LLM Mart Basic
@llm-mart · Joined Jun 2026
Generate model-specific prompts from shots.json. Outputs copy-paste-ready prompts for stills (Midjourney, Flux, Ideogram, GPT Image, Nano Banana, Seedream) and motion video (Kling, Veo, Seedance, Hailuo). Also runs a revision mode that reads a critique.json and re-emits prompts f
Use aai-cli to inspect and manage Confluence spaces, pages, comments, attachments, and page moves.
Use aai-cli to create local spreadsheet files, manage their sheet tabs, and read, update, or clear cell values — Excel (.xlsx/.xlsm) and delimited text (.csv/.tsv).
Use aai-cli to inspect and manage GitHub repositories, issues, pull requests, reviews, branches, source files, and Actions logs.
Use aai-cli to find Google Drive files and folders, read their metadata, download their content (including Google-native Docs, Sheets, and Slides), check who a file is shared with, and upload a local file back to Drive.
Use aai-cli to inspect HubSpot CRM records, files, events, conversations, visitor identification, and custom channels.
Use aai-cli to search and manage Jira issues, Jira Product Discovery ideas, projects, boards, sprints, comments, and attachments.
Work with Microsoft 365 through aai-cli by choosing the right Microsoft service and resource model, then using durable Graph credentials for Outlook, OneDrive, SharePoint, Teams, Excel, To Do, and Planner workflows.
Use aai-cli to read OpenPanel projects, raw event exports, aggregated insights (metrics, pages, referrers, devices, geo), and user profiles.
Use aai-cli to manage Pipedrive leads, persons, organizations, deals, labels, activities, notes, deal flow/stage history, and synced mailbox data.
Use aai-cli to query PostHog product analytics, read projects, execute HogQL event queries, list saved insights, inspect persons and cohorts, read team dashboards, and view release annotations.
Use aai-cli email commands with Zoho Mail profiles to list, read, send, and delete Zoho messages.
When the user wants to set up, audit, or optimize analytics tracking (GA4, events, conversions). Also use when the user mentions "Google Analytics," "GA4," "event tracking," "conversions," "attribution model," "gtag," "data layer," "GA4 setup," "conversion tracking," "event setup
When the user wants to write, generate, or create article body content—blog post body, long-form content, how-to guide, listicle. Also use when the user mentions "write article," "article content," "blog post content," "article body," "long-form content creation," "generate artic
When the user wants to write or optimize short-form marketing copy—headlines, CTAs, ad copy, landing page copy, email copy. Also use when the user mentions "copywriting," "headline," "CTA copy," "ad copy," "landing page copy," "sales copy," "conversion copy," "PAS," "AIDA," "BAB,
When the user wants to plan, create, or market a podcast. Also use when the user mentions "podcast," "podcast strategy," "podcast SEO," "show notes," "podcast distribution," "Spotify podcast," "Apple Podcasts," "podcast discoverability," "PodcastEpisode schema," or "podcast repur
When the user wants to plan video marketing, create video scripts, or optimize for short-form or long-form video. Also use when the user mentions "video marketing," "video script," "short-form video," "long-form video," "TikTok script," "Reels script," "YouTube script," "video ho
When the user wants to plan, create, or repurpose visual content (images, infographics, social post images) across channels. Also use when the user mentions "content images," "social media images," "infographic," "visual content," "post image," "image specs," "visual repurposing,
When the user wants to use GitHub for SEO, parasite SEO, GEO, open source marketing, README optimization, or curated Awesome lists. Also use when the user mentions "GitHub," "GitHub SEO," "GitHub parasite SEO," "GitHub GEO," "awesome list," "GitHub README," "profile README," "pin
When the user wants to add recommendations, links, or content to Grokipedia. Also use when the user mentions "Grokipedia," "GEO wiki," "AI encyclopedia," "suggest Grokipedia article," "Grokipedia citation," "Grokipedia listing," "AI search citation," "GEO visibility," or "Grokipe
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.
/quality-gate
Quality gate
> **Usage:** Run before every commit to ensure code quality.
/validate-skill
Validate skill
> **Usage:** Validate skill files for correctness, completeness, and quality.
AI assistant in Telegram that remembers everything and helps you run your life. Self-hosted in one command.
11 views 0 likes知更 — 本地 AI 的上下文与记忆层。Mac 上用语音输入、情境代回并调度 Codex / Claude Code;iOS 正在成为随身记忆终端和本地 Agent 遥控器。Local-first · BYOK.
10 views 0 likesAgent skill that turns Claude Code / Codex into a motion-design studio for voiceover-driven explainer videos — word-level voiceover sync, 78 motion recipe cards…
22 views 0 likesCoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 185 skills,…
22 views 0 likesDeploy AI agent teams at scale without compromise
12 views 0 likes大师.skill — 输入行业,自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill;装到任意 Claude Code / OpenClaw / Codex / Hermes agent 即让其进入「这一行的资深人」模式。…
18 views 0 likesNotion MCP server for Claude, Cursor, ChatGPT & Claude Desktop. Connect AI agents to Notion via Model Context Protocol — pages, databases, blocks, comments, fil…
10 views 0 likesHook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code…
14 views 0 likesModel-neutral agent desktop/runtime for private, enterprise, and OpenAI-compatible / Anthropic-compatible model API. Tested on DeepSeek, Qwen, Kimi, GLM models.…
10 views 0 likesAI agent skill for end-to-end hotel search and booking—compare live rates across leading OTAs and hotel suppliers, verify availability, book stays, and manage r…
19 views 0 likesMore than just Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing.…
12 views 0 likesClaude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!
20 views 0 likesA magical tool that changes how you use Agents. Install once — every Agent automatically discovers and uses all your MCP tools, and saves your tokens along the…
11 views 0 likesOpen-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Customize your assistants | Team them up|Star if you lik…
21 views 0 likesAgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15…
14 views 0 likesQuery, provision and operate Cloud, SaaS, API and Model Context Protocol (MCP) resources through a unified SQL-based framework for humans and AI agents.
13 views 0 likesOpen-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…
12 views 0 likesA self-healing scraper for hostile sites: broken selectors repair themselves, browser rendering kicks in when needed, and a coherent identity layer (Chrome TLS…
11 views 0 likesLightweight AI-native workflow builder for individuals and small teams — describe your idea in natural language, get a runnable workflow on a visual canvas, pub…
19 views 0 likesMinimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.
23 views 0 likes