# Everything for Gemini CLI What installs into Gemini CLI: skills, MCP servers and plugins. Each card has an install command and example prompts. 20327 cards · page 107 of 509 - HTML: https://affpapa.org/en/nevibecode/for/gemini-cli?page=107 - Instructions for agents: https://affpapa.org/en/nevibecode/agents.md - [hqq-quantization](https://affpapa.org/en/nevibecode/skills/hqq-quantization.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 962 installs — A skill that walks the agent through Half-Quadratic Quantization of LLM weights to 8/4/3/2/1-bit precision without a calibration dataset. - [verl-rl-training](https://affpapa.org/en/nevibecode/skills/verl-rl-training.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 962 installs — Provides step-by-step guidance for reinforcement learning post-training of LLMs using verl with FSDP, Megatron-LM, and Ray. - [twitter-cli](https://affpapa.org/en/nevibecode/skills/twitter-cli.md) — skill · jackwener · Claude Code, Codex, Cursor +3 · 594 installs — A skill that hands your agent a twitter binary for Twitter/X: pull the timeline, search, post, reply, like. - [terraform-stacks](https://affpapa.org/en/nevibecode/skills/terraform-stacks.md) — skill · hashicorp · Claude Code, Codex, Cursor +3 · 5600 installs — Guides AI coding assistants through HashiCorp Terraform Stacks syntax, component definitions, and multi-environment deployment configs. - [elysiajs](https://affpapa.org/en/nevibecode/skills/elysiajs.md) — skill · elysiajs · Claude Code, Codex, Cursor +3 · 14000 installs — This skill helps build, debug, and migrate Elysia v2 TypeScript backends. - [axolotl](https://affpapa.org/en/nevibecode/skills/axolotl.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 960 installs — Walks your agent through Axolotl training runs: YAML configs, LoRA and QLoRA, DPO, KTO, ORPO and GRPO methods, dataset formats. - [huggingface-tokenizers](https://affpapa.org/en/nevibecode/skills/huggingface-tokenizers.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 959 installs — Provides guides and code patterns for high-speed text tokenization using Hugging Face Tokenizers. - [sentence-transformers](https://affpapa.org/en/nevibecode/skills/sentence-transformers.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 959 installs — Guides an agent through local text and image embeddings for RAG, semantic search, clustering, and similarity work. - [svg-icon-generator](https://affpapa.org/en/nevibecode/skills/svg-icon-generator.md) — skill · Jeremy Longshore · Claude Code, Codex, Cursor +3 · 1300 installs — A skill for SVG icon work: it walks the agent through the steps, writes the code and checks the output. - [awq-quantization](https://affpapa.org/en/nevibecode/skills/awq-quantization.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 958 installs — A skill for 4-bit LLM weight quantization with AWQ: faster inference and lower GPU memory use. - [literature-search-biorxiv](https://affpapa.org/en/nevibecode/skills/literature-search-biorxiv.md) — skill · google-deepmind · Claude Code, Codex, Cursor +3 · 2500 installs — Search bioRxiv and medRxiv preprints by DOI or date range. - [clip](https://affpapa.org/en/nevibecode/skills/clip.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 957 installs — Use CLIP for zero-shot image classification, image-text matching, and semantic image search without fine-tuning. - [pytorch-fsdp2](https://affpapa.org/en/nevibecode/skills/pytorch-fsdp2.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 958 installs — Teaches a coding agent to wire PyTorch FSDP2 into a training loop: init, sharding, mixed precision and distributed checkpoints. - [nanogpt](https://affpapa.org/en/nevibecode/skills/nanogpt.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 956 installs — This skill guides work with a small PyTorch GPT implementation. - [redis-js](https://affpapa.org/en/nevibecode/skills/redis-js.md) — skill · upstash · Claude Code, Codex, Cursor +3 · 1500 installs — Reference guides for the @upstash/redis SDK in serverless setups. - [exploiting-sql-injection-vulnerabilities](https://affpapa.org/en/nevibecode/skills/exploiting-sql-injection-vulnerabilities.md) — skill · mahipal · Claude Code, Codex, Cursor +3 · 504 installs — Guides SQL injection testing across web applications during authorized security assessments. - [daily-update](https://affpapa.org/en/nevibecode/skills/daily-update.md) — skill · Ar9av · Claude Code, Codex, Cursor +3 · 2300 installs — daily-update maintains an Obsidian wiki by checking source freshness, refreshing the index and hot.md, and setting up a daily scheduler when needed. - [openrlhf-training](https://affpapa.org/en/nevibecode/skills/openrlhf-training.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 954 installs — A skill that hands your agent ready commands for PPO, GRPO, RLOO and DPO runs on models from 7B to 70B+. - [distributed-llm-pretraining-torchtitan](https://affpapa.org/en/nevibecode/skills/distributed-llm-pretraining-torchtitan.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 954 installs — Configures distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). - [transformer-lens-interpretability](https://affpapa.org/en/nevibecode/skills/transformer-lens-interpretability.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 954 installs — This skill guides TransformerLens research on transformer internals, from activation caching and attention analysis to activation patching experiments. - [modal-serverless-gpu](https://affpapa.org/en/nevibecode/skills/modal-serverless-gpu.