LLM Mart Basic
@llm-mart · Joined Jun 2026
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.
/tree-ring-certify
Tree ring certify
Generate Tree Ring harness or recall-quality evidence without confusing it with the full framework release suite
/tree-ring-dox-sync
Tree ring dox sync
Preview and synchronize DOX-style AGENTS.md guidance as source-linked Tree Ring memory
/tree-ring-recall
Tree ring recall
Recall durable Tree Ring Memory context before starting or resuming work
/tree-ring-status
Tree ring status
Check receipt-backed Tree Ring harness readiness without claiming configuration is activation
/browser-debug
Browser debug
Запусти Яндекс Браузер с удаленной отладкой (Chrome DevTools Protocol) для отладки веб-приложений.
/check-uuid
Check uuid
Проверь уникальность UUID в MDO-файлах 1С по указанному пути (или текущему проекту).
/docx-to-md
Docx to md
Конвертируй DOCX-файл в Markdown.
/move-project
Move project
Перенеси проект в другую папку, сохранив память, сессии и планы Claude Code.
/accept
Accept
Command dispatcher for accept.
/apply
Apply
Command dispatcher for apply.
/brainstorm
Brainstorm
Command dispatcher for brainstorm.
/change
Change
Command dispatcher for change.
/define
Define
Command dispatcher for define.
/design
Design
Command dispatcher for design.
/discover
Discover
Command dispatcher for discover.
/plan
Plan
Command dispatcher for plan.
/propose
Propose
Command dispatcher for propose.
/review
Review
Command dispatcher for review.
/tool
Tool
Command dispatcher for tool.
/browser-cdp
Browser cdp
浏览器操控。通过 CDP 协议控制 Chrome,复用已有登录态,执行浏览器自动化操作。
Your efficient agentic AI coding CLI assistant
2 views 0 likesAI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发…
1 views 0 likesAndroid in docker solution with noVNC supported, video recording, mcp server and AI-agent
2 views 0 likes