LLM Mart Basic

Turn SOP, policy and regulatory documents into human-verified Open Knowledge Format (OKF) bundles — every claim carries its source span. Desktop app + CLI + MCP…

A curated collection of 150+ specialized AI Skills for software development, frontend, backend, automation, UI/UX, SEO, and DevOps. Each skill encapsulates a f…

Craft long-form generative art for onchain platforms — Art Blocks, 256ART, Verse, Highlight, Plottables, bootloader.art, or a self-hosted drop — and for screen diffusion channels such as Artpoint. Covers hash-seeded determinism, resolution-agnostic rendering, features and rarity

Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server. Use when the user asks how far, how long, how to get somewhere (car, transit, bike, foot), what is near a place, or about the weather in a Chinese city.

Compare two to five options — products, plans, places, tools, offers — on the criteria that matter to the user, in a table the user can re-weight, with a recommendation. Use when the user asks which to pick, for a comparison, or "X vs Y".

The user's 飞书 / Lark through its command-line tool (lark-cli) — agenda, people and groups, reading and sending messages, events, tasks, documents — with no app open. Use when the user mentions 飞书, Lark, a 群, a 日程 or a 飞书文档, or wants a colleague told something.

Go through recent mail and sort it into needs-a-reply, waiting-on-others, to-do and can-ignore, with draft replies ready for review. Use when the user asks to triage, sort, catch up on or clear their inbox — never to send anything on its own.

Where a parcel is, when it will arrive and what a shipment would cost, through the 快递100 MCP server — any Chinese courier (顺丰, 京东, 中通, 圆通, 韵达, 邮政 and more) from a tracking number. Use when the user asks 快递到哪了, 什么时候到, 查一下单号, or how much it costs to send something.

Prepare for a meeting — who is in it, what was last said with them, what the user owes them and wants from them — as a one-page brief. Use when the user asks to prepare for or get ready for a meeting, a call or a visit; a trigger can run it before every meeting with a client.

Read and answer messages in the chat apps on the user's phone (微信 and the like) through the screen — catch up, draft a reply in the user's voice, send only text they confirmed. Use when the user asks what someone said on WeChat or wants a chat answered.

The user's 腾讯会议 via the official tmeet CLI — upcoming meetings, creating, changing or cancelling one, inviting people, then the recording, minutes, transcript and attendance. Use when the user mentions 腾讯会议, a 会议号, a 会议链接, 纪要 or 录制, or wants a meeting set up or looked up.

Trains in China through the 12306 MCP server — routes, dates, options, connections and stops with no screen; booking only on the user's word, in the 12306 app on their phone, stopping before payment. Use when the user asks about 火车票 / 高铁 / 12306 or a train between two cities.

Plan a trip end to end — itinerary by day, a packing list to tick off, a budget, and the calendar checked for conflicts — as pages in the workspace. Use when the user is going somewhere for more than a day and wants a plan, an itinerary or a packing list.

Look back at the past week and set up the next one — calendar, mail, goals and files in one page, with a short plan. Use when the user asks for a weekly review, a week in review, "how did my week go" or to plan next week.

Подготовка русского текста к проверке системой «Антиплагиат» (antiplagiat.ru, «Антиплагиат.ВУЗ»): оценка доли «ИИ-сгенерированного» текста по фрагментам в духе модуля ИИ-детекции, переписывание подсвеченных абзацев своим голосом, чистка технических артефактов, из-за которых докум

Аудит и правка русских текстов от признаков ИИ-генерации («ИИ-стиль», канцелярит, кальки с английского, шаблонная структура). Используй, когда просят «убрать ИИ-стиль», «очеловечить текст», «почистить от нейросетевых штампов», «проверить, не звучит ли как ChatGPT», «вычистить кан

Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.

Convert a grover_base checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a randomly-initialized cMIM decoder + latent_dist, then continue pretraining on the user's corpus as hybrid (vocab + contrast). Effectively kermt-continue-pretrain with a o

Continue KERMT pretraining on a custom SMILES corpus with a grover_base, cmim, or hybrid checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized training and write model bundles, prepared data, l

Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized embedding extraction and write model bundles, per-readout .npy embeddings, c

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.

One-screen inventory of skills, agents, commands, MCP servers, and hooks counts.

List the file-based memory store grouped by project (auto-memory) plus the CLAUDE.md files.

Show current Claude Code spend versus a budget number

Quick month-end spend projection from the daily trend

List the most expensive sessions pushing your spend up

Print the Agent Monitor dashboard URL and how to start/open it

Check Agent Monitor reachability and print UP/DOWN with latency

One-line Agent Monitor health + counts summary from /api/stats

Quick connectivity + health probe of the Agent Monitor dashboard.

Export Agent Monitor data (sessions/events/analytics/costs/all) as json/csv/md.

Show the latest N ingested events with timestamp, event_type, and tool_name.

List current cost and token outlier sessions via z-score

Compare two sessions side-by-side with cost and workflow deltas

Surface the top 3 data-backed insights about your Claude Code usage right now

Read-only inventory of CCAM alerts, webhook targets, and remote sources

CCAM platform status across hooks, config, updates, and MCP prerequisites

One-screen focus snapshot — avg turn duration, thinking-block usage, and longest sessions.

Quick daily standup from today's Claude Code sessions — grouped by project, with cost and errors.

Suggest the next action from your most recent in-progress sessions and recent errors.

List the most recent APIError events with their session and a summary

AI coding platform for teams

AI Multi-Agent Framework in .NET

Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs

UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight & extensible, works with any harnesses, any models,…

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support. Built with Tauri + React.

OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. Scheduled tasks support.

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

Exposes internet search tools for use by LLM-backed Assist in Home Assistant

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

Versus Incident is the self-hosted AI SRE agent. It learns what your system normally look like and escalates only what is new or unexpected issues — routing to…

Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.

Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework.

AgentiLoop Agent! An Autonomous Agentic Agent for Mac, and exclusive Apple only harnesss. Suppprtd automation, scripting, coding, build anything and more. Power…

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex