23,507 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 guide for taking apart a Codex Skill and explaining its design in plain language. A Skill is a set of instructions and supporting files that guides an AI coding agent through a task.
Skill Claude CodeCodex
Interactive tutorial that walks the user through designing, writing, testing, and distributing their own Skill for Claude. Use when the user says "teach me how to build a skill", "help me make a skill", "walk me through skill creation", "I want to learn skills", "/build-a-skill", or asks about SKILL.md structure, YAML…
Skill Claude CodeCodex needs its repo
Use when polling external AIs (OpenAI, Anthropic) outside the host session for a neutral second opinion on a roadmap, diff, prompt, or file set — or 'cross-check with another model'.
Skill Claude CodeCodex
ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous tool chain compositions via knowledge graph analysis, detects execution-level side effects (not just text output), and runs multi-phase trust exploitation campaigns that model real attacker behavior.
microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents
Skill Claude CodeCodex ✓ vendor
Operate the Foundry Toolbox and Foundry-hosted agents for the Fibey project: inspect, version, recreate, and smoke-test.
Skill Claude CodeCodex
Chain of Truth (CoT) workflow for AI-assisted software development. Validated artifacts as the Source of Truth (SoT) — not prompts. 7 phases: SRS → Product Structure (IA + Design System + User Flows) → HiFi Prototype → Data Model → UCIC → Implementation → Testing. Use when: building a new feature/application with AI…
arcayne/agentic-delivery-playbook
Skill Claude CodeCodex
Coding Agent Preflight for non-trivial coding work in Pi: classify direct/lightweight/full, lock goal/non-goals/risks/evidence, require approval when needed, and coordinate Pi goals/subagents with truthful routing. Use when ambiguity, risk, scope, or reviewability justifies a delivery contract; skip clear small direct…
Skill Claude CodeCodex
Set up, configure, run, and troubleshoot symphony-go — an autonomous agent orchestrator that polls Linear issues and runs Codex sessions. Use when the user asks to install symphony, create a WORKFLOW.md, configure Linear integration, start the orchestrator, debug stuck agents, fix failing hooks, tune retry/backoff…
Skill Claude CodeCodex
A coordinated team of ten agents for planning, auditing, designing, building, integrating, and assessing AI products using the Lean AI Methodology.
Skill Claude CodeCodex
Comprehensive Cline SDK skill for building AI agents. Covers the direct Agent runtime, ClineCore sessions, custom tools, plugins, events, LLM providers, scheduling, multi-agent teams, and production deployment. Use for any task involving @cline/sdk or its sub-packages.
Skill Claude Code
Level 2 — Pantheon-native context compression with priority scoring, semantic summarization, downstream-aware compression, budget allocation, and cross-references.
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 Code
Safety, privacy, cost management, and frank advice for building always-on AI agents with episodic memory. Covers data hygiene, privacy risk surfaces, runaway cost prevention, scope creep, psychological effects of persistent AI companions, and responsible deployment patterns. This is the skill that tells you what can…
Skill Claude CodeCodex
Govern an AG2 multi-agent network — identity (Passport, Resume), per-agent Rule with two top-level blocks access (AccessBlock) and limits (LimitsBlock, which nests RateBlock + InboxBlock), the swappable HubArbiter / RuleBasedArbiter access-&-routing seam, AuthAdapter / AuthRegistry registration, channel-level…
Skill Claude CodeCodex needs its repo
Update Agent Loop in the current repository from the official GitHub kit. Use when the user asks to update, upgrade, or refresh agent-loop.
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
Comprehensive system check for Mastra AI agent projects. Validates configuration, agents, workflows, memory, tools, prompts, and security across 66 rules organized by priority. Use when setting up new projects, debugging issues, reviewing code, or preparing for production deployment.
Skill Claude CodeCodex
Execute Codex CLI for code analysis, refactoring, and automated code changes. Use when you need to delegate complex code tasks to Codex AI with file references (@syntax) and structured output.
Skill Claude CodeCodex
Expert in agsync, the Git-native CLI that syncs skills, commands, and MCP tools across AI coding agents. You MUST use this skill when working on agent skills, commands, MCP configurations or agsync (agsync.yaml) directly.
Skill Claude Code
Multi-agent task system for complex tasks. Three-layer architecture (Skill + Code Graph + Memory), task lifecycle with validation, semantic search, drift detection. Use when: user requests PFC agent, complex multi-step tasks, multi-agent coordination, or mentions han.
Skill Claude CodeCodex
A skill that checks token usage and run logs before and after each automated work cycle. Tokens are the units used to measure an AI model’s input and output.
hansvangent/reflect-skill-claude
Skill Claude Code
Reflect on the current session and (1) extract durable learnings into CLAUDE.md / new skills, (2) propose targeted optimizations to existing CLAUDE.md / commands / settings based on what the session revealed, (3) compress CLAUDE.md against codebase truth when it has grown bloated. Phase 1 saves immediately; Phases 2…
Skill Claude Code
Orchestrate multiple worktree agents. Spawn, monitor, communicate, and merge.
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.
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: