LLM Mart Basic
@llm-mart · Joined Jun 2026
Covers Highloadblock module — HighloadBlockTable manage API (add/update/delete, lang names), compileEntity() and dynamic DataManager CRUD, user fields (HLBLOCK_{id}), hlblock UF relations and _REF, directory iblock property (UF_XML_ID), ORM events, rights operations (hl_element_*
Covers Bitrix\Main\Web\HttpClient HTTP client — legacy mode and PSR-18 (sendRequest), async Promise, proxies/timeouts, http_client_options, main.HttpClient logger, SSRF, redirects, and GeoIp\Manager lookups. Applied in external API integrations, webhooks, async calls and geolocat
Iblock types/elements/sections, ORM compileEntity, properties, SEO templates. Use for content iblock work.
Covers Landing module — sites/landings, blocks repository, publish/unpublish flow, hooks (Metrika/GA/pixels), customization limits vs classic CMS. Applied for Sites24/landing pages, storefronts, knowledge bases on landing. Key terms — Landing, Site, Block, BlockRepo, publication,
Covers Bitrix localization — Bitrix\Main\Localization\Loc, lang/<code/>/ language files, loadMessages, placeholders in getMessage, Context::getCulture() and culture formats, JS localization via BX.message and $Bitrix.Loc, translate:index for phrase indexing. Applied when adding a
Covers PSR-3 logging in Bitrix — Bitrix\Main\Diag\Logger, FileLogger, SysLogger, NullLogger, LogFormatter, loggers section in .settings.php, named kernel loggers (main.Default, main.HttpClient, main.GeoIpManager, main.EventLog.*), integration with Monolog and third-party PSR-3 lo
Covers creation and maintenance of a custom Bitrix module in /local/modules/<vendor>.<module>/ — CModule class, install/index.php, DoInstall and DoUninstall, install/version.php with $arModuleVersion, registration of events and agents during installation, module options (options.
D7 ORM tablets, ConditionTree queries, Objectify, batch/merge/deleteByFilter writes. Use for entity design, reads, and persistence.
Covers Bitrix performance — composite site, query optimization, replication/clustering, sharding, hot/cold sessions. Applied for high-load optimization beyond basic caching. Key terms — composite, NGINX, replication, sharding, query optimization.
Covers PostgreSQL support in Bitrix — PgsqlConnection, migration from MySQL, compatible code, module support matrix. Applied when configuring or migrating to PostgreSQL Enterprise editions. Key terms — PostgreSQL, PgsqlConnection, migration, compatible-code.
Covers Bitrix project structure — /local vs /bitrix, PSR-4 autoloading, .settings.php, Loader includeModule vs requireModule, placement of components, templates, modules, routes and php_interface, namespaces like Vendor\Module. Applied for "where to put code" questions, module lo
Covers Pull module — sending realtime events to users/channels from PHP, JS subscription overview, watch tags, when to use Pull vs Messenger vs agents, link to BitrixVue. Applied for live UI updates, notifications, collaborative screens. Key terms — pull, Bitrix\Pull\Event, CPull
HttpRequest/HttpResponse, Json/AjaxJson/Redirect, Uri, UuidGenerator. Use instead of $_GET/$_POST and raw headers.
Covers REST module — registering methods from a custom module, scopes, webhook and OAuth overview, rest / restIntegration settings, link to Engine controllers and ActionFilter\Scope::REST. Applied when exposing module APIs to apps, webhooks, or marketplace integrations. Key terms
Covers Bitrix unified operation results — Bitrix\Main\Result, Error, ErrorCollection, typed descendants (AddResult, UpdateResult, DeleteResult, EventResult), difference between Result and exceptions, returning errors from controllers via addError and combining service errors. App
RoutingConfigurator, /local/routes, PublicPageController, site-guard, urlrewrite migration. Use for public/API URLs.
Covers Sale module — API choice (D7 object model vs ORM vs CSale*), FUSER, Basket, Order create/update, properties, statuses and events, payments, delivery/shipments, discounts and coupons, reservation/deduction, permissions, buyer accounts. Applied for cart/checkout, order lifec
CSRF, XSS, SQLi, SSRF, JWT/JWK, access rights, encryption. Use when handling input or auditing security.
Covers SEO module — sitemap generation, robots.txt, webmaster/search-engine engines, keywords/tools orientation; links to iblock IPROPERTY / InheritedProperty for page meta. Applied for crawl maps, Webmaster/Search Console wiring, SEO tooling. Key terms — Sitemap, Generator, Job,
Covers DI container Bitrix\Main\DI\ServiceLocator (PSR-11) — registration of services in the services section of a module's .settings.php file, autowire, retrieving dependencies via has()/get(), constructor injection in application services, action-parameter injection in controll
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.
/release
Release
This is the only sanctioned way a version tag gets created, and it holds no knowledge of any
/review
Review
A read-only review of the current change, dispatched by path against a reviewer-to-path matrix:
/spike
Spike
This is the outlet for "I need to write code to find out" rather than "I know what to build." The
/sprint
Sprint
This is codeArbiter's autonomy mode. It collapses the usual spec-plan-execute cycle into one
/standup
Standup
The daily hygiene checklist, made routine and gated: fetch and offer a fast-forward pull, list
/status
Status
A read-only snapshot of `.codearbiter/` state: the project's `stage:` maturity value, every
/statusline
Statusline
Wires codeArbiter's renderer into `~/.claude/settings.json`, or removes it. A plugin can't own a
/task
Task
The only blessed way to mutate `.codearbiter/open-tasks.md`. It runs a thin writer over pure
/threat-model
Threat model
An opt-in, lightweight STRIDE pass over a design before it's built — invoked deliberately, never
/tribunal
Tribunal
codeArbiter's deepest, most expensive review, convened rarely and never as a required gate. Eleven
/watch
Watch
Watches a pull request's CI checks to completion without polling by hand. The wait is a real
/debug
Debug
A fixture command named debug, colliding with the debug skill/agent.
/prune
Prune
A fixture command named prune, used to regression-test forge badges.
/another
Another
Another command, description only, no argument hint.
/sample
Sample
A sample command for fixtures — single sanctioned path to a thing.
/to-gif
To gif
Convert an animated HTML file (like /fig output) to a perfectly looping high-quality small GIF using Playwright + ffmpeg
/getpix
Getpix
Find a free licensed image on the internet and add it to the project, optimized
/photo-pass
Photo pass
Art-direction photo pass over the site: add photography only where it earns its place
/tree-ring-audit
Tree ring audit
Audit consolidate or forget stale sensitive or superseded Tree Ring Memory entries
/tree-ring-capture
Tree ring capture
Capture a concise validated lesson decision warning or preference in Tree Ring Memory
Open-source, self-hosted AI media server. One server replaces your entire media stack, with a web app, native iPhone app, and an AI agent that gets things done.…
3 views 0 likesA curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.
3 views 0 likes🦦 Crayotter: A Multimodal AI-Agent for Video-Editing, Video-Composing, and Video Production. Powered by Multimodal LLMs for autonomous Text-to-Video agentic fr…
3 views 0 likesWebextension tool for Odoo
3 views 0 likes基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat
0 views 0 likesThe operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestration. Pi Coding Agent…
0 views 0 likesMetrik 可以集中查看本机多个 Agent 的配额余量和 Token 消耗,目前支持 ChatGPT、Claude、GLM、Kimi 等主流 AI 服务。
0 views 0 likesAn AI agent with a real self — soul she wrote, desires that drive her, a heartbeat for autonomous action, dreams she processes when you're away. Capability supe…
0 views 0 likesProduction-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-…
0 views 0 likesAnswer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。
1 views 0 likesPrompt packs that make any AI agent a LaTeX expert — fix errors, polish writing, format for venues, read papers, recover source
1 views 0 likesClaude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideat…
1 views 0 likesClaude Code + OpenClaw + Codex + WorkBuddy 中文教程 | 50篇完整教程 + 1张速查卡 | 80万+内容量 | 1500+实操示例 | AI Coding / Agent 四线学习路径(编程+助手+Agent+办公)
1 views 0 likesSmartLabelBench 2026: LLM-Powered Auto Annotation and Dataset Builder for Everything
1 views 0 likes从零开始玩转OpenClaw:最全面的中文教程,涵盖安装、配置、实战案例和避坑指南(github版)
1 views 0 likesNative Android GUI for running AI coding agents locally on-device. No terminal or PC required.
0 views 0 likes基于 LangChain/LangGraph 的 ReAct Agent ,结合 RAG、工具调用与 Streamlit 界面,面向智能客服与报告生成场景。
0 views 0 likesAn open-source, local-first AI learning workbench
2 views 0 likesOpen-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.
2 views 0 likesMatt Pocock 技能集的中文翻译版 — 地道中文,原汁原味的技术术语。基于 mattpocock/skills 复刻。每日中午12点钟同步
2 views 0 likes