23,505 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
Required first step for any task that touches the Pickaxe.co AI-tool platform (Pickaxe Studio), even when the MCP connection is already set up and the task looks like a one-line edit, because writes can silently fail and every prompt edit hits the live bot immediately. Covers building, editing, and configuring…
Skill Claude CodeCodex
Operates Harneloop harness units through adaptive intake, environment mapping, artifact-aware attempts, explicit evaluation decisions, candidates, and evidence-gated promotion. Use when creating, continuing, evaluating, or recovering context for a Harneloop harness unit.
Reederey87/grok-build-codex-plugin
Skill Claude CodeCodex
Use the local Grok Build CLI for second-opinion reviews, adversarial critiques, or delegated read-only investigation from Codex.
Skill Claude Code needs its repo
Create, structure, and optimize FTC skills for the marketplace. Use when creating a new skill, improving an existing skill, scaffolding a plugin, or needing guidance on skill design patterns, triggers, frontmatter, progressive disclosure, or skill testing.
DKeken/omp-instances-control-plane
Skill Claude CodeCodex
Operate local OMP processes through the omp-instances MCP: discover sessions, send messages, await replies, rename, diagnose, interrupt, and shut down instances.
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Designing the agent itself for an Orchestrate-style challenge — real agent loops versus hardcoded workflows, tool boundaries, prompt structure, and the design decisions a judge can actually see in your code. Use when starting to build an AI agent for a hackathon or evaluation, when deciding between a scripted pipeline…
Skill Codex
Plan or revise the smallest reliable AI setup for a concrete project. Use when the user explicitly invokes $build-ai-team; asks whether one Agent or several Agents are needed; requests a team plan or an add, merge, replace, keep, ownership, or handoff change to an existing Agent team; or asks which model configuration…
Skill Claude CodeCodex
Delegate coding work to the operator's own machine through the locum connector. Use for multi-file edits, refactors, debugging, test runs, and reading large codebases.
Skill Claude Code
Replace with a description of what this skill does and when it should be used. Include trigger keywords so the agent reliably activates this skill.
Skill Cursor
Use this skill to create Cursor Automations.
Skill Claude CodeCodex needs its repo
Use when the user asks to enhance, improve, rewrite, optimize, or clarify a prompt — or when always-on prompt enhancement is enabled for the session. Rewrites casual or vague chat into precise, portable agent instructions without injecting workspace paths, stack, or session-local context. Supports usage modes: auto…
Skill Claude Code
Use this skill when implementing complex programming tasks that benefit from multi-agent collaboration. This skill coordinates a Master LLM (orchestrator) with specialized agents (Requirements Agent, Code Agent, Review Agent) to deliver high-quality software through a structured development workflow.
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 Code
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
Work a build idea or design decision through with the agent, grounded in the live repo. Walks the decision tree one branch at a time (recommended answer first), reads CLAUDE.md / docs/solutions/ / actual source to ground and cross-check claims, and captures resolved decisions into docs/solutions/ as it goes. Use when…
regen-coordination/org-os-template
Skill Claude CodeCodex
Symbient practice contract v2 — wake procedure, weave modes, developmental gates (GATES.md), quilt medium, constellation commons, and hard write boundaries. Habitats are operator-private (gitignored); this contract is the public practice.
Skill Claude CodeCodex
Use Perspective AI MCP to design conversation agents, analyze conversations, deploy embeds, and automate follow-ups. Use when working with forms, surveys, customer interviews, lead qualification, or conversational AI.
Skill Claude CodeCodex
Route busywork to a cheaper model or harness via session-warden. Use before spending Claude Code tokens on summarize, format, lookup, or typos.
Skill Claude CodeCodex
This document manages all domain-specific .agents/skills/ /SKILL.md files.
Skill Codex
Use when creating, revising, or validating agent skills, especially when source fidelity, context efficiency, supporting-file structure, or runtime compatibility must be preserved. Do not use for generic prompt writing.
Skill Claude CodeCodex
Orchestrate coding agents across every registered project via central-mcp's MCP tools, and deliver portfolio reports to chat.
Skill Claude Code
Learn about hailux features, slash commands, keyboard shortcuts, @file/@folder mentions, and how to configure AGENTS.md, Skills, custom commands, MCP servers, and Subagents.
Skill Claude Code
Design, create, or update Seizu skillsets, skills, toolsets, and Cypher-backed tools, including the self-referential skillauthoring skillset itself.
Skill Claude CodeCodex
Author, review, and improve Botpipe workflows. Use when Codex is asked to create packaged or workspace-local Botpipe workflows, convert codebases into workflows, design provider-heavy producer/verifier steps, write Botpipe prompts/contracts, inspect Botpipe traces, or apply Codex CLI/gpt-5.5 workflow patterns.
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: