poorrican
190 verified skills
codex
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
tools
linear
Linear: manage issues, projects, teams via GraphQL + curl.
tools
stacked-issues
Implement multiple GitHub issues sequentially as stacked branches in separate worktrees, with an implementer sub-agent and an independent reviewer sub-agent per issue. Use when the user gives you two or more dependent issues and asks for them to be implemented in order, or says "stacked branches", "sequential issues", "issue chain", "do these in worktrees", or describes a parent epic with child issues that build on each other. Also reach for this whenever the user wants implementation and verification done by separate agents.
development
using-nautilus-trader
Use when building, backtesting, or deploying algorithmic trading systems with NautilusTrader (nautilus_trader) — writing Strategy/Actor classes and StrategyConfig, configuring BacktestNode/BacktestEngine, constructing instruments, order management, ParquetDataCatalog/wranglers, message bus and custom data streams, indicators, portfolio/analysis/report generation, or live TradingNode deployment. Curated for v1.230.0.
development
segment-anything-model
SAM: zero-shot image segmentation via points, boxes, masks.
data-ai
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
data-ai
stable-diffusion-image-generation
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
development
optimizing-attention-flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
development
peft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
development
grpo-rl-training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
testing
hermes-atropos-environments
Build, test, and debug Hermes Agent RL environments for Atropos training. Covers the HermesAgentBaseEnv interface, reward functions, agent loop integration, evaluation with tools, wandb logging, and the three CLI modes (serve/process/evaluate). Use when creating, reviewing, or fixing RL environments in the hermes-agent repo.
tools
pytorch-fsdp
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
testing
pytorch-lightning
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
development
simpo-training
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
testing
slime-rl-training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
development
linear
Linear: manage issues, projects, teams via GraphQL + curl.
tools
unsloth
Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.
tools
faiss
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
development
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
devops
notion
Notion API + ntn CLI: pages, databases, markdown, Workers.
tools
obsidian
Read, search, and create notes in the Obsidian vault.
tools
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
development
maps
Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.
development
powerpoint
Create, read, edit .pptx decks, slides, notes, templates.
content-media
nano-pdf
Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).
tools
airtable
Airtable REST API via curl. Records CRUD, filters, upserts.
development
airtable
Airtable REST API via curl. Records CRUD, filters, upserts.
development
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
tools
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
tools
maps
Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.
development
fine-tuning-with-trl
TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.
data-ai
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
data-ai
axolotl
Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).
data-ai
obsidian
Read, search, create, and edit notes in the Obsidian vault.
tools
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
data-ai
powerpoint
Create, read, edit .pptx decks, slides, notes, templates.
content-media
ocr-and-documents
Extract text from PDFs/scans (pymupdf, marker-pdf).
documentation
notion
Notion API via curl: pages, databases, blocks, search.
development
ocr-and-documents
Extract text from PDFs/scans (pymupdf, marker-pdf).
documentation
nano-pdf
Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).
tools
distributed-llm-pretraining-torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
development
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
development
feature-brainstorm
Multi-phase brainstorming for complex feature implementations using parallel sub-tasks. Use when the user asks to brainstorm, design, or plan a complex feature, wants to explore implementation approaches, or needs architectural analysis before coding. Triggers on phrases like "brainstorm feature", "design implementation", "explore approaches", "plan architecture", or "how should we implement".
data-ai
coding-agent-output-styles
Find, extract, and port coding-agent output style prompts across Claude Code, Pi, and OMP.
development
baoyu-infographic
Infographics: 21 layouts x 21 styles (信息图, 可视化).
tools
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
development
baoyu-infographic
Infographics: 21 layouts x 21 styles (信息图, 可视化).
tools
excalidraw
Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).
tools
ideation
Generate project ideas via creative constraints.
data-ai
design-md
Author/validate/export Google's DESIGN.md token spec files.
development
excalidraw
Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).
tools
claude-code-internals-inspection
Inspect installed Claude Code internals and official plugin recreations to locate prompts, output styles, built-in strings, and migration hooks.
tools
humanizer
Humanize text: strip AI-isms and add real voice.
data-ai
design-md
Author/validate/export Google's DESIGN.md token spec files.
development
manim-video
Manim CE animations: 3Blue1Brown math/algo videos.
development
manim-video
Manim CE animations: 3Blue1Brown math/algo videos.
development
humanizer
Humanize text: strip AI-isms and add real voice.
data-ai
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
development
comfyui
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.
tools
comfyui
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.
tools
ideation
Generate project ideas via creative constraints.
data-ai
webhook-subscriptions
Webhook subscriptions: event-driven agent runs.
development
webhook-subscriptions
Webhook subscriptions: event-driven agent runs.
development
github-issues
Create, triage, label, assign GitHub issues via gh or REST.
tools
github-pr-workflow
GitHub PR lifecycle: branch, commit, open, CI, merge.
testing
heartmula
HeartMuLa: Suno-like song generation from lyrics + tags.
tools
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
data-ai
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
development
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
development
tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
devops
clip
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
tools
media-transfer-to-te-amo
Use when copying TV media onto /mnt/Te_Amo and the imported show must be reshaped to match the nested TV Shows library layout on Te_Amo.
development
minecraft-modpack-server
Host modded Minecraft servers (CurseForge, Modrinth).
tools
github-auth
GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.
tools
github-repo-management
Clone/create/fork repos; manage remotes, releases.
tools
mcporter
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.
tools
marimo-pair
Drive a live marimo notebook as a workspace: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes. Use when the user wants to start a marimo notebook or pair on an active marimo session.
development
songsee
Audio spectrograms/features (mel, chroma, MFCC) via CLI.
tools
youtube-content
YouTube transcripts to summaries, threads, blogs.
content-media
lambda-labs-gpu-cloud
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
devops
modal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
development
huggingface-tokenizers
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
development
nemo-curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
development
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
content-media
jupyter-live-kernel
Iterative Python via live Jupyter kernel (hamelnb).
development
te-amo-tv-show-layout
Canonical folder and filename shape for TV shows stored under /mnt/Te_Amo/TV Shows.
tools
arch-aur-package-management
Use when setting up, repairing, or using Arch User Repository (AUR) workflows on Arch Linux: prerequisites, yay/paru helper installation, PKGBUILD downloads, libalpm rebuilds after pacman upgrades, and verification.
tools
kanban-worker
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.
development
kanban-orchestrator
Decomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
testing
kanban-worker
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.
development
kanban-orchestrator
Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
testing
spotify
Spotify: play, search, queue, manage playlists and devices.
development
youtube-content
YouTube transcripts to summaries, threads, blogs.
content-media
himalaya
Himalaya CLI: IMAP/SMTP email from terminal.
tools
github-pr-workflow
GitHub PR lifecycle: branch, commit, open, CI, merge.
testing
himalaya
Himalaya CLI: IMAP/SMTP email from terminal.
tools
minecraft-modpack-server
Host modded Minecraft servers (CurseForge, Modrinth).
tools
codebase-inspection
Inspect codebases w/ pygount: LOC, languages, ratios.
development
pokemon-player
Play Pokemon via headless emulator + RAM reads.
tools
github-issues
Create, triage, label, assign GitHub issues via gh or REST.
tools
jupyter-live-kernel
Iterative Python via live Jupyter kernel (hamelnb).
development
github-auth
GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.
tools
github-code-review
Review PRs: diffs, inline comments via gh or REST.
development
github-code-review
Review PRs: diffs, inline comments via gh or REST.
development
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
development
github-repo-management
Clone/create/fork repos; manage remotes, releases.
tools
spotify
Spotify: play, search, queue, manage playlists and devices.
development
native-mcp
MCP client: connect servers, register tools (stdio/HTTP).
tools
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
development
native-mcp
MCP client: connect servers, register tools (stdio/HTTP).
tools
outlines
Outlines: structured JSON/regex/Pydantic LLM generation.
data-ai
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
data-ai
evaluating-llms-harness
lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
data-ai
huggingface-hub
HuggingFace hf CLI: search/download/upload models, datasets.
tools
evaluating-llms-harness
lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
data-ai
obliteratus
OBLITERATUS: abliterate LLM refusals (diff-in-means).
data-ai
llama-cpp
llama.cpp local GGUF inference + HF Hub model discovery.
data-ai
obliteratus
OBLITERATUS: abliterate LLM refusals (diff-in-means).
data-ai
serving-llms-vllm
vLLM: high-throughput LLM serving, OpenAI API, quantization.
development
segment-anything-model
SAM: zero-shot image segmentation via points, boxes, masks.
data-ai
serving-llms-vllm
vLLM: high-throughput LLM serving, OpenAI API, quantization.
development
gif-search
Search/download GIFs from Tenor via curl + jq.
content-media
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
content-media
huggingface-hub
HuggingFace hf CLI: search/download/upload models, datasets.
tools
local-columnar-data-inspection
Inspect local columnar/partitioned datasets (Parquet, SQLite staging/workspace DBs, JSONL metadata exports) to answer data-availability, earliest/latest timestamp, schema, and provenance questions without assuming labels are obvious.
testing
heartmula
HeartMuLa: Suno-like song generation from lyrics + tags.
tools
codebase-inspection
Inspect codebases w/ pygount: LOC, languages, ratios.
development
songsee
Audio spectrograms/features (mel, chroma, MFCC) via CLI.
tools
gif-search
Search/download GIFs from Tenor via curl + jq.
content-media
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
development
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
development
find-nearby
Find nearby places (restaurants, cafes, bars, pharmacies, etc.) using OpenStreetMap. Works with coordinates, addresses, cities, zip codes, or Telegram location pins. No API keys needed.
development
apple-reminders
Manage Apple Reminders via remindctl CLI (list, add, complete, delete).
tools
marimo-pair
Drive a live marimo notebook as a workspace: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes. Use when the user wants to start a marimo notebook or pair on an active marimo session.
development
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
tools
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.
testing
apple-reminders
Apple Reminders via remindctl: add, list, complete.
tools
findmy
Track Apple devices/AirTags via FindMy.app on macOS.
development
imessage
Send and receive iMessages/SMS via the imsg CLI on macOS.
tools
macos-computer-use
Drive the macOS desktop in the background — screenshots, mouse, keyboard, scroll, drag — without stealing the user's cursor, keyboard focus, or Space. Works with any tool-capable model. Load this skill whenever the `computer_use` tool is available.
tools
claude-code
Delegate coding to Claude Code CLI (features, PRs).
tools
codex
Delegate coding to OpenAI Codex CLI (features, PRs).
tools
codex
Delegate coding to OpenAI Codex CLI (features, PRs).
tools
hermes-agent
Configure, extend, or contribute to Hermes Agent.
data-ai
opencode
Delegate coding to OpenCode CLI (features, PR review).
tools
opencode
Delegate coding to OpenCode CLI (features, PR review).
tools
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
development
ascii-art
ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.
testing
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.
testing
baoyu-comic
Knowledge comics (知识漫画): educational, biography, tutorial.
documentation
baoyu-comic
Knowledge comics (知识漫画): educational, biography, tutorial.
documentation
kanban-codex-lane
Use when a Hermes Kanban worker wants to run Codex CLI as an isolated implementation lane while Hermes keeps ownership of task lifecycle, reconciliation, testing, and handoff.
tools
ascii-art
ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.
testing
apple-notes
Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).
tools
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
tools
hermes-agent
Configure, extend, or contribute to Hermes Agent.
data-ai
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
development
claude-code
Delegate coding to Claude Code CLI (features, PRs).
tools
imessage
Send and receive iMessages/SMS via the imsg CLI on macOS.
tools
findmy
Track Apple devices and AirTags via FindMy.app on macOS using AppleScript and screen capture.
development
experiment-log-interview
Conducts a structured Socratic interview to produce or update a single experiment log entry — the durable record of what was run, what it showed, and what it means. Use this skill whenever the user wants to log an experiment, write up results, record a backtest, capture a finding, pre-register a run, document a study, or update an existing entry with new results or a revised interpretation. Trigger on phrases like "log this experiment," "write up the results of...", "I ran X, help me document it," "pre-register this," "update the entry for...", or when the user shares results and asks for help interpreting and recording them. The skill enforces the four-way separation between what happened, what it means, what it implies, and what comes next; challenges the user's interpretations with evidence requests and alternative explanations; and writes incrementally to keep context clean and the entry always grounded.
testing
research-proposal-structure
Use when an agent needs to produce, update, validate, or normalize a standardized research proposal artifact without running an interview. Defines the canonical structure, confidence-tag semantics, decision logic, and completion checks for proposal.md-style research plans.
testing
experiment-log-structure
Use when an agent needs to produce, update, validate, or normalize a standardized experiment-log entry without running an interview. Defines the canonical structure, pre-registration rules, evidence/interpretation split, calibration tags, and append-only revision model for durable experiment records.
testing
research-proposal-interview
Conducts a structured Socratic interview to produce a comprehensive markdown research proposal that handles cascading uncertainty (fixed end-question, branching experiments). Use this skill whenever the user wants to write a research proposal, research plan, study design, experiment plan, thesis proposal, RFC, or "spec out" a research direction — even if they don't explicitly say "interview me." Trigger when the user says things like "help me plan this research", "I want to design experiments for X", "draft a proposal for...", "think through a research direction", or shares a half-formed research idea and asks for help structuring it. The skill interviews the user, challenges their priors with evidence requests and falsifiers, optionally uses sub-agents to explore prior art, and builds the proposal markdown incrementally so context stays clean and the document is always grounded.
development
using-proton-pass-cli
Interact with Proton Pass via the `pass-cli` command-line tool. Use this skill when the user wants to manage passwords, vaults, items, SSH keys, secret injection, or any credential management through the Proton Pass CLI. Triggers on mentions of pass-cli, proton pass, secret references, pass:// URIs, vault management, or SSH agent integration with Proton Pass.
tools
analyzing-backtests
Analyzes algorithmic trading backtest results from Jupyter notebooks and generates summary reports. Use when the user wants to analyze or summarize backtest notebooks.
development
brainstorm
Adversarial brainstorming partner that pressure-tests ideas, challenges assumptions, and explores the codebase to arrive at well-architected solutions. Use when the user asks to brainstorm, challenge an idea, explore approaches, pressure-test a design, or think through architecture. Triggers on phrases like "brainstorm", "challenge this", "pressure test", "what if", "should we", "is this the right approach", "explore alternatives".
development
conventional-commits
Commit changes in a git workspace using the Conventional Commits specification. Use when the user asks to commit, stage, or save changes to git, or mentions "conventional commits". Analyzes staged/unstaged changes, groups related modifications, generates properly formatted commit messages, and commits files separately or together as appropriate. Confirms with user when commit ordering is ambiguous.
development
data-juicer
Primer for using the data-juicer Python library (also written `datajuicer` or `DJ`) — a YAML-driven, OP-based system for cleaning, filtering, deduplicating, transforming, and synthesizing text and multimodal data for foundation models. Use this skill whenever the user mentions data-juicer, DJ, dj-process, dj-analyze, "DJ format", building data recipes / YAML pipelines for LLM training data, or writing custom Filter / Mapper / Deduplicator / Selector / Aggregator / Grouper operators ("OPs"). Also reach for it when the user is putting together a data preprocessing pipeline for LLM pre-training, post-tuning, or multimodal datasets and DJ would be a natural fit, even if they haven't named the library yet — flagging DJ as an option is often the most helpful move.
development
manage-dotfiles
Manage dotfiles and keep synced with external directories. Use on Linux / macOS systemswhen thetre are external connfigs which are being imported into the dotfiles, or when stored dotfiles need to be brought outside to the XDG environment.
tools
package-skill
Package a Claude Code skill directory into a distributable .skill file. Use when the user wants to export, package, bundle, zip, or distribute a skill. Triggers on mentions of .skill files, packaging skills, exporting skills, or sharing skills.
development
stacked-prs
Push local branches and create stacked PRs. Analyzes branch topology, pushes, creates PRs with correct base branches, and resolves merge conflicts. Use when you have a chain of local branches to turn into stacked PRs.
data-ai
p5js
p5.js sketches: gen art, shaders, interactive, 3D.
tools
pretext
Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.
development
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
development
touchdesigner-mcp
Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
tools
p5js
p5.js sketches: gen art, shaders, interactive, 3D.
tools
pixel-art
Pixel art w/ era palettes (NES, Game Boy, PICO-8).
tools
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
development
pixel-art
Pixel art w/ era palettes (NES, Game Boy, PICO-8).
tools
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
development
touchdesigner-mcp
Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
tools
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
development
pretext
Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.
development
songwriting-and-ai-music
Songwriting craft and Suno AI music prompts.
data-ai
songwriting-and-ai-music
Songwriting craft and Suno AI music prompts.
data-ai
llama-cpp
llama.cpp local GGUF inference + HF Hub model discovery.
data-ai
pokemon-player
Play Pokemon via headless emulator + RAM reads.
tools
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
development
llava
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
tools