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.

Guided component creation with proper patterns

Review existing UI for issues and improvements

Initialize a design system with tokens

Generate unit tests for Python, JavaScript/TypeScript, and React code with mocks, edge cases, and coverage gap analysis

Turn a recorded product demo into a prioritized backlog with timestamped evidence.

Turn one screen recording of a bug into an evidence-backed GitHub issue draft (quote, frames, OCR identifiers, wall-clock; silent recordings work too).

Walk a recording's remarks against system logs using wall-clock timestamps.

Turn a recorded meeting (audio is enough) into action items, decisions, and open questions with timestamps.

Turn a recorded workshop or design walkthrough into a structured spec with quoted decisions and open questions.

Turn a narrated screencast into precise, evidence-backed findings JSON (bug / feature / question routing with frame evidence).

Generate and enforce policy gates for AI coding agents (Copilot, Claude Code) — real-time session hooks that deny protected-path edits and dangerous commands, plus a merge-time backstop for anything that bypasses them. Use when asked to "govern AI agents", "block AI from touching secrets", "add an AI policy gate", or "why did the AI agent hook not fire".

Show the active planning-with-files plan (id, mode, attestation, current phase, phase counts)

Start planning-with-files (task_plan.md, findings.md, progress.md); flags --gated, --autonomous, --template analytics, then an optional plan name

Run a paid-ads (ROAS) workflow: audience segments, account structure, ad creative, experiment design, pre-launch signal QA + the account-audit gate, measurement, and attribution. Not sure? Use /aaron-marketing:auto.

Natural-language front door to the marketing pack (narrative/TALE, SEO/GEO/SITE, social/ECHO, email/SEND, Paid Ads/ROAS, influencer/STAR, launch/RAMP). Use when a marketing goal is open-ended or spans disciplines, when it is unclear which skill fits, or for requests like 'help with our marketing', 'grow our traffic', 'plan our launch', 'what should we post', 'is our messaging landing' — it infers the discipline and runs the smallest useful workflow. Add --deep for exhaustive, maximum-rigor, or stress-test runs.

Run an email-marketing (SEND) workflow: deliverability/consent setup, segmentation, email creative, lifecycle flows, newsletter monetization, send-testing, and the email-quality audit gate. Not sure? Use /aaron-marketing:auto.

Run an influencer-marketing (STAR) workflow: audience & creator scouting, campaign targeting, briefs, outreach, amplification, and ROI reporting. Not sure? Use /aaron-marketing:auto.

Run a product-launch (RAMP) workflow: positioning and launch tiering, window/early-access design, message house and asset kits, the launch-readiness gate with a T-1 go/no-go, launch-day execution, and the post-launch prove loop. Not sure? Use /aaron-marketing:auto.

Run a brand-narrative & messaging (TALE) workflow: trace the current message and positioning truth, architect the durable message house/voice/story canon, land it consistently across every surface, and evaluate resonance with tests and drift monitoring. Not sure? Use /aaron-marketing:auto.

SEO/GEO end-to-end along the SITE loop: survey demand and competitors, implement content, tune quality/tech/on-page, and evaluate authority/rankings/reports/memory (--phase survey|implement|tune|evaluate). Not sure? Use /aaron-marketing:auto.

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding