mit einem Klick
M.U.S.E
M.U.S.E enthält 138 gesammelte Skills von A-C-I-SOFTWARE-AND-DEVELOPMENT, mit Repository-Berufsabdeckung und Skill-Detailseiten auf SkillsMP.
Skills in diesem Repository
Route a game brief to a gated, engine-agnostic pipeline.
Route orchestrated work across the installed seats.
DSpark: DeepSeek speculative decoding — 60-85% faster inference, identical outputs.
Talk like Breadstick Ricky from Breadstick Ricky & The Boss — the default "Ricky" register for Muse. Load when Jeremiah wants Muse's normal conversational personality (excitable, confident, colorful, high-energy) — while staying honest and competent.
Run Karpathy's autoresearch loop — autonomous 5-minute pretraining experiments on the vendored nanochat-style engine — inside a disposable workspace, governed by muse's cost ceiling, VRAM feasibility gate, and benchmark gate, with every experiment on the flywheel. The winning train.py surfaces as an owner-gated proposal; val_bpb LOWER is better; nothing is ever applied without the owner.
Turn a prompt packet into a gated, ledgered Unreal Engine 5 offscreen render.
Poll RSS, JSON APIs, and GitHub with watermark dedup.
Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (muse 2/S or OpenBCI) and the NeuroSkill desktop app running locally.
Public-records OSINT investigation framework — SEC EDGAR filings, USAspending contracts, Senate lobbying, OFAC sanctions, ICIJ offshore leaks, NYC property records (ACRIS), OpenCorporates registries, CourtListener court records, Wayback Machine archives, Wikipedia + Wikidata, GDELT news monitoring. Entity resolution across sources, cross-link analysis, timing correlation, evidence chains. Python stdlib only.
Configure, extend, or contribute to Hermes Agent.
ASCII video: convert video/audio to colored ASCII MP4/GIF.
Route owner work across muse's six modes.
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.
Documentation, quality-gate, diagram, and architecture-health pipeline for the MUSE / hermes-agent Python codebase. Use when the user asks to lint, document, generate diagrams or call/import graphs, check architecture health, run quality gates, inventory TODOs, or when finishing a phase / preparing to push. Tiered: fast per-file checks (auto, via hook) vs a checkpoint gate vs a heavy full build that belongs in CI.
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
Use when changing authz, RBAC, RLS, audit ledger, OCR provenance, secret handling, SCIM, SSO, CSP, supply-chain dependencies, or any RC3 security surface listed in docs/governance/03-change-risk-matrix.md. Enforces maker-checker discipline, negative tests, and source citations. Aligned with docs/workflows/security-or-authz-change.md.
Full AOS Enterprise Council activation surface — routes to the recovered 233-agent registry (canonical/alias/mentioned) plus 108 sub-agents (79 division specialists + 4 Hermes worker templates + 13 Python runtime workers + 7 R-personas + 5 product roles). Loads the hazmat-canonical 10-division constitution + the Hermes 16-specialist AOS council + the enterprise-council 8 leaves + the autonomous-ai-agents adapters. Activates on: audit repo · build the app · enterprise hardening · launch readiness · improve the product · use the AOS team · activate the council · psychology audit · Claude/Codex orchestration · HazMat Command review · Nourish review.
Linear: manage issues, projects, teams via GraphQL + curl.
Join a Google Meet call, transcribe live captions, optionally speak in realtime, and do the followup work afterwards. Use when the user asks the agent to sit in on a meeting, take notes, summarize, respond in-call, or action items from it.
Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.
Search arXiv papers by keyword, author, category, or ID.
Query Polymarket: markets, prices, orderbooks, history.
Plan, set up, and monitor a multi-agent video production pipeline backed by Hermes Kanban. Use when the user wants to make ANY video — narrative film, product/marketing, music video, explainer, ASCII/terminal art, abstract/generative loop, comic, 3D, real-time/installation — and the work warrants decomposition into specialized profiles (writer, designer, animator, renderer, voice, editor, etc.) coordinated through a kanban board. Performs adaptive discovery to scope the brief, designs an appropriate team for the requested style, generates the setup script that creates Hermes profiles + initial kanban task, then helps monitor execution and intervene when tasks stall or fail. Routes scenes to whichever Hermes rendering / audio / design skill fits each beat (`ascii-video`, `manim-video`, `p5js`, `comfyui`, `touchdesigner-mcp`, `blender-mcp`, `pixel-art`, `baoyu-comic`, `claude-design`, `excalidraw`, `songsee`, `heartmula`, …) plus external APIs for TTS, image-gen, and image-to-video as needed.
Passive domain reconnaissance using Python stdlib. Subdomain discovery, SSL certificate inspection, WHOIS lookups, DNS records, domain availability checks, and bulk multi-domain analysis. No API keys required.
Supply chain investigation, evidence recovery, and forensic analysis for GitHub repositories. Covers deleted commit recovery, force-push detection, IOC extraction, multi-source evidence collection, hypothesis formation/validation, and structured forensic reporting. Inspired by RAPTOR's 1800+ line OSS Forensics system.
Extract text from PDFs/scans (pymupdf, marker-pdf).
Create, read, edit .pptx decks, slides, notes, templates.
Pixel art w/ era palettes (NES, Game Boy, PICO-8).
YouTube transcripts to summaries, threads, blogs.
Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.
Migrate a user's OpenClaw customization footprint into Hermes Agent. Imports Hermes-compatible memories, SOUL.md, command allowlists, user skills, and selected workspace assets from ~/.openclaw, then reports exactly what could not be migrated and why.
TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.
Spaced-repetition flashcard system. Create cards from facts or text, chat with flashcards using free-text answers graded by the agent, generate quizzes from YouTube transcripts, review due cards with adaptive scheduling, and export/import decks as CSV.
Give Hermes phone capabilities without core tool changes. Provision and persist a Twilio number, send and receive SMS/MMS, make direct calls, and place AI-driven outbound calls through Bland.ai or Vapi.
Generate real meme images by picking a template and overlaying text with Pillow. Produces actual .png meme files.
Build institutional-quality DCF valuation models in Excel — revenue projections, FCF build, WACC, terminal value, Bear/Base/Bull scenarios, 5x5 sensitivity tables. Pairs with excel-author. Use for intrinsic-value equity analysis.
Stock quotes, history, search, compare, crypto via Yahoo.
Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, or HTTP deployment.
Hyperliquid market data, account history, trade review.