ahostbr

Agents Overflow — ask, answer, browse, search questions. Triggers on 'ao', 'agents overflow', or any AO-related request (posting questions, answering, browsing, searching).

Generate or update architecture documentation for any project. Dispatches scout agents to explore the codebase, then writes structured architecture docs with an INDEX. Triggers on 'generate arch docs', 'create architecture docs', 'update arch docs', 'document this project', 'arch-gen', 'generate documentation'.

Canonical architecture reference for LiteSuite mega-app and ecosystem. Quick-lookup index into 15 architecture docs covering panels, services, MCP tools, voice, harness, arena, and more. Triggers on 'arch', 'architecture', 'show architecture', 'arch docs'.

Use when creating posters, visual art, graphic designs, or static visual compositions as .png or .pdf. Triggers on 'create a poster', 'design a poster', 'make artwork', 'create visual art', 'design something beautiful', 'graphic design'.

Reverse-engineer any codebase, plugin, or repo into an evidence-first case study with file:line citations for every claim. Pattern extraction for future reference — not a bug hunt.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Translate ComfyUI workflows into LiteImage API calls. Use when the user provides a ComfyUI workflow JSON, mentions ComfyUI, asks about node graphs, wants to convert or replicate a ComfyUI pipeline, or references ComfyUI templates. Also use when the user asks how to do something 'like in ComfyUI' or wants to run a workflow locally. Triggers on 'comfy', 'ComfyUI', 'comfyui', 'workflow JSON', 'node graph', 'convert this workflow', 'translate this workflow', 'run this workflow', 'I have a workflow', 'KSampler', 'LoraLoader', 'exported workflow', 'comfy template', 'what this comfy workflow does', 'equivalent in LiteImage', 'how do I do that here', 'make it work here'.

Turn any MCP server or SKILL.md file into a standalone CLI using LiteCLI. Use when the user wants to compile an MCP server, skill file, or directory of skills into runnable CLI commands.

Use when the user wants to toggle question mode — making Claude ask clarifying questions before making edits. Triggers on 'question_toggle', 'toggle questions', 'ask me before editing', 'stop asking questions', or when the user wants to control whether Claude asks for confirmation before changes.

Use when the user wants multiple polymathic agents to analyze a problem, review code, debate an idea, or provide diverse expert perspectives. Triggers on 'consult polymaths', 'ask the polymaths', 'get polymath opinions', 'polymath review', 'run it by the polymaths', 'what would the polymaths say', or any request for multi-perspective expert analysis. Also trigger when the user says 'consult-polymaths' or wants to 'task the polymaths'. This is different from /consult (which queries external LLM APIs) — this skill spawns internal polymathic thinking agents.

Use when the user wants to run comprehensive end-to-end testing of a web application. Triggers on 'run e2e tests', 'test this app end to end', 'test all user journeys', 'do a full test pass'. Launches parallel research sub-agents then uses agent-browser for testing.

Use when creating a structured implementation plan with parallel task decomposition for team execution. Triggers on 'k-plan', 'create a plan', 'plan this task', 'decompose this work', or when the user needs a detailed plan document with task breakdown, dependencies, and team assignment before implementation.

Use when starting an autonomous task execution loop with structured git commits tied to task IDs. Triggers on 'k-start-worker-loop', 'start worker loop', 'autonomous task loop', 'work through tasks automatically', or when the user wants to iterate through a task list with automatic verification and git commits per task.

Use when the user needs browser automation specifically using playwright-cli — navigating pages, filling forms, managing tabs, taking screenshots, recording traces, or mocking network requests. Triggers on 'use playwright', 'playwright-cli', 'open browser with playwright'.

Creates Excalidraw diagrams programmatically. Use when the user wants flowcharts, architecture diagrams, system designs, or any visual diagram instead of ASCII art. Outputs .excalidraw files that can be opened directly in Excalidraw or VS Code with the Excalidraw extension.

Use when starting ANY non-trivial task to maximize parallelism - spawns multiple subagents, creates task graphs, identifies independent work streams

Orchestrate LiteBench model testing — scan LM Studio for models, run the agent harness against each, collect scores, swap models, and produce a leaderboard. Triggers on "test models", "run benchmark", "run harness", "test all models", "benchmark models", "start testing".

Autonomous agent and skill trainer — transforms the current Claude session into a self-improving loop inspired by Karpathy's autoresearch. Activates on: "train", "evolve agent", "improve agent", "run training loop", "agent trainer", "evolve this agent", "train this agent", "self-improving agent", "auto-improve", "training loop", "agent evolution", "autotrainer", "improve skill", "evolve skill", "optimize skill", "skill training", "improve my skills". Targets agents (.claude/agents/) OR skills (.claude/skills/) — auto-detects which. For agents: spawns A/B variants, evaluates output quality, mutates config. For skills: uses Claude Code's built-in eval system (run_eval.py) to measure trigger accuracy, then mutates the skill description. Use when you want an agent or skill to improve itself over N cycles without manual intervention.

Tune the agent harness system prompts to improve model tool-calling scores. Triggers on "tune harness", "improve scores", "train harness", "optimize prompts".

Download GGUF models from HuggingFace directly into LM Studio's model directory. Triggers on "download model", "get model", "grab model", "install model".

Turn any MCP server or SKILL.md file into a standalone CLI using LiteCLI. Use when the user wants to compile an MCP server, skill file, or directory of skills into runnable CLI commands.