LLM Mart Basic

Flutter Riverpod app architecture and Windows installer delivery. Use before changing a Riverpod Flutter app/package or its Windows desktop packaging/update pipeline; skip non-Riverpod stacks and pure-Dart work.

Review PR, branch, commit or working-tree changes for concrete defects and fidelity to intended behavior. Also use when explicitly asked to independently challenge a prepared plan, diagnosis or verification claim.

Design or review module ownership, public interfaces and abstractions; UI token/component ownership; or domain-driven models, bounded contexts and invariants. Use for structural decisions, not routine edits within an established owner.

Prove real user journeys across browser, mobile, desktop, API and CLI surfaces using the project's existing test tools. Use for end-to-end verification, runtime UI review or requested visual proof.

Apply Hard Eng's planning, project context, verification and gate-adaptation guidance when implementing or reviewing code in an installed project.

Implement and verify a ready, authorized plan through focused fixes and integrated checks, ending with a ready-for-ship handoff. Use for implementation, bug fixes or resuming build work; skip planning-only, review-only and shipping-only requests.

Prevent verified repeated failures and preserve lasting decisions in terse ADRs. Use when failures recur, prevention needs strengthening, or accepted decisions and steering need durable capture; skip ordinary one-off fixes and routine task updates.

Plan a change before implementation, resolve material user decisions and prepare repository-grounded UX references. Use a compact plan for small changes; route large, unclear efforts or explicit Wayfinder requests to Wayfinder. Skip explanation-only requests and execution already

Deliver a verified build through a task branch and PR, check the intended remote result, and clean up the completed task safely. Use for PR creation, shipping, merging or release/deployment requests; skip planning, implementation and review-only work.

Make a voiced product marketing or explainer video from real product screens. Script, cut walkthrough clips or stage app screenshots with a cursor, pick voice takes, render branded motion graphics and diagrams, mix music and review every second before delivery.

Investigate a codebase, compare tools or approaches, verify current external or library facts, and research failures before making a substantive technical recommendation. Use for sufficiency and gap reviews; ordinary edits with settled requirements do not need a research stage.

Review authorized application code, configuration, designs or artifacts for concrete authorization, data exposure, injection, secret, dependency and LLM/tool security risks. Use for a requested security review or a change affecting a trust boundary.

Write, revise or review an agent skill (SKILL.md package).

Use when explaining System V AMD64, ARM AAPCS, RISC-V psABI, stack frames, variadic calls, or FFI register rules. Not for the Rust FFI binding layer: use rust-ffi.

Use when the user wants to classify abstractions as useful, bad, or busy and keep one shallow level. Not for tasks requiring source or remote-system changes.

Use when configuring ADC sampling time, DMA-driven ADC, calibration, or DAC channel setup on bare-metal MCUs. Not for the DMA stream itself: use dma-baremetal.

Use when creating AF_XDP sockets, configuring UMEM and XSK rings, writing an XDP redirect program, or choosing copy versus zero-copy mode. Not for full kernel bypass: use dpdk.

Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.

Use when asked to audit or repair agent surfaces (plugins, agents, skills, CLAUDE.md/AGENTS.md, docs, prompts, commands, hooks) or improve one skill at depth. Not for agent grading: use skill-doctor.

Use when a redacted, trimmed agent transcript must be appended to a GitHub PR or issue body, with human approval and preview. Not for automated or model-initiated insertion.

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.

Shows status of the Supabase local development stack.

Stops the Supabase local development stack.

Manage vanity subdomains for Supabase projects.

Configure Tavily MCP server credentials

Run Rigor Explore on top of current_research using the current compatible slug.

Run Rigor Reproduce on this repository using the current compatible slug.

Run Rigor Analyze on this repository using the current compatible slug.

Run Rigor Debug on a research repository failure before patching.

Runs the Open Steps install check and reads the result back in plain words. Use it after installing the pack, when a report never appears, or when someone asks whether the install is sound. The script does the checking and sets the exit code. This command reports what the script printed and nothing else.

`crabbox exec` executes a command on a supported existing lease without syncing files,

List the preflight names accepted by this installed Crabbox binary, their

Редакторский аудит русского текста без переписывания

Редактура русского текста с сохранением смысла и голоса автора

Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.

Run the one-command quality gate and report the real N/N result. Use before claiming any build/review is done.

Interrogate the brief before a line is built — ask only the questions whose answers change the work, and put every unasked decision on the record as a stated assumption.

Scaffold a new design-product project that matches the recommended Claude Code layout (the reference structure). Use when starting a fresh product/app that will be built with this design system.

Pre-release gate — run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.

Run every objective gate this project can prove and report the real N/N. Use before claiming any screen or component is done.

Create API connector tools for AG2 agents with auth handling, pagination, rate limiting, and error mapping

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts.…

A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for ma…

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-class AI agent UX.

同花顺官方 A股金融数据服务，提供股票实时行情、历史行情、财务报表、指数、板块、涨停等数据，适用于 AI Agent、量化研究和应用开发，支持 API、MCP、CLI 和 Python。Official Tonghuashun (HiThink) A-share financial data service provi…

Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 15+ more databases like DuckDB, ClickHouse, Redis and Firestore. Built-in MCP server…

🤖 Local-assist BOSS Zhipin CLI for AI agents — search, welfare filtering, shortlist, JSON-envelope output; low-risk & compliant by default.

The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives your live graph: edits,…

Persistent memory for Claude Code — identity, context, and continuity across sessions

🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI…

A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Lo…

World Memory Protocol.

Run your own organization of agents.

The most RAM efficient harness

AI-native, free, open-source alternative to Jira, Trello, ClickUp & Monday. Built for Scrum teams where humans and AI agents collaborate as equals — on the same…

Free open-source desktop app that scrapes JAV metadata and generates NFO + cover art for Jellyfin, Emby & Kodi. No Docker, no CLI — one-click install on Windows…

A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync ever…

天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限，基于认知虚拟机 (CVM)、自感知层和信息素（Stigmergy…