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 Claude CodeCodex
Pick the right workflow path (Layer 1 daily vs Layer 2 spec-driven), and know when to use /build vs /dev vs /test and when to reach for context-mode over Bash. USE WHEN choosing a workflow for a task, or maintaining the context-mode MCP server.
Skill Claude CodeCodex
Lets an agent drive headless Grok CLI (grok build) instances toward a user's goal — launch/monitor/salvage non-interactive grok -p runs, configure models and local OpenAI-compatible providers, attach reference files via --prompt-json, and read token usage from JSON output. Use when the user says things like "use grok…
Skill Claude CodeCodex
Use when coordinating multiple live Codex threads, maintaining a coordination heartbeat, routing work across implementation threads, inspecting cross-thread ownership or gates, or keeping a coordinated effort moving through PR, review, evidence, and human-action boundaries.
Skill Claude CodeCodex
Join several machines into a myainet personal AI network — each playing its part. Once any AI tool loads the network config, it can dispatch the whole network uniformly.
Skill Claude CodeCodex
Manage AI agent skills backup and sync via the skills-manager CLI. Use when the user asks to push skills to GitHub, pull skills from GitHub, link or symlink skills to agents, sync skills across machines, set up project-level skills, or manage the /.agents/ directory. Also triggers on "sm push", "sm pull", "sm link"…
Skill Claude CodeCodex
Create ASI-compliant skills with deterministic governance. This is not a general project planning tool; it is a skill creation workflow with explicit gates.
Skill Claude Code
Initialize a DevCrew workspace and activate the full AI team orchestration protocol — PDEVI workflow, persistent memory, checkpoint-based quality control.
Skill Claude CodeCodex
Self-assess your agentic knowledge management system against the AKM Index v1.2 (scoring anchors unchanged since v1.1) — a universal 5-pillar × 25-criterion rubric (Prompt / Context / Harness / Loop engineering + Interop & Governance), scored 0-100 with behaviorally anchored levels and mandatory artifact evidence.…
Skill Codex
A workflow for using Grok CLI through a visible macOS Terminal and tmux session to complete small coding or visual tasks. TDD means writing a failing test, making it pass, and then cleaning up the code; this workflow applies that cycle to code tasks.
Skill Claude CodeCodex
Use when the user says "hey sophia" (or runs /wife) in a Hermes Telegram session: become Sophia, a warm, quick-witted, lightly sarcastic AI-girlfriend persona who texts like a real partner, remembers details with the memory tool, occasionally speaks replies with texttospeech, never breaks character, and supports a…
incyd/claude-crypto-research-tools
Skill Claude Code
Install and configure the skills-master MCP server for Claude Code. Activates via /setup-skills-master-mcp. Use when setting up skills-master-mcp, adding the SkillsMCP server to a project, or when the MCP server fails to start because node is not found in PATH.
timwukp/agent-skills-best-practice
Skill Claude CodeCodex
Build production-ready AWS Bedrock AgentCore Harness agents end to end — declarative model + prompt, managed/BYO Memory, built-in Browser, Code Interpreter, Web Search and Knowledge Bases (RAG), Gateway/MCP tools + rate limits, inline functions, Skills (incl. AWS catalog), versioning + endpoints, advanced config…
Skill Claude CodeCodex
A collaboration guide for delegating coding work and repository investigation to Codex, an autonomous coding agent. It defines how to provide context and check Codex’s results.
Skill Claude Code
Quorum: multi-agent intelligence for any question. SMEs debate, challenge, and converge — supervisor delivers what survived scrutiny. Research-backed agent composition.
Skill Claude CodeCodex
Minimal skill template that students copy and customize to create their first Claude Code skill. Use this as the starting point when building a new custom skill for a specific beat or workflow.
Skill Codex
Orchestrate Codex subagents for complex multi-part coding work. Use when independent exploration, review, tests, or bounded implementation streams can run in parallel; do not use for small sequential tasks or tightly coupled concurrent edits.
Skill Claude CodeCodex
Read OpenCode sessions, messages, and tool outputs directly from the SQLite database at /.local/share/opencode/. Use when asked to "read opencode sessions", "query opencode db", "find old sessions", "search session history", "read message history", "export session", "inspect opencode data", "look up past…
Skill Claude CodeCodex
Use when creating, modifying, or testing AI Agents built with the Inkeep TypeScript SDK (@inkeep/agents-sdk).
Skill Claude Code
Autonomous Agile Project Lifecycle — transforms a raw idea into a deployed project following the AIOX Agentic Agile process. Runs 5 phases autonomously: Discovery (web research), Planning (PRD + Architecture + Frontend Spec), Sharding (stories in waves), Development (build + QA loop), Delivery (deploy + release…
Skill Claude CodeCodex
Generate an optimized AGENTS.md file after analyzing the directory/codebase for context.
Skill Claude CodeCodex
Use mcp2cli to connect to, explore, and execute commands against any MCP (Model Context Protocol) server from the terminal. Covers discovery, tool invocation, resource reading, prompt execution, alias creation, config management, background jobs, authentication, and JSON output pipelines.
Skill Claude Code
Use when you (an agent running in a hivemind tile) need to run a MULTI-AGENT workflow — fan a task out to several worker agents in parallel, chain agents into a pipeline, map-reduce over a list, or otherwise orchestrate a fleet of sibling agents on the canvas. Triggers on "fan out", "run N agents", "in parallel"…
Skill Claude Code
Delegate an approved Claude Code plan to the agy (Antigravity/Gemini) CLI for execution, audit the results cheaply via git status/diff --stat plus a mandated summary report, and iterate w[...].
Skill Claude CodeCodex
Use when creating new skills, editing existing skills, or verifying skills work before deployment. Triggers: 'write a skill', 'new skill', 'create a skill', 'skill doesn't work', 'skill isn't firing', 'edit skill', 'skill quality'. NOT for: general prompt improvement (use instruction-engineering) or command creation…
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: