Building agents skills

23,553 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

delegate-to-agent

3505

psychofanPLAYS/gemini4codex-mcp

Skill Claude CodeCodex

Delegate tasks to isolated Antigravity/Gemini subagents for parallel execution, code review, or research.

not rated 1 1mo ago A 26 tokens original MIT

HeadStone1/AgentBridge

Skill Codex

Use AgentBridge MCP when the active AgentBridge global/project configuration permits collaboration and the task benefits from Claude Code/Codex consultation, review, or a joint conclusion.

not rated 1 23d ago A 39 tokens

graph-mission

3507

dizeldz20-ux/agent-shared-memory

Skill Claude CodeCodex

Compile and run complex, multi-lane Codex work as an evidence-backed mission graph tied to ASM: recall before decomposition, define measurable success and non-goals, coordinate only independent lanes, persist resumable lineage, verify effects, and write back durable outcomes. Use when the user explicitly asks for…

not rated 1 13d ago A 107 tokens original MIT

spokes

3508

Dente22/Spokes

Skill Claude CodeCodex

Use Spokes MCP before inventing code. Triggers on: implement a feature, build an app, add auth/api/ui, reuse existing code, find how I did this before, check my GitHub repos, avoid reinventing the wheel, pull logic from my projects. Always consult Spokes memory of the user's owned GitHub repositories first.

not rated 1 29d ago A 72 tokens original MIT

author-codemode-skill

3509

stjbrown/codemodekit

Skill Codex

Author, refine, or evaluate the domain-aware runtime Agent Skill inside a CodeModeKit Agent Plugin. Use after scaffolding or catalog changes, when guidance is generic, when adding workflows, examples, write safety, and result contracts, when maintaining plugin metadata, or when preparing the skill for experimental MCP…

not rated 1 11d ago A 73 tokens original Apache-2.0

peter14l/kotlin-agent-orchestrator

Skill Claude CodeCodex

Skill "kotlin-agent-orchestrator" from peter14l/kotlin-agent-orchestrator, covering kotlin multi-agent orchestrator (mcp server & skill), 🌟 complete specialized agent roster (24 tools), 🚀 core architecture & engineering agents, ⚡ hackathon fast-prototyping agents and 📦 installation & setup.

not rated 1 24d ago A 0 tokens original MIT

codex-dsh-orchestrator

3511

Fly2Kiana/Codex-DSH-Orchestrator

Skill Codex

A set of instructions for coordinating work between Codex and DSH through an existing tool connection. DSH is treated as a worker for bounded coding tasks, while Codex keeps responsibility for planning, technical decisions, supervision, and final review.

not rated 1 +1 7d ago A 141 tokens original MIT

hello-world

3512

skillmds/skillmd

Skill Claude CodeCodex

Greet the user warmly and demonstrate the minimal shape of a valid Agent Skill.

not rated 1 2d ago A 19 tokens original MIT

design-mcp-server

3514

cyanheads/federal-reserve-mcp-server

Skill Claude CodeCodex

Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.

not rated 1 26d ago A 62 tokens

self-maintainer

3515

vivy-yi/awesome-skills

Skill Claude CodeCodex

Self-maintaining skill that updates, improves, and audits the awesome-skills maintenance skill system. Use when: (1) updating skills to new patterns, (2) auditing skill health, (3) self-improvement. Triggers on: "self-maintain", "audit skills", "skill health", "improve skills", "skill maintenance", "maintain myself".…

not rated 1 3mo ago A 92 tokens original MIT

agents-generator

3516

OJPalenzuela/agents-generator

Skill Claude Code

Generate a complete, project-specific AGENTS.md compatible with the agents.md standard (60k+ open-source projects). Also generates platform-specific files (.cursorrules, Copilot instructions, GEMINI.md) for detected platforms. Use when setting up AI agent rules, creating project conventions for Claude Code, Cursor…

not rated 1 1mo ago A 180 tokens original MIT

loops

3518

5dive-ai/skills

Skill Claude CodeCodex

Author or modify a LOOP.md — the portable agenticloops.dev format for a recurring, scheduled agent (trigger + skills + prompt in one file). Use when writing a new loop or editing an existing one; to find and install a loop that already exists use find-loops.

not rated 1 changed 3d ago A 59 tokens original MIT

clawdirect-dev

3519

napoleond/clawdirect

Skill Claude CodeCodex

Build agent-facing web experiences with ATXP-based authentication, following the ClawDirect pattern. Use this skill when building websites that AI agents interact with via MCP tools, implementing cookie-based agent auth, or creating agent skills for web apps. Provides templates using @longrun/turtle, Express, SQLite…

not rated 1 6mo ago A Socket: failSnyk: fail 69 tokens

self-evolver-pro

3520

gitstq/awesome-ai-agent-skills

Skill Claude CodeCodex

Self-improving AI agent evolution engine with intelligent experience management. Captures learnings, errors, and feature requests from every interaction, deduplicates them intelligently using semantic similarity, and promotes high-value patterns into reusable skills. Unlike basic memory skills, it features automatic…

not rated 1 6mo ago A 148 tokens original MIT

mcp-demo-enforcer

3521

danduh/mcp-security

Skill Claude CodeCodex

Forces the model to always use the mcp-security demo MCP server tools instead of native capabilities. Use this skill whenever the user is working in the mcp-security project and asks to read files, count lines, write files, check npm packages, inspect npm config, verify registry, or do any file/npm operation. This…

not rated 1 2mo ago A 119 tokens

PanGucheng/codex-deepseek-delegate-mcp

Skill Codex

Delegates complex Codex codebase exploration, implementation, verification, task resume, task history lookup, and read-only review through the local deepseekdelegate MCP server. Use for prompts mentioning DeepSeek delegate, delegatetask, repo-scout, implementer, reviewer-helper, approvedCommands, delegatestatus…

not rated 1 2mo ago A 82 tokens

agent-workspace-mcp

3523

HrRodan/agent-workspace-mcp

Skill Claude CodeCodex

Provides a highly secure, containerized Linux workspace via the Model Context Protocol (MCP) mounted at /workspace. Uses this skill when the agent needs to autonomously code, test, and debug safely using filesystem, execution, and editing tools, while adhering to strict environment constraints such as mandatory use of…

not rated 1 3d ago A 73 tokens

cheaplane-delegate

3524

millennialdreamer/cheaplane

Skill Claude CodeCodex

Use the delegate MCP tool to offload replaceable grunt work (boilerplate code, mechanical refactors, formatting, translation, summarizing long documents) to cheap models, so you keep your premium tokens for judgment work. Trigger whenever a subtask is mechanical, well-specified, and doesn't need your full reasoning.

not rated 1 1mo ago A 71 tokens original MIT

oakallow-governance

3525

oakallow/oakallow-mcp

Skill Claude CodeCodex

Use this skill when an AI agent needs to act safely through oakallow, the runtime permission, approval, and audit layer for AI agent tool execution. Trigger it whenever you are about to take a tool action that could be risky, irreversible, or that touches another system, and you need to know whether it is allowed…

not rated 1 2mo ago A 205 tokens original MIT

self-improving-agent

3526

Grail-Computer/Self-Improving-Agent

Skill Claude CodeCodex

Meta-skill for making the agent self-improving. Covers updating AGENTS.md, creating new skills from repeated workflows, and deciding what to systematize. Invoke after completing tasks, when noticing repeated friction, or at session end.

not rated 1 +1 7mo ago A Socket: passSnyk: pass 54 tokens

slack-agent-mesh

3527

nickvasilescu/slack-agent-mesh

Skill Claude CodeCodex

Connect an existing agent (Hermes, Claude Code, Codex, any stdin/stdout CLI, an HTTP endpoint, or an MCP client) to Slack Agent Mesh, and operate correctly inside it — addressing agents by @name, delegating agent-to-agent, and respecting loop limits and untrusted-content rules. Use when wiring an agent into a shared…

not rated 1 1mo ago A 95 tokens original MIT

toolhome

3528

crayonlu/toolhome

Skill Claude CodeCodex

Deploy and manage a self-hosted ToolHome instance: an MCP and Hosted CLI control plane that aggregates upstream capabilities and platform CLIs. Use when the user wants to set up ToolHome, manage MCP servers or hosted CLIs, reuse encrypted credentials, authorize OAuth upstreams, install from the Market catalog…

not rated 1 changed 2d ago A 97 tokens original MIT

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: