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
Reedtrullz/codex-antigravity-auth
Skill Codex
Use the optional Anti helper after Antigravity Claude Opus/Sonnet is available in Codex: sidecar review, consult lane, deep autonomous work plan, official DeepSeek V4, $anti workflow preset, or $anti panel MoA/Fusion workflow. Trigger when the user writes $anti, @anti, $anti workflow, $anti workflow review-ready…
Skill Claude CodeCodex
Install and configure tg-cli-bridge — a Telegram bot that lets you drive any agentic CLI (Gemini CLI, AGY/Antigravity, Claude Code) from your phone. Each message you send spawns the CLI with your prompt, waits for it to finish, and replies with the clean output. Supports session continuity, inline menu buttons, and…
Skill Claude CodeCodex
Audit a repository's AI-agent readiness with the agentlint CLI and fix the findings. Use when the user asks to score, audit, or improve how well a repo works with AI coding agents (AGENTS.md, build/test docs, conventions, guardrails), or mentions agentlint.
Skill Claude CodeCodex
Drive CLIque over its HTTP API to run and coordinate coding agents on a box — start sessions, send prompts, read output, and wait for one to finish or come back asking. Use when a task means running work across several repos or agents at once and collecting the results, rather than doing it all in one session.
Skill Claude CodeCodex
Self-driving mission runner — once started, runs an endless discover→analyze→plan→execute→verify→learn cycle on a user-defined mission until told to stop. Boot interview captures mission, allow/forbidden paths, risk tier, cadence, auto-compact threshold, escalation, update policy, resume policy. Safety policy blocks…
Skill Claude CodeCodex
Bootstrap an agent collaboration system into an Obsidian vault — memory, protocols, task boards, and per-client instruction files via a conversational interview. Use when asked to "set up my vault", "onboard me", "bootstrap agent collaboration", "set up session protocols", "configure my vault for AI", or at the start…
WebisityStudio/claude-codex-mcp-bridge
Skill Claude Code
Coordinates multi-turn Claude and Codex work with durable messages, native background pings, resumable sessions and isolated worktrees.
SkiTemplar/ultron-control-center
Skill Claude Code
Master orchestrator for the ULTRON system. Routes requests across memory layers, skill packs, hooks, and the AI Router (primary→fallback chain). Loads on every Ultron session via the SessionStart hook. Customize this file for your own workflows — the shipped version is a minimal starting template.
Skill Claude CodeCodex
Enables Clawdbot to communicate with other AI agents via the A2A (Agent-to-Agent) protocol.
Skill Claude CodeCodex
Runs repeatable AI work with checks, budgets and traces.
Skill Codex
Connect, initialize, resume, or coordinate MDevolved Projects from Albatross using its agent.config.json stdio MCP surface, a pinned OAuth bridge, qualified tool names, workspace prompt continuity, path forks, resets, and independently attributable participant identities. Use when a repository runs Albatross, contains…
Skill Claude Code
Global lightweight Forge Core. Use for any goal-shaped build/create/automate/fix/research request, or triggers: install Forge V2 into this project, use Forge system, gebruik Forge systeem, start Forge dashboard. Runs the Forge Command Center at 127.0.0.1:4100.
IGTA-Tech/claude-skills-research
Skill Claude CodeCodex
This enhanced skill should be used when the user asks to create an agent, automate a repetitive workflow, create a custom skill, or needs advanced agent creation capabilities. Activates with phrases like every day, daily I have to, I need to repeat, create agent for, automate workflow, create skill for, need to…
csiddhant796-blip/claude-skills-collection
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
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
Skill Claude CodeCodex
Use when executing implementation plans with independent tasks. Dispatches fresh delegatetask per task with two-stage review (spec compliance then code quality).
Skill Claude Code
Find work, earn money, and collaborate with other AI agents on ClawdWork - the job marketplace for AI agents.
Millsondylan/Claude-code-agents
Skill Claude Code
Run the full multi-agent pipeline to complete a task from start to finish.
Skill Claude Code needs its repo
Operate and improve SCP governance for multi-agent teams: self-bootstrap and teardown of federated pods, generic role topology, TEAM PM / TEAM ODIN separation, minimal bootstrap receipts, terminal locator identity, control-plane non-implementation, delegation receipts, terminal/CMUX delivery proof and verdicts…
Skill Claude CodeCodex
Turn existing Supabase applications into end-user-facing Streamable HTTP MCP servers. Use for installing, configuring, developing, debugging, testing, deploying, or upgrading the chumbo package, including when a user asks generically to add MCP capabilities to a Supabase app. Covers tools, Resources, prompts, MCP…
Skill Claude CodeCodex
A skill for creating WebAssembly plugins that follow contract version 5. WebAssembly is a portable format for running compiled code, and this workflow covers a Rust plugin project, tests, and publishing details.
Skill Claude Code
Operate the Waygate MCP server's implemented filesystem, search, command, and HTTP tools with explicit safety boundaries. Use when inspecting files under a configured Waygate root, making a deliberate file change, running a bounded local command, or calling an explicitly authorized HTTP endpoint. Trigger with "use…
wardawgmalvicious/agent-config
Skill Claude Code
Author a new skill for this repo end to end — take a topic, check for existing coverage, drill the official docs behind it, write a filled handoff brief to docs/handoffs/, then draft the SKILL.md and run the post-draft checks. Use when asked to write, author, create, or scaffold a new skill, or when a drift-audit…
RayYeung1989/dsh-plugin-development
Skill Claude CodeCodex
A development guide for dsh plugins, which are npm packages that extend DeepSeek Harness profiles for web, headless, or custom use.
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: