23,376 tagged Building agents, measured the same way as everything else here.
Browse within: LLM 207agent 200agentic-ai 197agents 149skills 149openai 86antigravity 83agentic-workflow 79ai-skills 75cli 75agentic-framework 73Autonomous Agents 67ai-assistant 65agent-framework 59
Skill Claude CodeCodex
Guide for authoring Better-Claw skill sets and skills — directory structure, SKILL.md/SKILLSET.md format, frontmatter fields, best practices, and testing methods.
Skill Claude CodeCodex
User wants the Entity Engagement Protocol in their application—EEP, signed webhooks, SSE, gates, "agent-ready API," or running eep-dev/agent-adopt. Use for adopt EEP, add EEP, EEP webhooks, not for generic REST without EEP.
Skill Claude Code
Send an application message (MSG) to a specific IronMesh peer. Use when the user asks to "send X to agent Y" or "ping peer Z". Has side effects — only invoke when the user explicitly asks.
WildPigKing/codex-project-skill-manager
Skill Codex
Inventory, classify, route, catalog, relocate, or validate Codex skills and generate a skills menu. Use for skill-library organization or when Codex must find task-relevant skills. Classification, relocation, creation, revision, and promotion require user approval.
Skill Claude CodeCodex
Iteratively improve code, strategies, or prompts through mutation, evaluation, and selection.
Skill Claude CodeCodex
../../agnosticv/skills/catalog-builder/SKILL.md.
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, 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
Architecture patterns for AI agents that communicate over email -- why agents need dedicated inboxes rather than human email accounts, infrastructure/provider tradeoffs, one-inbox-per-agent, two-way conversation loops, human-in-the-loop drafts, WebSocket vs webhook event design, multi-agent topologies, OTP flows, and…
Skill Claude Code
Distill any book into an executable Claude Code skill pack. Evaluates skillability, generates structured skills with modules/templates/examples, and supports multi-book synthesis. Use when you want to turn a book's methods into repeatable, actionable skills.
Skill Claude CodeCodex
洁癖 Skill: Audit installed AI agent skills across Codex, Claude Code, Cursor, and optional project-local skill folders. Use when the user asks which skills are installed, how often Claude Code/Codex/Cursor used skills, whether a skill was used recently, which skills are stale or unused, or wants cleanup/removal/disable…
gjbjzyvivian-netizen/vibe-coding-prd
Skill Claude CodeCodex
A workflow for turning rough requirements, product documents, or competitor research into a concise product brief for coding agents such as Claude Code, Codex, or Cursor. It includes features, technical choices, prototypes, details, and testable acceptance criteria.
Skill Claude Code needs its repo ✓ vendor
Use when building Slack agents/bots with eve (Vercel's filesystem-first agent framework), @vercel/connect, or eve/channels/slack. Covers defineAgent/defineTool patterns, Vercel Connect credential brokering, Slack channel setup, testing requirements, and quality standards.
Debarpan08/hermes-skill-registry
Skill Claude CodeCodex
Use when searching for, installing, publishing, or rating Hermes skills via the community registry. Like npm for Hermes skills.
kesslerio/soulcraft-openclaw-skill
Skill Claude CodeCodex
Create or improve SOUL.md files for OpenClaw agents through guided conversation. Use when designing agent personality, crafting a soul, or saying "help me create a soul". Supports self-improvement.
Skill Claude CodeCodex
Pangu Skill 1.0 (盘古.skill 1.0): autonomous Agent Skill quality evaluator and validation optimizer. Uses a 9-dimension rubric, test-prompt validation, git ratchet keep/revert decisions, independent judge review when available, dry-run fallback when unavailable, human-in-the-loop checkpoints, and visual result-card…
Skill Claude CodeCodex
A skill for creating, editing, and benchmarking Pi skills stored in SKILL.md files. Benchmarking means testing a skill against examples to measure and improve its behavior.
Skill Claude CodeCodex
Official AGBook (www.agbook.ai) HTTP API: catalog, search, contributions, feedback, review, reports, points with AGBOOKAPIKEY. Read APIs before heavy writes; after using catalog entries to complete work, prefer POST /feedback to close the loop. Use for AGBook, api.agbook.ai, /api/v1/catalog, discover/candidates…
Skill Claude Code
Turn Raw-layer traces (conversation, pitfalls, best practices) into Wiki-layer skills, or CRUD existing ones, then notify guide to update the routing table.
charlie947/agent-harness-starter
Skill Claude CodeCodex
Interactive walkthrough that builds the user's agent harness — Personalisation (/.claude/CLAUDE.md), Context (project CLAUDE.md), Memory (/.claude/memory/), Skills (/.claude/skills/), Agents (/.claude/agents/), and suggested MCP connectors. Use when the user asks to "set up my agent harness", "build my CLAUDE.md from…
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Skill Claude CodeCodex
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞.
Skill Claude CodeCodex
Pydantic AI Python agent framework. Covers typed tools, model providers, evals, MCP, UI adapters, and observability. Use when building Python AI agents with Pydantic AI, configuring model providers, implementing typed tools/dependencies, running evals, or integrating MCP servers. Keywords: pydantic-ai, agents, evals…
Skill Claude CodeCodex
Delegate tasks to other agents in the team by creating real PaperClip child issues. Covers single-agent delegation and multi-agent coordination, with failure handling and idempotency. Trigger phrases: any task outside your direct capabilities (email/calendar/drive) that should be routed to Coder, Infrastructure…
Skill Claude CodeCodex
Invoke OpenCode CLI as a sub-agent to leverage alternative AI models (GPT-5.x, Codex, local models) for code implementation, review, debugging, research, and second opinions. Use when the user asks to "use opencode", "get a second opinion from GPT/Codex", "implement with opencode", "review with opencode", "let…
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: