23,505 tagged Building agents, measured the same way as everything else here.
Browse within: LLM 209agent 202agentic-ai 195skills 149agents 145openai 86antigravity 83agentic-workflow 79cli 75agentic-framework 73ai-skills 73Autonomous Agents 67ai-assistant 66agent-framework 59
Skill Codex
A file-based handoff process for two agents named Sol and Grok to implement and review coding tasks across separate conversations. It uses shared project files to record the next actor, task details, implementation notes, and review results.
sharif-smj/jules-swarm-orchestrator
Skill Claude CodeCodex
Orchestrates parallel Jules agent swarms for codebases. Dispatches 8 specialized agents (Architect, Bolt, Navigator, Palette, Sentinel, Verifier, Janitor, Scribe), manages file ownership to prevent merge conflicts, and defines review/merge workflow. Use when user says "run jules swarm", "dispatch agents", "jules…
dungnotnull/arid-region-water-saving-irrigation-agent-skill
Skill Claude CodeCodex
Complete skill registry for arid-region-water-saving-irrigation - production-grade harness with dynamic skill routing, lifecycle hooks, and type-safe configuration management.
Skill Claude CodeCodex
Create, edit, debug, and manage zo-dispatcher agents. Covers dispatch patterns, agent file format, prompt authoring, webhook setup, channel configuration, scheduling, and debugging. Triggers on: 'create an agent', 'edit an agent', 'schedule a task', 'add a webhook', 'cron job', 'recurring task', 'debug agent', 'agent…
MitchellkellerLG/system-comparison
Skill Claude CodeCodex
Systematic gap assessment between two skill/tool systems. Spawns parallel research agents per domain track + one fitness agent covering 10 structural vectors (prerequisites, cost, QC, UX, skill standard, security, architecture, workspace compatibility, trigger precision, maintenance decay). Produces ranked steal-list…
mekotenkov-ux/seomeatagentscreator
Skill Claude CodeCodex
A process for creating, checking, packaging, and publishing production-ready AI agents, skills, and workflows.
zhouyou-gu/skill-marketplace-template
Skill Claude CodeCodex
Turn the current chat history and optional pasted agent transcripts into a reusable skill package. Use when a conversation already contains a repeatable workflow that should be drafted in the current project .temp/ folder and optionally published into a skill-marketplace-template-style marketplace. Do not use it for…
realsigridjin/interview-copilot-with-skills
Skill Claude CodeCodex
Claude Developer Platform Skills feature. Custom knowledge packages for agents, curated playbooks, and versioned expertise domains.
Skill Claude Code
A structured reasoning framework for agents modeled on prefrontal cortex (PFC) function. Use this skill whenever an agent needs to solve multi-step problems, make decisions under uncertainty, plan across time, self-correct mid-task, use tools, or avoid impulsive/shallow responses. Triggers on: agentic tasks, tool use…
Skill Claude CodeCodex
A workflow for creating or updating two OpenClaw photography agents: an artistic director and a curator.
shyamsridhar123/AlltheVibes-WildHackathon
Skill Claude CodeCodex
Automatically assigns Star Wars character personalities to subagents spawned during execution, making each agent communicate in the distinctive style of a randomly selected character while maintaining technical accuracy.
AEON-7/create-agentic-personas
Skill Claude CodeCodex
Create a new fully-embodied AI persona — an OpenClaw chat agent with a Matrix identity, a personality, an optional knowledge corpus, a custom Qwen3-TTS voice (cloned or designed), and a live WebRTC voice-call line. USE THIS SKILL whenever the user asks to: create/add/build/scaffold an agent, persona, character, bot…
Skill Claude CodeCodex
Builds multi-language (Python, TypeScript, Go, Kotlin) autonomous agent and multi-agent system workshops using Google Agent Development Kit (ADK). Generates Coordinator-Worker agent architectures, tool bindings, Human-in-the-Loop (HITL) checkpoints, and trajectory evaluation labs.
Skill Claude CodeCodex
Use Stet to measure whether an AI coding change is safe to ship. Trigger on model comparisons, AGENTS.md or CLAUDE.md effectiveness, shared instruction, policy, skill, harness, tool-policy, reasoning, or runtime rollouts, repo eval setup, dataset building, regression detection, benchmarking, promote/rollback…
Skill Claude CodeCodex
Pure decision-making logic. Maps (targetcfg, resourcestate, memory) → which variant, which counter, execute or skip, what to do with a drop, which trait/option to take, how the meta is trending. No I/O, no browser, no wallet, no LLM calls — just deterministic policy.
Skill Codex
Manage scoped skills across global and local skills/ directories. Use when the user wants to initialize skill scoping, discover unregistered skills, add/remove/move a skill between scopes, locate the absolute path of a skill for editing, audit drift between disk and AGENTS.md, query which skills are installed and…
Skill Claude CodeCodex
Use when starting or resuming a SpecForge task — the orchestrator that scaffolds the task directory, detects the current phase, and routes to the explore, spec, or execute stage skill. Triggers on "specforge", "execution spec", "spec-driven implementation".
Skill Claude Code
This skill should be used when the user asks to "set up night shift", "add night shift workflow", "set up the agent loop", "initialize night shift", "add night shift to this project", or wants to configure autonomous overnight AI agent development using the Night Shift method by Jamon Holmgren.
Skill Claude CodeCodex
Chain multiple AI agent skills into sequential pipelines. Output of each skill feeds as context into the next.
Wayfound-AI/wayfound-agent-skills
Skill Claude CodeCodex
Lightweight self-supervision that piggybacks on your existing memory system. Adds a simple rubric to SOUL.md and a daily review cron job — no new infrastructure, no parallel systems. Your agent reviews its own day in 200 tokens, writes findings to memory where they compound naturally, and surfaces issues that need…
Skill Claude CodeCodex
Coordinate a fleet of worker agents in a pane-based multiplexer — one default pipeline (coordinator → flat-rate spec-writer → local builder) with exception surfacing, dispatch and briefing templates, push-based completion protocol, review gates, verification ladder. Use when running inside a supported multiplexer…
Skill Claude CodeCodex
A project-starting workflow that turns a broad software idea into written product and technical context. It can also document the first small end-to-end slice of a product, meaning one useful path that works from beginning to end.
1chen666/codex-handoff-skill-test-by-deepseek-
Skill Claude CodeCodex
Explicit file-based handoff mode for Codex workflows that switch between GPT and DeepSeek through CCSwitch. Use this skill only when the user explicitly invokes /handoff or says Use codex-model-handoff; do not activate it for ordinary coding questions, small edits, explanations, or implicit continuity needs. It…
qinghui316/ecl-harness-engineer
Skill Codex
Create, audit, or migrate a project-bound local Harness for reliable AI coding. Use when a project needs ECL Change planning, layered project knowledge, local Codex/Claude worktree coordination, PR-like Integration, Harness Evolution, greenfield guidance, or reference-source maps. Do not use for ordinary feature…
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: