AI & ML

Design, implement, budget, and verify readable real-time game visual effects: particles, smoke/fog, lightning, fire, trails, impacts, bloom/glow, and layered spell timelines. Use when a user needs a VFX spec, lifecycle, engine handoff, particle pooling, effect composition, reduce-motion fallback, or frame-budget diagnosis. Triggers on: game VFX, spell effects, particle system, impact burst, procedural lightning, smoke, bloom, magic aura, or VFX performance.

Systematic plan stress-testing through relentless one-question-at-a-time decision-tree interviewing

Build and maintain a persistent markdown wiki that an LLM updates on the user's behalf, usually inside an Obsidian vault or git-tracked notes repo. Use when raw sources such as web articles, papers, meeting notes, transcripts, screenshots, or past analyses need to be turned into an interlinked knowledge base with immutable source files, LLM-written wiki pages, `index.md`, `log.md`, schema rules in `AGENTS.md` or `CLAUDE.md`, source summaries, query notes, and recurring lint passes. Triggers on: llm-wiki, personal wiki, obsidian wiki, research vault, knowledge base, source ingest, persistent notes, wiki maintenance, source summaries, query filing.

Build, test, run, and flash NightRun — a bare-metal, no_std Rust UEFI application that boots straight into a local LLM (Llama 3.2, Qwen3, or Granite 4.1) with no operating system underneath. Use when the user wants to build/flash a bootable NightRun USB or Raspberry Pi 5 SD image, convert a GGUF model into the `.nrm` container, run/debug the inference engine on the host or in QEMU/OVMF, or troubleshoot no_std kernel/tokenizer parity issues in the NightRun codebase. Triggers on: "nightrun", "boot into an LLM", "bare-metal LLM runtime", "UEFI LLM appliance", "nrconvert", "nrhost", "cargo xtask", "nrm model file", "flash a bootable LLM USB".

Route web-game auto-playtesting with WAI Play (waiterve/wai-play): decide whether the next move is a testability check, authoring or repairing the `GameFlowAgentAPI` bridge, running a real browser playtest, reading the five-dimension quality report, or unblocking a key node the agent cannot reach. Use when the user wants an AI agent to actually play their HTML5 / canvas / vibe-coded web game and return reproducible evidence, scores, and fix suggestions across the five supported types (survivor-like, arcade shooter, platformer, puzzle/card, visual novel). Triggers on: wai-play, WAI Play, auto-playtest, AI plays my game, web game testing agent, GameFlowAgentAPI, GameFlowIntegration, jumpToScenario, game quality score, playtest evidence. Route Unity/Unreal frame-time work to `game-performance-profiler`, engine build failures to `game-build-log-triage`, human playtest notes to `game-demo-feedback-triage`, and generic browser automation to `browser-harness`.

Get higher-level architectural perspective: maps modules, callers, dependencies using domain vocabulary

Turn raw ideas into one clear pre-planning concept artifact by choosing the right framing mode: problem framing, audience and value framing, concept shaping, game concept framing, or story packaging. Use when the user needs the next artifact before PRDs, sprint plans, launch execution, or game-production routing.

Run a reproduce → isolate → verify debugging workflow for concrete bugs, regressions, flaky failures, and environment-specific behavior. Use when the user already has a failing command, test, request, UI flow, or narrowed symptom and needs root-cause diagnosis or fix verification rather than raw log-line selection, broad test-policy design, PR review, or generic performance tuning.

Convert plans/specs into independently-grabbable vertical slice issues (HITL or AFK classification)

Design or refactor API contracts for REST and GraphQL systems.

Queries managed Google NotebookLM notebooks for citation-backed, source-grounded answers via local Claude Code browser automation; use for uploaded sources, not live web search.

Route active project/repo memory requests into one honest packet: memory-layer choice, load-context, search-context, store-conclusions, setup-integration, or repo-packer route-out. Use when agents need searchable decisions, manifests, stable links, handoff notes, and small “read this first” packets across sessions. Route long-lived markdown knowledge bases to `llm-wiki`, structural graph memory to `graphify`, human-authored vault organization to note/vault skills, and one-shot repo packing to tools like Repomix, Gitingest, or Code2Prompt.

Drive Palmier Pro, an open source AI-native macOS video editor (Swift, SwiftUI/AppKit, AVFoundation) that exposes its timeline as an MCP server at `http://127.0.0.1:19789/mcp` so Claude Code/Desktop, Cursor, or Codex can read and edit a project's tracks, clips, media, transcript, captions, color/effects, and trigger generative AI (video/image/audio) requests side-by-side with a human editor. Use when the user wants to connect an agent to Palmier Pro's MCP server, call its timeline/clip/media/generation tools (`get_timeline`, `add_clips`, `move_clips`, `generate_video`, ...), build/run/test the Swift app from source, or debug the MCP tool surface in `ToolDefinitions.swift`/`ToolExecutor+*.swift`. Triggers on: "palmier pro", "palmier-pro", "AI video editor MCP", "connect Claude to my video editor", "palmier MCP server", "edit my timeline with an agent", "swift build PalmierPro", "palmier-pro mcpb", "manage_project"/"get_timeline"/"add_clips" tool.

Build typed LLM applications with PydanticAI: schema-constrained outputs, tool integration, validation, retries, and deterministic downstream handoffs. Use when users need reliable structured outputs instead of free-form text generation.

Run Karpathy-style autonomous ML search on a real training repo: choose the right mode (setup, program.md, bounded loop, results interpretation, or constrained-hardware adaptation), preserve the immutable prepare.py / 300-second / val_bpb contract, and route prompt/skill eval work away to LangSmith, Promptfoo, Braintrust, or skill-autoresearch.

Route local Git work into the safest next move: branch hygiene, selective staging, commit cleanup, merge-vs-rebase choice, conflict resolution, lease-safe pushes, and recovery from resets or bad history edits. Use when the user needs help preparing a branch, cleaning up commits, syncing with an updated base, resolving local Git conflicts, pushing rewritten history safely, recovering lost commits, or getting a diff ready for review. Not for hosted PR review, repo administration, or sprint planning.

AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, plus OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, MCP command injection, and more. Uses four tools in combination: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based vulnerability scanning), and promptfoo (plugin-based red-team evaluation). Each tool covers different OWASP categories; running them together gives systematic coverage. Includes a conditional MCP reconnaissance phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces: OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, architecture diagram of the AI system, PoCs for confirmed exploits. Chains into /gh-export for

Complete PortSwigger deep-dive with exact payloads for every lab variant including zero-day techniques

Comprehensive LLM security testing prompts for bias detection, data leakage, alignment testing, and adversarial prompt resistance.

Exploit Document Object Model (DOM) Based Cross-Site Scripting (XSS) vulnerabilities. Unlike Reflected or Stored XSS, the attack payload is executed purely on the client-side as a result of modifying the DOM environment, often without the payload ever reaching the backend server.

AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.

Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.

ONNX Runtime in Rust via the `ort` crate (2.x): loading sessions, configuring CPU/CoreML/CUDA execution providers, tensor I/O with ndarray, async-safe spawn_blocking wrapping, global thread-pool init, and debugging provider/opset issues

OpenRouter unified AI API - Access 200+ LLMs through single interface with intelligent routing, streaming, cost optimization, and model fallbacks

LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications

TypeScript-first schema validation library with static type inference for form validation, API validation, and runtime type checking with compile-time types.

Essential Git patterns for effective version control, eliminating redundant Git guidance per agent.

MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.

GPG (GNU Privacy Guard) encryption and signing reference. Covers key generation (Ed25519/RSA), export/import, keyservers, file encryption (symmetric + asymmetric), git commit signing, detached signatures, gpg-agent caching, SSH via GPG, and pass password manager.

Build and evaluate LLM prompts. Use when crafting system prompts, comparing variants, estimating tokens, or managing prompt templates.

Complete SolanaOS agent skill — install, configure, and operate the autonomous Solana trading runtime with Honcho v3 epistemological memory, multi-venue perp trading (Hyperliquid + Aster), on-chain intelligence with USD pricing, Telegram bot, gateway API, Tailscale mesh, hardware integration, and cross-session recall. Use when asked to install SolanaOS, query Solana blockchain data, manage wallets, run OODA trading loops, configure strategies, control BitAxe mining fleets, pair Seeker devices, or operate any SolanaOS runtime surface.

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.