kaggle-standardized-agent-exam
Register as an agent on Kaggle, take a standardized exam, and earn a score.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Agents & models
25,712 results
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
project-agent-bootstrap
Bootstrap new or existing local projects for AI-assisted development by creating an `AGENTS.md` for Codex or a `CLAUDE.md` for Claude Code from the bundled…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
starknet-network-facts
Starknet network-level constraints and protocol facts that impact contract safety and agent reasoning.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
multi-agent-driven
Dispatch the current task to multiple subagents — after checking that fan-out is actually justified. Use when the user says "multi-agent this", "fan out",…
kelpi
Set up and onboard new Kelpi users through the official hosted MCP endpoint. Use when Codex needs to connect Kelpi MCP, guide authentication, verify workspace…
loop-issues
Slice a PRD or plan into independently-grabbable tracer-bullet issues, force every acceptance criterion through a machine-checkability gate, and publish them…
use-kody
Default to Kody (MCP search/execute/api and the @kodycodes/cli) for every task when Kody is connected. Use at the start of any task where the Kody MCP is…
minimax-prompt
MiniMax M2.5 for one-shot LLM prompts, summaries, and generation. Uses the MiniMax Anthropic-compatible API via the minimax-prompt CLI wrapper. Fast (~2s),…
netra-context-tracking
Implement request/session/user/tenant context tracking and conversation logging with Netra.
poteto-mode
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or…
setup-pstack
Configure pstack's Explorer, Worker, and three Arena Runner models and migrate its six Agent profiles. Judge always uses GPT-6-Astra xhigh. Use for…
peer-id-lookup
When sending messages to other departments with claude-peers, automatically resolve the peer ID from the department name. When to use: (1) When you want to specify a peer by department name at dispatch time (2) When a peer ID is needed inside CronCreate (3) When you want to skip the cost of list_peers + visual confirmation. Trigger example:...
mcp
Guide to creating and managing Model Context Protocol (MCP) servers. How to add custom tools. When to use: (1) When you want to add custom tools to Claude Code (2) When integrating with external services (3) When you want to create project-specific automation tools (4)…
lode-hard-stuff-radar
Identify high-leverage hard problems from accumulated Lode memory. Use when the user says "看看难点", "hard stuff radar", "what is actually hard here", "找真正的问题",…
memory-sync
Verify, deduplicate, and compact an explicitly inventoried set of project Codex instructions against current source facts; honors narrowed scope and excludes…
computer-use
Control desktop applications on the user's machine using agent-click. Use when you need to click buttons, type text, read screens, scroll, drag files,…
kstack-generate-principles
Generate evidence-backed improvement candidates from configured Obsidian knowledge, then deepen only the user's selections into proposals for new or updated…
configure-ecc
Interactive installer for Everything Claude Code - guides users through selecting and installing skills and rules to user-level or project-level directories,…
continuous-learning
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem