ai-agents skills

FreePeak/devagent

Skill Claude CodeCodex

Dispatch implementation tickets through the DevAgent pipeline (worktree isolation, test gates, PR delivery) from any agent session.

Hans-Vader/squadjs-plugin-creator-skill

Skill Claude CodeCodex

Use when creating, writing, or scaffolding a new SquadJS plugin, adding a server-side feature to a Squad server via SquadJS, or deciding whether SquadJS can support a desired behaviour ("can SquadJS detect X / do Y on a Squad server?"). Covers the plugin lifecycle, the full event/RCON capability surface, and the hard…

Lucius1105/daihaowa-ai-parenting-expert

Skill Codex

A parenting coach for practical guidance about raising and teaching children from birth through age 18.

Hansweek/echo-guard

Skill Codex

A finalization guide for deliverables after corrections, rejected proposals, or requests to remove or replace content.

quantDIY/GERP

Skill Claude CodeCodex

Content Operating and Management System (Markdown-Native CMS).

agentdecksdk/agentdeck

Skill Claude CodeCodex

How to write a handover note when closing out a shift - use before filing one.

lizard-build/lizard-cli

Skill Claude Code

Core Lizard CLI usage guide. Read this before running any lizard commands. Covers the full app lifecycle (login, init, link, add, up, redeploy, logs, events, status, scale, restart, secrets, domains, run, ssh, metrics), the workspace → project → service model, managed addons (postgres, redis, s3 with auto-public…

panbergco/pi-peer-agent

Skill Claude CodeCodex

Manage resident peer agents: long-running monitors that live inside the pi session, tick on minute intervals, watch the main agent's work, and push findings back mid-turn. Use when the user asks to launch/stop/ask a peer, watcher, monitor, observer, sentinel, or auditor; wants standing review, drift/scope watching…

uvwt/agentdock-skills

Skill Claude CodeCodex

Use this skill before or during code changes and code review to enforce readable, restrained, maintainable code with low patch smell.

davidmosiah/fitbit-mcp

Skill Claude CodeCodex

Unofficial Fitbit data for AI agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Fitbit data or actions through an agent.

fmind/dot

Skill Claude CodeCodex

Automate Google Workspace with gws: schema-first calls, profile isolation, bounded reads, and verified Drive, Docs, Sheets, Gmail, Calendar, or Chat writes. Use for Workspace from the terminal.

robbyczgw-cla/web-search-plus-mcp

Skill Claude CodeCodex

Use the Web Search Plus MCP tools (websearch, webextract) for source-backed web research: current events, prices, release notes, docs and API references, arXiv papers, CVEs, local and shopping queries, and reading a specific page. Use when the user mentions "web search plus", "websearchplus", "wsp", asks which sources…

Bilal140202/the-lord-of-the-skills

Skill Claude CodeCodex

Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic…

V-Songbird/foundry

Skill Codex

Prepare and publish an explicitly requested Foundry plugin or edition release using its actual release branch, version owner and catalogs. Includes coordinated README and verification gates; never an automatic release trigger.

0xSoftBoi/suwappubot

Skill Claude CodeCodex

Build with the Suwappu REST API: cross-chain quotes, simulation, self-custody or managed swaps, managed-wallet portfolio/prices, Polymarket research and orders, Hyperliquid market research, and Morpho lending-market research.

jon-devlapaz/improve-perceived-value

Skill Codex

Diagnose and improve actual value and perceived value for products, services, offers, brands, and customer experiences. Use when a user wants to increase trust, quality perception, relevance, distinctiveness, desirability, ease, confidence, adoption, retention, or willingness to pay; audit why an offering feels weak…

a2uicatalog/a2ui

Skill Claude CodeCodex

Compose an A2UI payload (typed atom blocks) and render it into real HTML — a chart, dashboard, status board, decision tree, or any structured UI, once the right atoms are already known (see the a2ui-catalog skill for picking them). Use when asked to SHOW something rather than describe it, and the host can display HTML…

samrusani/AliceMemory

Skill Claude CodeCodex

Use Alice as the user's durable local memory. Load before answering from context, and whenever you learn something worth keeping across sessions.

metaforismo/serve-droid

Skill Claude CodeCodex

Stream, inspect, and control an Android emulator or physical device from a browser or agent.

justinstimatze/gemot

Skill Claude CodeCodex

Review code with multiple specialist subagents, then use gemot to find where they disagree and why. Requires gemot MCP server configured.

DanceNitra/agora

Skill Claude CodeCodex

Build a 2D dungeon game where AI agents cooperate, work on businesses, and an orchestrator (human) guides them — Phaser 3 + TypeScript + React + Node backend with LLM agents.

Feeless402/feeless402

Skill Claude CodeCodex

Pay for x402-priced HTTP APIs (HTTP 402 Payment Required) with feeless, sub-second Nano (XNO) micropayments from a self-custodied local wallet. Use when an API returns 402 Payment Required, when you need pay-per-call access to a paid endpoint, to compare payer cost across payment rails, or to send/receive/top-up Nano.…

SpecLeft/specleft

Skill Claude CodeCodex

Skill "docs" from SpecLeft/specleft, covering specleft cli reference, setup, workflow, quick checks and safety.

Omodaka9375/wake

Skill Claude CodeCodex

You are connected to a WAKE MCP server. WAKE (Will-Aware Knowledge Execution) is a post-mortem protocol for AI agents. Follow these instructions based on the user's role.