LLM Mart Basic

Orient skill for FluentCRM extension development. Covers the

Register a custom AJAX option list for FluentCRM trigger / action / benchmark editor pickers. Pairs `'type' => 'rest_selector', 'option_key' => '...'` in a settings field with a server-side `add_filter('fluentcrm_ajax_options_{key}', $callback, 10, 3)` callback. Filter signature

Add and parse FluentCRM 3.x SmartCodes and build Pro dynamic contact segments. Covers the addSmartCode method of FluentCrmApi('extender'), parser syntax, fallback/default values, transformers, funnel context smart codes, dynamic segment filters, and ContactsQuery advanced filter

Builds and reviews third-party Fluent Forms input fields with the Free-core BaseFieldManager API. Covers fluentform/loaded bootstrap, editor component schema, frontend rendering, input-name mapping, conditional logic, server-side normalization and validation, response formatting,

Reads, relates, updates, and audits Fluent Forms forms, submissions, entry details, and submission meta from third-party plugins. Covers fluentFormApi, FormFieldsParser, Submission and SubmissionMeta models, form-scoped queries, response JSON versus normalized detail rows, pagina

Builds and audits configurable third-party Fluent Forms feed integrations with IntegrationManagerController. Covers addon/global settings, per-form feed UI, field mapping, conditional execution, smart-code parsing, synchronous versus asynchronous dispatch, ff_scheduled_actions, A

Implements and audits Fluent Forms server-side submission behavior from parsed field data through sanitization, validation, persistence, entry details, notifications, integrations, and confirmation. Selects the correct fluentform/input_data_*, fluentform/validation_errors, fluent

Builds or audits third-party integrations with JetEngine Custom Content Types (CCT): resolving Factory instances, custom-table fields and service columns, Item_Handler create/update/delete hooks, safe queries, Query Builder, related single posts, REST routes and capability bounda

Builds or audits JetEngine Data Store integrations for favorites, bookmarks, likes, recently viewed items, user IDs, and CCT IDs. Covers cookie, session, user-meta, local-storage, and user-IP semantics; Factory lookup; frontend and programmatic mutation; Query Builder; counters;

Registers or audits a custom JetEngine Dynamic Visibility condition by extending Conditions\Base and using the conditions/register hook. Covers show/hide polarity, AND/OR behavior, listing-context value resolution, custom controls under condition_settings, groups, module timing,

Registers or audits a JetEngine Listings callback used by Dynamic Field rendering through jet-engine/callbacks/register or the legacy callback filters. Covers callable identifiers, positional control arguments, multi-callback chains, zero-value defaults, serialized/non-scalar inp

Registers or audits a custom JetEngine Query Builder type with paired runtime and editor classes. Covers all six Base_Query abstract methods including set_filtered_prop, setup_query dynamic/macro merging, pagination, automatic item caching and explicit count caching, filtering, R

Configures the JetFormBuilder action events system — the named events (DEFAULT.PROCESS, DEFAULT.REQUIRED, GATEWAY.SUCCESS, GATEWAY.FAILED, BAD.REQUEST, ON.DYNAMIC_STATE, never) that decide WHEN a Form Action runs. Covers declaring supported / unsupported / required events on a cu

How to read submitted JetFormBuilder form data from a custom

Wraps every action item in the JetFormBuilder action editor with

Surfaces user-facing custom messages from a JetFormBuilder

Registers a custom JetFormBuilder Form Action — a server-side

Adds a per-form settings panel to the JetFormBuilder

Registers a custom settings tab in the JetFormBuilder admin

Extend JetSmartFilters with a custom provider for an unsupported renderer or a custom native JSF Listing query type for a non-post data source. Use when code must register on jet-smart-filters/providers/register or jet-smart-filters/listing/render/query-types/register, extend Jet

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.

Require justification for new files (short for /ar:justify)

Require justification before creating new files

Block a command pattern in this session

Allow a blocked pattern in this session

Plan export status and settings [on|off|globalon|globaloff|dir <path>|pattern <template>|rejected [on|off|dir <path>]|reset]

Universal System Design Philosophy - the 17 core principles, short for /ar:philosophy

Plan export status and settings [on|off|globalon|globaloff|dir <path>|pattern <template>|rejected [on|off|dir <path>]|reset]

Create a structured plan, short for /ar:plannew

Execute an approved plan step by step, short for /ar:planprocess

Critique and improve an existing plan, short for /ar:planrefine

Start autoproc - procedural autonomous workflow

Sync an existing plan with the codebase, short for /ar:planupdate

Force-reload all integration rules from config files

Restart the daemon for the current autorun install/source tree

Start autorun - autonomous task execution

Emergency stop - immediately halt all actions (short for /ar:estop)

Show current AutoFile policy status (short for /ar:status)

Show current AutoFile policy and settings

Graceful stop - finish current task then stop autorun

Inspect tasks or configure pause, prompts, recovery, and ignore behavior

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat ap…

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evid…

Ultimate Multi-Agent OS for Autonomous AI NPCs 2026

Personal AI Agent Hub 2026 — Build Your 24/7 Autonomous Assistant

Proven 2026 Multi-Agent AI Review System – Verdict-Driven Quality Control

Slash API Batch: Cut AI Costs by 50% in 2026

Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics

Agent Skills for Solopreneurs

AirLLM dramatically reduces inference memory usage, letting 70B large language models run on a single 4GB GPU card

Zero, your trustworthy AI teammate for real work.

一套 DSH runtime，Desktop、Web 与 TUI 三种开发体验。

Open-source operational advisor for ClickHouse — real-time monitoring plus AI-driven index/partition/materialized-view recommendations.

⚙️ TypeScript Style Guide and Agent Skill. A concise set of conventions and best practices for consistent, maintainable code.

Framework for AI agents to build and maintain a digital brain through Obsidian wiki

Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorde…

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active H…

Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Sin…

NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of productio…

An open-source AI coding agent that lives in your terminal.

PawWork — free, open-source desktop AI agent for macOS and Windows. Alternative to Codex App and Claude Cowork. BYOK with 75+ providers, ChatGPT OAuth, local mo…