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.

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

Lightweight Q&A about the project — answer from context and return, no routing, no state change.

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

Clean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.

Show the codeArbiter command catalog — the public command list and what each routes to.

Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.

Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.

Audit stale provenance-tracked docs on request. Report first; re-scout or re-baseline only for selected docs.

Build project context from an existing codebase through isolated scouts, resolve gaps, and preserve initialization gates.

Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff. A no-action close records a board note. Not for implementing a known fix, new features, or explanation-only questions.

Develop greenfield project context through a layered interview, preserve decisions, and initialize only after the required gates.

Verify the active host install, package, command ownership, enforcement, and harmless live-fire probe. Read-only.

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.

Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

Open a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority.

Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.

Implementation of Podlite markup language

Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP — storyboard, references, generat…

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.

本地优先的类飞书 Markdown 编辑器,内置可审改的 AI 助手 | Local-first WYSIWYG Markdown editor with a reviewable AI agent

A lightweight all-in-one terminal with 20+ protocols — SSH, RDP, SFTP, databases, Kubernetes and more. With a built-in autonomous AI Agent that plans and runs m…

一款专注于桌宠方向的AIAgent。特点是一键安装、功能齐全、极低开销、完全暴露上下文、全功能插件化、AI自主插件开发、永久唯一会话、类游戏引擎交互策略。具有极高的扩展性和拟人程度上限，非常适合想长期培养和自定义需求高的用户。

Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace MCP Server & CLI Tool

一个先接住情绪、再分析关系并给出可执行策略的 Codex 恋爱军师，内置心理、法律、社会、人文、哲学、婚姻家庭与性学知识库，支持多元关系。

AI-powered SRE platform — read-only infrastructure diagnostics with deep investigation, security governance, and team collaboration

An open-source AI desktop companion inspired by Cyrene, combining immersive Chat, personalized long-term memory, and an agentic Work mode.

A local-first AI agent with persistent memory, emotional intelligence, and a peer-to-peer skills economy.

The open-source, multi-agent alternative to Claude Tag. @ any agent, wherever work happens, your agents work alongside your team and each other, learning as the…

Simple LLM service identification - translate IP:Port to Ollama, vLLM, LiteLLM, or 60+ other AI services in seconds

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

Claude in Chrome, reverse-engineered and open-source. No domain blocklist. Any Chromium browser. Same 18 MCP tools, same performance.

Agent-native flight & hotel search and booking — MCP server, CLI, and Python/JS SDKs. Hundreds of airlines plus the major booking sites, with per-flight reliabi…

Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.

Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs l…

Privacy-first Codex skill for discovering, validating, completing, and tracking job applications