Discover and install skills to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
UnicomAI/wanwu Compose one publication-grade multi-panel figure. Entry from a one-line claim + data files, OR from an existing figure via `derive_outline_prompt` (you read the PNG). Runs a per-figure loop: outline (12-col grid, per-panel ask + label_budget) → render each panel with `panel_task` (loading `figure-style`), one at a time or parallelized → tile + stamp letters with `compose_figure` → adversarial composite self-review with two-tier feedback (Tier-1 outline_revisions / Tier-2 per-panel violations) → regen affected panels, ≤3 rounds. Helpers: panel_task / compose_figure / compose_crops / composite_review_task / derive_outline_prompt. For one standalone plot use `figure-style`; for whole-paper figure ordering use `paper-narrative`. | Skills | |
gridaco/grida Doctrine for designing and evolving any **SDK** Grida ships — TypeScript, Rust, or otherwise. "SDK" here means a surface that crosses a foreign-or-foreign-treated boundary: published packages, separately-versioned consumers, FFI bindings, public-by-design modules. An SDK's job is to refuse; a strict, honest surface rejects the wrong contents and keeps the package testable in isolation. Default is "core, not customizable"; customization is the exception, defended by a deciding table. Use when authoring or evolving any such surface — `@grida/*` published packages, engine crates (gridaco/nothing `crates/*`) published or FFI-exported, intent/message vocabularies, any contract a second author will compile against. Internal-only helper packages are welcome to follow, not forced. Companion skill for two-sided contract work: $sdk-seam. Critique partners: $pedantic, $etiology. Related: $naming. | Skills | |
NVIDIA/skills Run `tao-daft convert` to convert NVIDIA TAO DAFT datasets between supported formats. Do not use for non-DAFT data. Use when the user asks to convert a DAFT dataset, change DAFT format, change a TAO dataset format, or run `tao-daft convert`. | Skills | |
NVIDIA/skills Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or install. | Skills | |
NVIDIA/skills Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity. | Skills | |
NVIDIA/skills Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging docs on disk; not for downloading. | Skills | |
wanikua/danghuangshang 深度调研 - 当需要检索真实世界细节、推演复杂逻辑、获取风格参考时触发。关键词:调研、检索、搜索、参考、素材。 | Skills | |
kylecorry31/Trail-Sense Summarize a Trail Sense backtrack recording session on a connected Android device as a timeline table and ranked findings, using the adb scripts in scripts/debugging. | Skills | |
flutter/agent-plugins Create model classes with `fromJson` and `toJson` methods using `dart:convert`. Use when manually mapping JSON keys to class properties for simple data structures. | Skills | |
mitsuhiko/agent-stuff Use `uv` instead of pip/python/venv. Run scripts with `uv run script.py`, add deps with `uv add`, use inline script metadata for standalone scripts. | Skills | |
mitsuhiko/agent-stuff Reverse engineer binaries using Ghidra's headless analyzer. Decompile executables, extract functions, strings, symbols, and analyze call graphs without GUI. | Skills | |
public-clis/twitter-cli Use twitter-cli for ALL Twitter/X operations — reading tweets, posting, replying, quoting, liking, retweeting, following, searching, user lookups. Invoke whenever user requests any Twitter interaction. | Skills | |
Simon-He95/markstream-vue Integrate markstream-vue2 into a Vue 2 plus Vite app. Use when Codex needs Vite-friendly worker imports, `?worker` or `?worker&inline` setup for Mermaid or KaTeX, modern CSS ordering, or Vue 2 compatibility in a Vite-based repository. | Skills | |
synthetic-sciences/openscience Fast LLM fine-tuning with Unsloth - 2-5x faster training, 50-80% less VRAM. Use for single-GPU LoRA/QLoRA SFT, GRPO/RL reasoning training, vision/TTS fine-tuning, and GGUF export to Ollama/vLLM/llama.cpp. Supports 300+ models including Llama, Qwen, Gemma, DeepSeek, Mistral, Phi, and gpt-oss. | Skills | |
synthetic-sciences/openscience Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism. | Skills | |
synthetic-sciences/openscience Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference. | Skills | |
synthetic-sciences/openscience Set an explicit objective, success criteria, and stopping conditions for the current OpenScience session. | Skills | |
synthetic-sciences/openscience Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL). | Skills | |
open-gitagent/opengap Semantic search over ingested documents using RAG (LlamaIndex/ChromaDB or Foundational RAG) | Skills | |
Norman-bury/research-writing-skill Use before submission or when reviewing papers - provides evaluation checklists, bias detection, and self-review templates | Skills |
Can't find what you're looking for? Evaluate a missing skill.