AI Agent Skills

Exploratory QA of web apps: find bugs, evidence, reports.

Yuanbao (元宝) groups: @mention users, query info/members.

Track Apple devices/AirTags via FindMy.app on macOS.

p5.js sketches: gen art, shaders, interactive, 3D.

Audio spectrograms/features (mel, chroma, MFCC) via CLI.

Spotify: play, search, queue, manage playlists and devices.

Send and receive iMessages/SMS via the imsg CLI on macOS.

Himalaya CLI: IMAP/SMTP email from terminal.

MCP client: connect servers, register tools (stdio/HTTP).

Search arXiv papers by keyword, author, category, or ID.

Throwaway HTML mockups: 2-3 design variants to compare.

HeartMuLa: Suno-like song generation from lyrics + tags.

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.

Search/download GIFs from Tenor via curl + jq.

Manage Apple Notes via memo CLI: create, search, edit.

Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

X/Twitter via xurl CLI: post, search, DM, media, v2 API.

ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.

Author/validate/export Google's DESIGN.md token spec files.

Humanize text: strip AI-isms and add real voice.

Pixel art w/ era palettes (NES, Game Boy, PICO-8).

Systematic VPS cleanup — analyze files, categorize by importance, safely delete temporary/old data to free disk space

GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.

Control Philips Hue lights, scenes, rooms via OpenHue CLI.

Generate guided Chinese software copyright application materials from a real project. Use this skill when the user asks for 软件著作权, 软著申请资料, 软著代码材料, 操作手册, 申请表信息, or wants Word/TXT materials for software copyright registration. The workflow analyzes the imported project, extracts real source code, creates Markdown drafts for user confirmation, then uses bundled DOCX tooling to produce final Word documents and TXT.

Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).

Passive domain reconnaissance using Python stdlib. Use this skill for subdomain discovery, SSL certificate inspection, WHOIS lookups, DNS records, domain availability checks, and bulk multi-domain analysis. No API keys required. Triggers on requests like "find subdomains", "check ssl cert", "whois lookup", "is this domain available", "bulk check these domains".

DSPy: declarative LM programs, auto-optimize prompts, RAG.

Linear: manage issues, projects, teams via GraphQL + curl.

Notion API via curl: pages, databases, blocks, search.

Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.

Query Polymarket: markets, prices, orderbooks, history.

ASCII video: convert video/audio to colored ASCII MP4/GIF.

Knowledge comics (知识漫画): educational, biography, tutorial.

Manim CE animations: 3Blue1Brown math/algo videos.

Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.

Create, triage, label, assign GitHub issues via gh or REST.

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Read, search, create, and edit notes in the Obsidian vault.

Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.

Apple Reminders via remindctl: add, list, complete.

Multi-container Docker applications with docker-compose — define services, networks, volumes, and orchestrate local development environments

Play Pokemon via headless emulator + RAM reads.

YouTube transcripts to summaries, threads, blogs.

HuggingFace hf CLI: search/download/upload models, datasets.

Airtable REST API via curl. Records CRUD, filters, upserts.

Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).

Analyze NFT projects for investment decisions — evaluate fundamentals, identify red flags, assess risk, and provide buy/hold/avoid recommendations

Extract data from websites, including JavaScript-rendered SPAs and dynamic content

Refines ideas iteratively. Refine ideas through structured divergent and convergent thinking. Use "idea-refine" or "ideate" to trigger.

Design one-off HTML artifacts (landing, deck, prototype).

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

Create, read, edit .pptx decks, slides, notes, templates.

Generate architecture diagrams with draw.io in headless/server environments (WSL2, VPS, Docker)

Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".

Outlines: structured JSON/regex/Pydantic LLM generation.

Review PRs: diffs, inline comments via gh or REST.