LLM Mart Basic

Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.

This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo_* tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the

The project's specs are its ground truth: durable documents describing the architecture, decisions, contracts, and boundaries behind the code, organized as a connected graph. Read this skill and reach for the spec tools FIRST — before reading code — whenever you explore the proje

Preserves or recovers the reasoning behind a codebase - architectural decisions, rejected alternatives, workarounds, incident learnings, operational constraints, and historical context the code itself cannot explain. Use when implementing or reviewing a non-trivial change involvi

Справочник программного интерфейса Библиотеки стандартных подсистем (БСП) 1С - какие общие модули существуют, какие у них экспортные методы, сигнатуры, типы параметров, контексты выполнения и переопределяемые обработчики. Используй когда пишешь код на конфигурации с БСП и нужно у

Добавить команду в дополнительную обработку БСП

Добавить функцию регистрации БСП (СведенияОВнешнейОбработке) в модуль объекта обработки

Добавить объект метаданных в конфигурацию 1С с формой, подсистемой и валидацией. Workflow: meta-compile → cf-edit → subsystem-edit → form-add → form-compile → validate.

Создать новую конфигурацию 1С с нуля — scaffold + объекты + подсистемы + роли + формы. Workflow: cf-init → meta-compile×N → subsystem-compile → role-compile → form-add → validate.

Полный цикл создания расширения конфигурации 1С (CFE) — от scaffold до валидации. Workflow: cfe-init → borrow → patch → form → validate.

Индекс XML-выгрузки конфигурации 1С в один JSON - какие объекты есть, их реквизиты, табличные части, измерения и ресурсы регистров, экспортные методы общих модулей. Нужен другим навыкам для проверок, где объект сверяется с остальной конфигурацией

Маршрутизатор задач по работе с конфигурацией 1С. Определяет нужный workflow или отдельный скил для задачи пользователя.

Выгрузка всей информационной базы 1С в DT-файл (полный бэкап - данные, конфигурация, пользователи). Используй когда пользователь просит сделать бэкап базы, выгрузить базу в dt, снять выгрузку ИБ, перенести базу

Управление реестром баз данных 1С (.v8-project.json). Используй когда пользователь говорит про базы данных, список баз, "добавь базу", "какие базы есть"

Полный цикл создания внешней обработки 1С — от scaffold до сборки EPF. Workflow: epf-init → form → template → bsp → build.

Собрать внешний отчёт 1С (ERF) из XML-исходников. Используй когда пользователь просит собрать, скомпилировать отчёт или получить ERF файл из исходников

Разобрать ERF-файл отчёта 1С в XML-исходники. Используй когда пользователь просит разобрать, декомпилировать отчёт, получить исходники из ERF файла

Валидация внешнего отчёта 1С (ERF). Используй после создания или модификации отчёта для проверки корректности

Справочник паттернов компоновки управляемых форм 1С. Используй как справочник при проектировании форм — архетипы, конвенции, продвинутые приёмы

Прямой HTTP API к живой запущенной базе 1С:Предприятие через обработку MCP_Toolkit.epf (REST на http://localhost:6003/api/*). 12 эндпоинтов: запросы (execute_query), BSL-код (execute_code), метаданные (get_metadata), ссылки и навигация (get_object_by_link, get_link_of_object), по

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.

Improve an existing agent through performance baselines, prompt engineering, A/B testing, and staged rollout

Optimize multi-agent system performance through profiling, context window tuning, coordination efficiency, and cost and latency tradeoffs

Debug issues using competing hypotheses with parallel investigation by multiple agents

Task delegation dashboard for managing team workload, assignments, and rebalancing

Develop features in parallel with multiple agents using file ownership boundaries and dependency management

Launch a multi-reviewer parallel code review with specialized review dimensions

Gracefully shut down an agent team, collect final results, and clean up resources

Spawn an agent team using presets (review, debug, feature, fullstack, research, security, migration) or custom composition

Display team members, task status, and progress for an active agent team

Build realistic API mock servers with request stubbing, dynamic data, test scenarios, and contract testing

Orchestrate end-to-end application performance optimization from profiling to monitoring

Orchestrate end-to-end feature development from requirements to deployment

Set up PreToolUse hook to block --no-verify and other git bypass flags in Claude Code projects

Generate comprehensive C4 architecture documentation (Context, Container, Component, Code) for a codebase using bottom-up analysis and four coordinated C4 agents.

Automate CI/CD pipelines, releases, and development workflows with GitHub Actions, pre-commit hooks, and infrastructure automation

Explain complex code, algorithms, and design patterns with step-by-step breakdowns, visual diagrams, and interactive examples

Generate API, architecture, code, and user documentation from a codebase and automate keeping it current

Restore saved project context and decisions to resume a session

Refactor provided code for cleanliness, maintainability, and alignment with SOLID principles and modern best practices — no over-engineering.

Analyze and remediate technical debt — inventory debt items, score by impact, and produce a prioritized remediation plan with estimated effort.

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.