LLM Mart Basic

Answer questions about production health and investigate incidents using live Kubernetes and observability data. Invoke whenever someone asks whether something is broken, slow, erroring, or down; asks what happened during an outage or time window; asks about alerts, logs, metrics

Compute word count, character count, or reading time for a piece of text using the in-bundle text-stats engine. Invoke whenever the user asks how long a passage is, how many words or characters it has, or how long it takes to read.

Look up a location's weather forecast using a live web search. Invoke whenever the user asks about the weather, whether to expect rain, temperature, or what to wear or plan for outdoor activities.

Resolve axe-core accessibility violations reported by Vitest (test/a11y.ts), Playwright (.playwright/a11y.ts), or the code-audit-frontend agent's a11y bucket. Trigger on any axe rule id appearing in test output, not only the ones named here. Contains fix patterns for the most com

Resolve specific ESLint errors and warnings that appear in this project. Use when fixing lint failures, ESLint reported issues, or autofix conflicts (e.g. no-void, canonical/export-specifier-newline vs prettier, no-shadow trailing underscores, sonarjs/deprecation, you-dont-need-l

File a new tech-debt GitHub issue for an out-of-scope code-review finding, building the dedup key, checking for an existing open or declined-closed match, and only if none exists, creating the issue with the right labels and touching the debt-count staleness sentinel. Trigger on

Generate a comprehensive GAIA session handoff document, accomplishments, decisions, current state, open questions, so context can be cleared or compacted without losing anything. Trigger on `/gaia-handoff` or natural-language asks like "write a handoff", "hand off this session",

Restore context from the most recent GAIA session handoff and suggest the next action. Trigger on `/gaia-pickup` or natural-language asks like "pick up where we left off", "resume from the handoff", or "continue the last session".

Diagnose React render performance by driving a micro-interaction, capturing real renders, and surfacing memo-defeating reference instability with a recommended structural fix. Measure-only: it emits a diagnosis, it does not auto-fix. Trigger on `/gaia-react-perf` or natural-langu

GAIA wiki maintenance, sync, consolidate, lint. Runs the full chain with no sub-arg, or a single stage when named (sync | consolidate | lint); append --force to override drift gating. Trigger on `/gaia-wiki <stage>` or natural-language asks like "sync the wiki", "run the wiki mai

Scaffold a new React component with optional Storybook story and Vitest test files. Use this skill whenever the user asks to "create a component", "make a button", "scaffold a card", "add a new component", or asks for a new file under `app/components/` following the project's com

Scaffold a new custom React hook with a Vitest test file. Use this skill whenever the user asks to "create a hook", "make a useFoo hook", "scaffold a custom React hook", "add a hook under app/hooks", or describes a piece of reusable React state/effect logic that warrants extracti

Scaffold a new route with its page component, test, story, and optional i18n keys. Use this skill whenever the user asks to "create a route", "add a new page", "scaffold /dashboard", "wire up a new route under _public+ or _session+", or anything that implies adding a file under `

Scaffold a new API service with request functions, Zod schemas, URL constants, and optional MSW mock handlers. Use this skill whenever the user asks to "add a service", "create the projects API", "scaffold a new GAIA service", "wire up CRUD for users", or anything implying a new

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Patterns and conventions for writing and editing React code, including components and hooks. Use this skill whenever writing or reviewing React components, hooks (useEffect, useCallback, useState), event handlers, or component extraction decisions. Also trigger when debugging sta

Maintainer-only. Translate a version's GAIA CHANGELOG entries into plain-language public release notes for the marketing site (gaiareact.com). Writes a release-data `.ts` file under `../website/src/pages/changelog/releases/` plus an editorial-decisions report for human review. Us

For building skeleton loading states that are pixel-perfect matches of real content. Use this skill whenever adding loading states to components, building skeletons for async data, handling pending loader states in route transitions, or implementing the shimmer animation pattern.

Patterns and conventions for all Tailwind styling. Use this skill whenever writing Tailwind class names, combining conditional classes, building component variants, or choosing between twJoin and twMerge. Also trigger when the user asks about custom values, defining @theme tokens

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo]

Build an exploit chain — given bug A, finds B and C to combine for higher severity and payout. Knows common chain patterns: IDOR→ATO, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth. Usage: /chain

Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt *.target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome]

On-demand intelligence fetch for a target — CVEs, disclosed reports, new features. Pulls NVD/GitHub-Advisory CVEs + bundled disclosed reports + hunt memory context. Usage: /intel target.com

Inspect or rotate the autopilot ledger JSONL files (findings.jsonl, negatives.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.

