, frontend, fullstack, AI/ML, DevOps, QA, security, code reviewer, performance engineer, system architect, tech lead) that Claude Code autonomously picks up from .claude/agents/. Use this skill whenever…
Skill Claude CodeCodex
Run an autonomous, self-directed build loop that keeps working across many goals without per-step prompting — design the system that does the work, then let it run (Addy Osmani's "loop engineering"). Use whenever the user wants to "keep going on your own", "run until done", grind through a backlog or goal-list…
Skill Claude CodeCodex
Que puede hacer Claude y donde (Chat, Claude Code, Code web, Cowork, Chrome), con el como exacto. What Claude can do & where, across surfaces. Usa /claud o pregunta una capacidad.
Skill Claude Code
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update 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
A Chinese-language thinking and response workflow built around role-playing rules, problem classification, and required checkpoints.
Skill Claude CodeCodex
Audit a skill folder before you publish to ClawHub. Catches the frontmatter-vs-code mismatches, missing metadata, leaked secrets, and file-limit problems that hide or reject a release — so it passes the scan on first upload. Not for vetting a skill you're about to install (see skill-vetter).
Skill Claude CodeCodex
Build, refactor, and lint agent skills: create a new skill, edit its steps, restructure it cleaner, check it for problems, or convert a workflow into one. Trigger on any mention of a skill, SKILL.md, or skill steps.
Skill Claude CodeCodex
Generate optimal Claude Code configuration for any project. Creates CLAUDE.md, settings.json, skills, hooks, agents, and commands tailored to your stack. Run /forge to start.
Firekid-is-him/Reasoning-Skill-Claude
Skill Claude CodeCodex
A reasoning framework that forces Claude to think beyond its training data, challenge its own answers, understand context before responding, and find paths around walls instead of stopping at them. Use this skill for every conversation — especially when a problem seems impossible, when the user is asking for something…
whaojie797-design/Novera-AI-pipeline
Skill Claude CodeCodex
Orchestrates a four-agent coding pipeline (Specifier -> Coder -> Refactorer -> Architect) with steel-cage quality gates and automatic failure routing. Use when the user wants spec-driven development, says "run the four-agent pipeline", "compile this requirement into acceptance criteria", "multi-agent TDD", or wants AI…
Skill Claude CodeCodex
Generate agent skill ideas through problem-driven brainstorming. Situation-specific, narrow-but-universal. Triggers when user wants skill ideas or needs to expand their skill collection.
Skill Claude CodeCodex
Use this skill whenever the user wants to design, build, harden, review, or debug an MCP (Model Context Protocol) server — including "build me an MCP server for X", connecting an AI agent/Claude to a database or API, adding tools/resources to an existing MCP server, reviewing a contributor PR against an MCP server, or…
Skill Claude Code
A tool for cataloguing AI prompts and skills stored in local folders. It scans those files and creates an interactive HTML map that can be used with platforms such as Claude Code, ChatGPT, Cursor, and Gemini.
Skill Claude CodeCodex
A decision-review process that asks five independent AI agents to examine an important question from different viewpoints, then has a chair agent combine their conclusions. It is designed to reduce agreement bias, where an AI too readily supports the user's apparent preference.
Skill Claude CodeCodex
Publish a skill you wrote to Agent Skill Depot. Trigger on 'share this skill', 'publish this', 'post this to agent skill depot', 'upload this skill'. Also trigger after 'this works' / 'looks good' to proactively offer publishing. Never publish without explicit 'publish' approval — 7-step quality pipeline runs locally…
daman8271/the-perfect-orchestrator
Skill Claude CodeCodex
Spawn and orchestrate a fleet of autonomous Claude Code workers in tmux. One LEAD Claude (you) spawns N worker sessions, hands each a task brief, coordinates them via a shared message bus, monitors them live, intervenes when they drift, and adversarially verifies results before reporting. Use for parallelizable…
DennisWei9898/loop-engineering-reviewer
Skill Claude CodeCodex
A reviewer for automated agent or workflow projects, based on the Loop Engineering rules by Addy Osmani. It checks whether creation and review are separated, whether pass conditions are objective, and whether the loop has limits and human approval points.
JesseRaber/manus-prompt-engineering-skill
Skill Claude CodeCodex
Design and audit Manus prompts for engineering, release, production, and security work. Use when writing a Manus prompt or reviewing a Manus execution or recording against authorization and evidence.
shimo4228/agent-adoption-triage
Skill Claude Code
Five-question triage for routing AI work to the right architecture — script, algorithmic search, LLM workflow, or autonomous agentic loop — before any agent is built. Use when someone says "let's build an agent for X", when deciding whether a use case actually needs an autonomous agent, when reviewing an agent…
Skill Claude CodeCodex
Guide for background coding agents running inside Replicas cloud workspaces.
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: