LLM Mart Basic

Desktop control - see the real screen, click, type, press shortcuts, scroll, drag and drive any native application (Windows / macOS / Linux X11 and Wayland) with the built-in `computer` tool. Use for anything a browser tab cannot reach (Office, IDEs, installers, system dialogs, l

General-purpose content production - articles, reports, social posts, newsletters, product descriptions, and docs - with channel adaptation and quality control. Use as the entry point for "write me content" requests.

Turn one long-form piece into LinkedIn posts, X threads, Instagram carousels, TikTok scripts, and emails. Use to multiply reach from existing content.

Compress long histories and documents into durable decision summaries without losing constraints, TODOs, or file paths. Use before long continuations, handoffs, or when context is getting large.

Extract structured data from contracts - parties, dates, amounts, obligations, deadlines, and renewal terms - into usable tables. Use to digest contract stacks.

Review commercial contracts - flag risky clauses, missing protections, and negotiation points. Use before signing or sending any agreement. Not a substitute for a lawyer.

Optimize landing pages, forms, CTAs, and funnels - diagnosis, hypotheses, and test plans. Use when traffic exists but conversions lag.

Write sales pages, ads, slogans, and persuasive copy using proven frameworks (AIDA, PAS, value-first). Use when words must convert, not just inform.

Write personalized cover letters and motivation messages that connect a candidate's story to a specific company and role. Use alongside tailored CVs.

Critically review code, plans, or agent output for bugs, security issues, missing tests, and weak assumptions before delivery. Use before merging, deploying, or sending user-facing results.

Keep the CRM clean - log activities, update deal stages, maintain contact data in HubSpot, Salesforce, or a workspace CRM. Use after every sales interaction.

Schedule reminders and recurring tasks.

BTC / ETH / SOL swing skill for the Trading Agent OS. Technical + sentiment + vol cap; no fake token fundamentals.

Build ICP and buyer personas - pains, goals, objections, triggers, and watering holes - from real evidence. Use before messaging, targeting, or content planning.

Generate professional, ATS-compatible CVs from career information - structure, achievement phrasing, and clean formatting. Use to create or rebuild a CV.

Adapt an existing CV to a specific job offer - keyword alignment, reordering, and emphasis, without fabrication. Use for each serious application.

Plan and execute source→target data migrations with mapping, transforms, reconciliation, and cutover checks. Use for CRM/ERP/DB moves.

Audit data protection and privacy - PII/PHI handling, encryption at rest and in transit, retention, logging of sensitive data, tenant isolation, and GDPR/CCPA obligations. Use for /vault, privacy reviews, or compliance-driven data audits.

Detect duplicates, missing values, schema drift, and inconsistencies across datasets. Use before migrations, reporting, or model training.

Explore PostgreSQL, MySQL, MongoDB, Redis, and SQLite schemas and sample data safely (read-first). Use when understanding data models or diagnosing query issues.

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.

Scaffold a Python project (FastAPI, Django, library, or CLI) with uv, type hints, testing, and dev tooling

Open a review-action approval window by creating the ./.review-approved flag file. Takes an optional reason string that is recorded in the flag file and an unsigned approval log.

List the review actions that the review-governance policy blocked in this session. protect-mcp 0.7.4 writes no receipt for a denied call, so the list comes from the session, not from ./review-receipts/.

Review software compliance controls, regulatory requirements, and audit readiness

Scan dependencies for vulnerabilities and generate supply chain security evidence

Orchestrate comprehensive security hardening with defense-in-depth strategy across all application layers

Static Application Security Testing (SAST) for code vulnerability analysis across multiple languages and frameworks

Initialises the ShipMate pipeline in the current project. Creates the stories folder, sets up the pipeline state directory, and runs the initial codebase scan to generate project-doc.md and AGENTS.md.

Master pipeline entry point. Routes requirements from a story file through scan → orchestrate → architect → implement → review → QA → playwright stages. Use /ship stories/foo.md to start, /ship status to check progress, /ship resume to continue.

Generate comprehensive investor-ready business case document with market, solution, financials, and strategy

Create detailed 3-5 year financial model with revenue, costs, cash flow, and scenarios

Generate comprehensive market opportunity analysis with TAM/SAM/SOM calculations

Scaffold a Rust project (binary, library, workspace, or Axum web API) with Cargo, testing, and dev tooling

Execute a comprehensive TDD workflow with strict red-green-refactor discipline

Implement minimal code to make failing tests pass in TDD green phase

Write comprehensive failing tests following TDD red phase principles

Refactor code while keeping all tests green in TDD refactor phase

Resolve a GitHub issue from triage and root cause analysis through test-driven implementation and a pull request

Generate async standup notes from git commits, Jira tickets, and Obsidian notes

Audit UI code for WCAG compliance

Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation

The agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚

Sesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

Latitude is the open-source AI monitoring platform.

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…

Grix : Work with agents like talking to people.

Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

AI that ships your tickets.

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

An open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…

Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.

The open-source AI workbench for scientific research

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.