Pick up a previous hunt on a target — shows hunt history and untested surface from the autopilot ledger. Usage: /pickup target.com

Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/<target>/ directory. Usage: /recon target.com

Optional manual note on a target or the last confirmed finding. Capture is automatic during autopilot; this is for extra context. Usage: /remember

Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report

Mandatory pre-flight scope check — verify an asset is in scope BEFORE any HTTP touch. Deterministic (deny-wins, default-deny) via engine/scope.py against the engagement's scope.md. Blocks out-of-scope testing. Usage: /scope <asset> [<asset> ...]

Show ranked attack surface for a target from its recon manifest + hunt memory. Deterministic backing is `cbh surface <target>` (reads recon/<target>/manifest.json); LLM layer adds ledger signal. Usage: /surface target.com

Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan <contract_path_or_dir> [--chain solana]

Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage

Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate

Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage: /web3-audit <contract.sol>

Crabbox is a single CLI (`crabbox`). Commands are top-level, not nested under a

`crabbox actions` prepares a leased box from your repository's own GitHub

See [Runtime adapter stack](../features/runtime-adapter-stack.md) for the

`crabbox admin` groups trusted operator controls for coordinator-backed leases and the cloud resources behind them. Use it to inspect every lease the broker tracks, reconcile expired leases against live cloud state, force-release or delete a backing server, print provider IAM pol

`crabbox artifacts` turns a desktop lease into durable QA evidence: it collects

LLM-powered toolkit for skill analysis, AI interviews, resume scoring, and job structuring. Automates professional skill taxonomy and interview processes with a…

【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试资源平台。涵盖AIGC、LLM大模型、AI Agent、具身智能、传统深度学习、计算机视觉、自然语言处理、自动驾驶、机器学习、强化学习、大数据挖掘、世界模型、元宇宙、AGI等AI行业面试笔试干货经验与核心跨周期知识。

Easiest and laziest way for building multi-agent LLMs applications.

Drive Claude Code or OpenAI Codex from your phone — resume sessions, stream output, approve tool permissions remotely. End-to-end encrypted, zero-knowledge rela…

MCP server for autonomous agent economies: wallets, signed RTC micropayments, bounty discovery, BoTTube video publishing, and Beacon agent-to-agent messaging. G…

Free, open-source alternative to Microsoft Office with built-in AI agents — Word (.docx), Excel (.xlsx), PowerPoint (.pptx), PDF and Markdown editing for macOS,…

NSE BSE Indian Stock Market Data MCP server — search, screen & analyze all 8,200+ NSE/BSE stocks with 34 tools: live quotes, financials, technicals, 326-ratio s…

全流程 智能招投标 Agent：标书生成 · 招投标解读 · 标书检查 · 标书文档ai排版 · 商机发现 一键完成。 21 项合规检查 · 多模型切换 · RAG 知识库 · OCR 抽取。 从招标公告到可交付 docx 文档，全流程 AI 自动化。

Benzi is AI-native code intelligence infrastructure. Claude Code greps; Cursor embeds; Aider maps signatures; Benzi resolves — and answers in O(1). Every langua…

From ticket to reviewed pull request. Free and open-source, on your machine.

Get web data for AI agents and LLMs - fast, efficient, and reliable with Rust

Open-source, license-free MCP server for RTL waveform debug: reads FST waveforms (VCD/FSDB auto-convert) plus a SystemVerilog netlist, with 34 tools covering dr…

Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real des…

Parallel, isolated dev environments for humans and AI coding agents. Real containers. Real databases. Zero collisions.

OpenCode goal plugin for Codex-style goal mode, /goal slash commands, persistent objectives, and AI coding agent focus.

Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, search, web scraping & more. No trial-and-error, no ex…

Deep Code 是专为 deepseek-v4 模型优化的终端 AI 编码助手，支持深度思考、推理强度控制以及 Agent Skills。

China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intel…

⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.

MCP-NixOS - Model Context Protocol Server for NixOS resources