AI & ML

lerianstudio Skill

Hardening a skill so it resists rationalization under pressure: run combined-pressure scenarios on a subagent without the skill (RED), capture excuses verbatim, write/edit the skill (GREEN), then plug loopholes (REFACTOR) until compliance holds. Use when deploying or editing a discipline-enforcing skill that an agent could rationalize away. Skip for pure reference skills with no rules to violate.

rwilson504 Skill

Render a labeled 2D top-down (or side/front) layout map of a parametric build123d model from its FeatureRegistry, drawing every cavity, hole, cutout, and boss to scale on an outer-box outline with a north/south/east/west compass and color-coded annotations. USE FOR: "show me a layout diagram", "annotated top view", "where are the holes", "draw the layout", "schematic of the box", "diagram the compartments", verifying spatial intent before printing, communicating layout to the user.

rwilson504 Bundle

Design and author n8n workflow JSON files. Use when user says "build an n8n workflow", "design a workflow", "wire these nodes", "add a trigger", "convert this requirement into n8n", "set up a Schedule/Webhook trigger", "build an AI workflow", "use the AI Agent node", "add a Switch/IF/Merge/Loop Over Items", "split into sub-workflows", "add error handling", "create an error workflow", "build a webhook that responds to the caller", or asks for a runnable workflow JSON. Covers workflow JSON schema, node/connection wiring, the n8n data structure (array-of-items), triggers (Manual, Webhook, Schedule, Form, App triggers, Error Trigger), flow logic (IF/Switch/Merge/Loop Over Items/Wait), expressions and the `={{ }}` template, AI cluster nodes (Agent + Chat Model + Memory + Tools + Vector Store), sub-workflows, and import/export. Do NOT use for executing workflows at runtime, building community node packages (use n8n-create-nodes), Code-node scripting (use n8n-code-node), or hosting setup (use n8n-self-host).

rwilson504 Skill

Catalog of external tools for the build123d ecosystem: editors, viewers, CAM toolpath generation, Blender integration, topology optimization, browser-based CAD, package management, and CI/publishing. USE FOR: OCP CAD Viewer, ocp-vscode, view model, preview CAD, CNC toolpath, CAM, Blender, blendquery, nething, generative AI CAD, topology optimization, dl4to4ocp, OCP.wasm, browser CAD, PartCAD package manager, MakerRepo, makerrepo-cli, publish model, share model, Yet Another CAD Viewer.

rwilson504 Skill

Foundational build123d (Python CAD) patterns and OCCT gotchas that apply to ANY parametric 3D model — not specific to electronics enclosures. USE FOR: BuildPart/BuildSketch/BuildLine context managers, sketch-on-face + extrude, face selection, plane orientation, sign of extrude amounts, fusion rules, fillets/chamfers, parameterization, shallow copies, packing for 3D print plates, common FDM print-orientation rules. Load this BEFORE any enclosure / 3D-model skill.

rwilson504 Skill

Generate a per-face inventory of a parametric build123d model: for each axis face (top/bottom/left/right/front/back) lists the features (holes, cutouts, debossed text, protrusions) sitting on that face with their positions and dimensions. USE FOR: "what is on the top face", "list features by side", "show me a feature map", "describe the model", debugging "which wall has the notch", documenting a part for review, AI ↔ user direction conversations.

sitaggart Skill

Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.

sitaggart Bundle

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.

sitaggart Bundle

Use when building a custom UI (page, dashboard, buttons) that should wake a agent over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale. Checks native runtime support first.

sitaggart Bundle

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

lerianstudio Skill

Adopting the lib-commons/v5 shared Huma (OAS 3.1) OpenAPI wrapper + RFC 9457 problem model (commons/net/http/{openapi,problem}) in a Lerian Go service: wire openapi.New/ServeSpec + problem.Install (central >=500 scrub) on BOTH runtime and spec-gen paths, the per-rail problem.MapError flex seam, and rename-only spec regen. Orchestrates a gated cycle dispatching ring:backend-go. Use for greenfield Huma or migrating a service off a local openapi/humaerr wrapper. Skip for non-Go or non-HTTP work.

pmarashian Skill

Guide for configuring Vite projects for AI agents. Use when setting up Vite development servers for agent-browser, Playwright, or other automated browser tools. Ensures proper server configuration to prevent unwanted browser windows from opening during agent automation.

pmarashian Skill

Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format.

