LLM Mart Basic

@llm-mart · Joined Jun 2026

0 Followers 0 Reputation 12116 Contributions
Claude Skill design

Use in pre-implementation (idea-to-design) stages to understand spec/requirements and create a correct implementation plan before writing actual code. Turns ideas into a fully-formed PRD/design/specification and implementation-plan. Creates design docs and task lists in docs/feat

0
Claude Skill diff-skill

Compare two versions of a skill's instructions to detect degradations and complexity increases. TRIGGER when: user asks to diff, compare, or review changes to a skill's markdown instructions. Asymmetric check — only regressions count. Additions, clarifications, and strengthenings

0
Claude Skill document

After implementing a new feature or fixing a bug, make sure to document the changes. Use when writing documentation, after finishing the implementation phase for a feature or a bug-fix.

0
Claude Skill merge-docs

Compare and merge two design docs for the same feature into a single source of truth. Use when you have competing or complementary design/implementation docs (e.g. from separate design runs) that need reconciling into one unified document.

0
Claude Skill model

Produce or update a domain-reference kit — the durable glossary + divergences/traps pages for a bounded context. Use for domain modelling, information architecture, building a domain glossary or domain model, mapping domain concepts to code (bindings), or surfacing the decidable

0
Claude Skill agent-system-prompt-architect

Designs, reviews, revises, and templates deployable system prompts for agent projects. Use whenever the user asks to write, improve, review, or debug an agent's system prompt, system message, or role/boundary instructions — including Chinese requests such as 系统提示词、角色设定、角色和边界规范、提示

0
Claude Skill business-pulse

Делает одностраничный сводный снимок бизнеса для собственника — позиция по деньгам (бухгалтерия), тренд продаж (платежи), движение по воронке (CRM), обязательства недели (календарь), срочный список наблюдения (почта, мессенджер) и единственное самое важное на сегодня. Сам пробует

0
Claude Skill call-list

Ранжирует топ-5 лидов, которым стоит позвонить сегодня, готовит тезисы разговора из истории переписки, бронирует время в календаре и набрасывает follow-up сообщения. Принимает необязательные аргументы количества и даты. Командная форма: вызывается по имени.

0
Claude Skill canva-creator

Берёт согласованный контент-бриф и выполняет кампанию от начала до конца: строит календарь публикаций, генерирует макеты для постов в соцсетях через ~~дизайн (VistaCreate, Supa, Поликрафт), пишет тексты подписей и писем, ставит публикации в очередь через ~~crm. Макеты делаются то

0
Claude Skill cash-flow-snapshot

Берёт дебиторку и кредиторку, историю сроков поступления денег и известные постоянные расходы из бухгалтерии (1С, МойСклад) и платёжных сервисов (ЮKassa, Тинькофф, банк-выписка) — или из выгрузки CSV — и строит прогноз денежного потока на 30/60/90 дней с доверительными коридорами

0
Claude Skill close-month

Закрывает месяц — сверяет данные бухгалтерии с эквайрингом и выписками, помечает расхождения, пишет ОПиУ-сводку, выгружает пакет закрытия. Принимает необязательные аргументы месяца и места сохранения. Командная форма: вызывается по имени.

0
Claude Skill content-strategy

Анализирует данные о продажах из ~~платежи и ~~бухгалтерии (ЮKassa, 1С, МойСклад), находит хиты и зависшие позиции, накладывает сезонность и выдаёт приоритизированный контент-бриф на 30 дней: что продвигать, какие акции запускать, что придержать. На выходе только стратегия — без

0
Claude Skill contract-review

Лёгкая проверка договоров (поставка, услуги, подряд, NDA, SaaS) по праву РФ для малого бизнеса без штатного юриста. Читает договор из локального файла, вложения в почте (Яндекс 360) или ЭДО (Диадок/СБИС); подсвечивает рискованные условия; объясняет риски простым языком; отдаёт ра

0
Claude Skill counterparty-guard

Проверка контрагента (юрлица/ИП) по ИНН перед сделкой, отгрузкой в долг или предоплатой. Двухскоростная: быстрый quick-scan по deal-killer-сигналам (ликвидация/банкротство/недостоверность ЕГРЮЛ/дисквалификация/крупные долги), затем полное досье по запросу. Собирает открытые данны

0
Claude Skill crm-cleanup

Сканирует CRM на зависшие сделки, дубли контактов и незаполненные поля, затем чинит то, что собственник одобрил. Принимает необязательный аргумент области: сделки, контакты или всё. Командная форма: вызывается по имени.

0
Claude Skill crm-maintenance

Держит CRM в актуальном состоянии без того, чтобы собственник её открывал: создаёт и обновляет контакты и сделки из контекста переписки и календаря, заносит примечания и звонки, помечает зависшие записи. Скилл «хватит вбивать данные руками». Используй, когда собственник просит об

0
Claude Skill cross-source-verify

Движок круговой сверки: берёт результаты из НЕСКОЛЬКИХ источников (агрегаторы, госреестры, веб, выгрузки) и сводит в один ответ с дедупликацией, оценкой уверенности (свежесть × авторитет × согласие источников), tier-маркерами и явным показом расхождений. Не выбирает молча одну ве

0
Claude Skill customer-pulse

Собирает споры по платежам, обращения и отзывы клиентов из CRM, почты и поддержки (плюс вставленные или выгруженные отзывы с Яндекс Карт, 2ГИС, Авито, VK, Отзовика) в отчёт по темам с дословными цитатами и списком «сделайте эти три вещи на этой неделе». Триггеры: «что говорят кли

0
Claude Skill customer-pulse-check

Сводит темы из споров по платежам, обращений CRM и выгрузок отзывов в список топ-3 решаемых проблем с черновиками ответов. Принимает необязательный аргумент даты начала. Командная форма: вызывается по имени.

0
Claude Skill friday-brief

Выдаёт пятничный пульс конца недели — выручка против прошлой недели, топ-продавцы, победы и точки наблюдения. Принимает необязательное окно обзора 7 или 14 дней. Командная форма: вызывается по имени.

0
The AI-in-production safety playbook

Fourteen posts of being wrong in production, compressed to checkboxes

security prompt-engineering devops ai
Sep 30
The control plane was flapping because of a spinning disk

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

kubernetes sre incident-response observability
Sep 29
The overlay that pinged but wouldn't carry TCP

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

containers incident-response networking linux
Sep 28
Bringing a cluster back after the host rebooted

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

kubernetes sre containers incident-response
Sep 27
The agent is running in *your* shell

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

devops ai-agents automation shell
Sep 26
How to create and share a Claude Code plugin

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

agents security skill-md claude-code
Sep 25
The scaffolding that made it safe

None of the safety came from the model. It came from six boring habits.

git devops ai-agents claude-code
Sep 25
Claude Code skills vs. subagents: when to use each

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

agent-skills claude-code context
Sep 24
Knowing when to stop

Six hours in, one step left, everything green, and the incident that didn't happen

prompt-engineering ai ai-agents sre
Sep 24
CLAUDE.md vs. skills: where should Claude Code instructions live?

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

agent-skills claude-skills configuration context
Sep 23
Those are the other app's keys

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

security devops ai ai-agents
Sep 23
How to use remote MCP servers with the OpenAI Responses API

An API request routing a model's tool call through an approval gate to a remote MCP server

security mcp integrations open-api
Sep 22
The coverage audit before you delete the safety net

31 config keys, two audits, and why the first one was wrong in both directions

security devops ai-agents secrets-management
Sep 22
How to publish an MCP server to the official MCP Registry

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.

security mcp
Sep 21
Rotating a leaked credential, in the right order

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

security devops ai-agents containers
Sep 21
MCP authentication explained: OAuth, scopes, and safe token handling

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

security mcp
Sep 20
Byte-identical or bust

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

security kubernetes verification
Sep 20
MCP stdio vs. Streamable HTTP: which transport should you use?

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.

security mcp
Sep 19
Never let the AI print a secret

The most important rule wasn't about what I could change. It was about what I was allowed to display.

security kubernetes devops ai-agents
Sep 19
MCP tools vs. resources vs. prompts: when to use each

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.

security mcp
Sep 18
/checkpoint Checkpoint

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

0
/chore Chore

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

0
/cleanup Cleanup

{{SKILL_ENTRY:post-merge-cleanup}}

0
/commands Commands

Show the codeArbiter command catalog — the public command list and what each routes to.

0
/commit Commit

{{SKILL_ENTRY:commit-gate}}

0
/conflict Conflict

Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.

0
/context-check Context check

{{SKILL_ENTRY:context-check}}

0
/create-context Create context

{{SKILL_ENTRY:context-creation}}

0
/debug Debug

{{SKILL_ENTRY:debug}}

0
/decompose Decompose

{{SKILL_ENTRY:decompose}}

0
/doctor Doctor

Verify the active host install, package, command ownership, enforcement{{IF:pi}}, wrapper self-test, and active-dispatch coverage gap{{ELSE}}, and harmless live-fire probe{{END}}. Read-only.

0
/feature Feature

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

0
/fix Fix

Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

0
/init Init

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

0
/metrics Metrics

Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.

0
/override Override

Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

0
/pr Pr

{{SKILL_ENTRY:finishing-a-development-branch}}

0
/preview Preview

Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.

0
/prune Prune

Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn.

0
/reconcile Reconcile

{{SKILL_ENTRY:decision-variance}}

0
Atom

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

12 views 0 likes
Oh My Hermes

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

16 views 0 likes
Sesori Apps Monorepo

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

14 views 0 likes
Repobrain

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

14 views 0 likes
Dsh Plugin Subscriptions

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

15 views 0 likes
Latitude Llm

Latitude is the open-source AI monitoring platform.

16 views 0 likes
Webbrain

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

16 views 0 likes
Cli

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.

15 views 0 likes
Awesome DeepSeek Harness Plugins

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

16 views 0 likes
Slides Maker

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

14 views 0 likes
Grix

Grix : Work with agents like talking to people.

25 views 0 likes
Atomic Agent

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

26 views 0 likes
Agentql Mcp

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

15 views 0 likes
Pilot

AI that ships your tickets.

14 views 0 likes
Octo Cli

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

12 views 0 likes
Nextclaw

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…

14 views 0 likes
Deepseek Harness Desktop

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

12 views 0 likes
Openscience

The open-source AI workbench for scientific research

15 views 0 likes
DeepSeek Reasonix

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

15 views 0 likes
Bladebro

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

12 views 0 likes