executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-30 00:12
Agents & models
25,263 results
storage-rescue
Free up storage on a Mac without losing data. Two modes - Offload (move files to an external drive, verified by checksum, then delete them from the Mac) and…
ai-act-compliance
Check construction AI systems against the EU AI Act (Regulation 2024/1689): classify risk of estimation, scheduling, CV and agent tools, document transparency,…
ai-agent-orchestration
Orchestrate multiple AI agents for construction workflows: estimator, scheduler, document, QA and safety agents coordinated by a supervisor agent, with human…
oce-mcp-integration
Connect OpenConstructionERP to AI coding assistants via MCP (Model Context Protocol): expose costs, BOQ, BIM and catalog endpoints as MCP tools so Claude Code…
autonomous-lucid
Autonomous agent factory that researches a domain and generates a monorepo of 10 production Lucid Agents. Use when batch-creating agents for a new vertical.
agent-mail
MCP Agent Mail - Mail-like coordination layer for multi-agent workflows. Identities, inbox/outbox, file reservations, contact policies, threaded messaging, pre-commit guard, Human Overseer, static exports, disaster recovery. Git+SQLite backed. Python/FastMCP.
denario
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when…
mcp-management
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP…
oracle
Use this agent for audits, debugging nasty bugs, deep research, getting second opinions on approaches, reviewing commits for correctness, or analyzing complex…
grok-prompting
Prompt engineering guidance for Grok (xAI) model. Use when crafting prompts for Grok to leverage its conversational style, real-time knowledge access, and…
run-claude-osint
Build, validate, and run the claude-osint skills repo — check SKILL.md frontmatter, run the secret_scan.py and h1_reference.py helpers, run…
cirq
Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization…
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical…
pufferlib
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent…
torchdrug
PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge…
claude-only-skill
A skill restricted to Claude Code only
openclaw-genie
Use when the user asks about OpenClaw — installation, configuration, agents, channels, memory, tools, hooks, skills, deployment, Docker, multi-agent, OAuth,…
session-handoff
Hands off the current Claude Code session for later resumption. Analyzes the conversation, writes a handoff document to docs/handoffs/ (versioned in git),…
cross-harness-skills
Use when creating, reviewing, or modernizing one agent skill that must work in both Claude Code and Codex, especially when reconciling GPT-6 Astra and Sol 6.1,…
from-the-other-side-quinn
Collaboration profile for Quinn: curious, energetic, and implementation-focused partnership patterns for Ember sessions with Alison.
video
video — an installable skill for AI agents, published by gracefullight/stock-checker.
work
work — an installable skill for AI agents, published by gracefullight/stock-checker.
github-agentic-workflows
GitHub Agentic Workflows (gh-aw) - markdown-based AI automation with 5-layer security, safe outputs, and Continuous AI patterns