pmarashian Skill

Generate pixel art game assets (characters, animations, tilesets) directly from code using PixelLab MCP Server. Use when creating game assets, character sprites, animations, or tilesets for game development.

pmarashian Bundle

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

pmarashian Skill

Generate speech, transcribe audio, create voice agents, compose music, and manage voices using ElevenLabs MCP Server. Use when working with text-to-speech, speech-to-text, voice cloning, conversational AI agents, or music composition.

pmarashian Skill

Comprehensive guide to MCP servers including PixelLab (async operations, asset download), ElevenLabs (cost warnings, tool selection), and Screenshot Analyzer workflows. Use when working with MCP servers for asset generation, audio processing, or screenshot analysis.

rwilson504 Skill

PartCAD — package manager + public repository of community CAD parts and assemblies (https://partcad.org/repository). Browse hundreds of parts (electrical, electronics, electromechanics, furniture, medical, robotics, std, storage), import them into build123d via `pc.get_part_build123d(...)`, publish your own packages. Covers install, CLI (`pc list/info/inspect/export`), Python API (build123d / CadQuery / generic), partcad.yaml package authoring, AI-generated parts (Google / OpenAI), assembly composition (.assy). USE FOR: PartCAD, partcad, find a community part, browse part catalog, public CAD repo, import community part into build123d, pc.get_part_build123d, pc inspect, pc export, pc list parts, AI-generated CAD model, ai-cadquery, ai-openscad, publish CAD package, OpenVMP robot.

rwilson504 Skill

Read an existing STL (or STEP) file, measure it, and rebuild it as a parametric build123d model. Covers mesh loading (trimesh / OCCT), bounding-box and primitive detection, hole/fillet inference, alignment to a sane coordinate system, and an iterative measure → propose → diff workflow. USE FOR: "rebuild this STL parametrically", "extract dimensions from this mesh", "convert STL to build123d", "reverse engineer a downloaded model", "I have an STL but no source", "measure features in a mesh", "import STEP into build123d".

sitaggart Skill

Configure which models pstack uses per role. Detects your available models and writes host-specific model overrides for the bundled defaults. Use for /setup-pstack, "configure pstack models", or changing pstack's model choices.

sitaggart Skill

Compact the current conversation into a durable handoff document for another agent or future session. Use when the user asks to hand off, pause with context, summarize work for the next session, or prepare a continuation brief.

sitaggart Bundle

Search coding agent session history across Claude Code, Codex, Cursor, OpenCode, and Hermes. Use for past work, previous attempts, or prior investigations.

pmarashian Skill

Ensures all screenshots are saved to a dedicated screenshots/ folder instead of project root. Use when capturing screenshots via agent-browser, Playwright, Puppeteer, or any other screenshot capture method to maintain project organization.

pmarashian Skill

Handle asynchronous operations from MCP servers (PixelLab, ElevenLabs, etc.) with intelligent polling, timeout management, and parallel work opportunities. Use when waiting for async jobs, polling status, or managing long-running operations. Provides exponential backoff, ETA-aware waiting, and prevents premature downloads.

kesslerio Skill

Use oracle CLI to bundle prompts and files for second-model debugging, refactor, design, or review checks.

kesslerio Skill

Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.

kesslerio Skill

List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.

sitaggart Skill

Use RepoPromptCE / rpce-cli for token-efficient codebase exploration, planning, review, refactor context, and prompt exports.

sitaggart Bundle

Run metric-driven optimization loops with experiments and hard gates. Use for search, clustering, build, prompt, or measurable quality tuning.

sitaggart Skill

Normalize a consequential or ambiguous request when missing context, boundaries, or proof could materially change the work. Explicit invocation previews the improved prompt.

pmarashian Skill

Tool selection decision framework, domain validation (visual vs audio), cost awareness, and when to use which tool. Use when deciding which tools to use for a given task, especially when working with MCP servers.

pmarashian Skill

Monitor for identical tool calls in short timeframes, track progress metrics, and recognize stuck states. Use when agent behavior shows repetitive patterns, no progress, or excessive retries. Prevents infinite loops and stuck execution states.

pmarashian Skill

Multiple testing approaches when primary methods fail, ensuring verification always completes even when tools are unavailable. Use when browser testing fails, agent-browser is unavailable, or primary testing tools don't work. Ensures 100% verification coverage with fallback methods.

kesslerio Bundle

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code.

kesslerio Skill

Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.

allanninal Skill

Generate and maintain AGENTS.md files with concise agent instructions for AI coding assistants. Use when setting up project-level AI configuration.