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 954 installs — A skill for running ML workloads on Modal's serverless GPUs: training, inference, batch jobs. - [sglang](https://affpapa.org/en/nevibecode/skills/sglang.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 954 installs — Equips your agent with patterns for serving LLMs via SGLang, configuring RadixAttention prefix caching, and decoding constrained JSON. - [evaluating-code-models](https://affpapa.org/en/nevibecode/skills/evaluating-code-models.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 953 installs — Runs code-model benchmarks and reports pass@k metrics. - [dual-axis-skill-reviewer](https://affpapa.org/en/nevibecode/skills/dual-axis-skill-reviewer.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — Reviews skills with deterministic checks and an LLM axis, then combines both into one score. - [edge-hint-extractor](https://affpapa.org/en/nevibecode/skills/edge-hint-extractor.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — Turns daily market observations and news reactions into structured edge hints, written out as hints.yaml. - [edge-concept-synthesizer](https://affpapa.org/en/nevibecode/skills/edge-concept-synthesizer.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — Abstracts raw detector tickets and hints into reusable edge concepts before drafting strategies. - [trader-memory-core](https://affpapa.org/en/nevibecode/skills/trader-memory-core.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — This skill keeps investment theses from a screener idea through a closed position with a postmortem. - [pead-screener](https://affpapa.org/en/nevibecode/skills/pead-screener.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — Screens gap-up stocks after earnings for PEAD follow-through, reading weekly candles for red-candle pullbacks and breakouts. - [kanchi-dividend-us-tax-accounting](https://affpapa.org/en/nevibecode/skills/kanchi-dividend-us-tax-accounting.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — Classifies US dividend streams for stocks, REITs, and BDCs while evaluating holding periods and placement across taxable and retirement accounts. - [edge-candidate-agent](https://affpapa.org/en/nevibecode/skills/edge-candidate-agent.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — Turns US equity EOD observations into research tickets and exports validated candidates for trade-strategy-pipeline Phase I. - [ftd-detector](https://affpapa.org/en/nevibecode/skills/ftd-detector.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — Detects Follow-Through Day signals using William O'Neil's methodology and scores whether it's time to increase exposure after a correction. - [strategy-pivot-designer](https://affpapa.org/en/nevibecode/skills/strategy-pivot-designer.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — Detects stagnation in backtest iteration loops and generates structurally different strategy proposals when parameter tuning hits a local optimum. - [data-quality-checker](https://affpapa.org/en/nevibecode/skills/data-quality-checker.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — A skill that checks market analysis documents before publication: price scale, tickers, dates, allocation totals, units. - [dividend-growth-pullback-screener](https://affpapa.org/en/nevibecode/skills/dividend-growth-pullback-screener.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — Finds dividend growers with 12%+ annual payout growth that have slipped to RSI 40 or below. - [theme-detector](https://affpapa.org/en/nevibecode/skills/theme-detector.md) — skill · tradermonty · Claude Code, Codex, Cursor +3 · 3300 installs — Identifies trending cross-sector market themes and evaluates their lifecycle stage using FINVIZ data. - [pyvene-interventions](https://affpapa.org/en/nevibecode/skills/pyvene-interventions.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 952 installs — This skill guides causal intervention experiments on PyTorch models using pyvene. - [sentencepiece](https://affpapa.org/en/nevibecode/skills/sentencepiece.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 952 installs — A skill that walks the agent through training and running a SentencePiece tokenizer on raw text, with BPE or Unigram. - [huashu-slides](https://affpapa.org/en/nevibecode/skills/huashu-slides.md) — skill · alchaincyf · Claude Code, Codex, Cursor +3 · 834 installs — Builds PPTX presentations from raw notes through a multi-step workflow. - [testability-obstacle](https://affpapa.org/en/nevibecode/skills/testability-obstacle.md) — skill · dotnet · Claude Code, Codex, Cursor +3 · 2500 installs — Adds the smallest production seam in C#/.NET code so a test stops depending on real time, files or randomness. - [slime-rl-training](https://affpapa.org/en/nevibecode/skills/slime-rl-training.md) — skill · Orchestra Research · Claude Code, Codex, Cursor +3 · 951 installs — Guides LLM post-training with RL using the slime framework, connecting Megatron-LM and SGLang. Next: https://affpapa.org/en/nevibecode/for/gemini-cli.md?page=108 ## Refine [cli](https://affpapa.org/en/nevibecode/tag/cli.md) · [python](https://affpapa.org/en/nevibecode/tag/python.md) · [typescript](https://affpapa.org/en/nevibecode/tag/typescript.md) · [react](https://affpapa.org/en/nevibecode/tag/react.md) · [api](https://affpapa.org/en/nevibecode/tag/api.md) · [ui](https://affpapa.org/en/nevibecode/tag/ui.md) · [ios](https://affpapa.org/en/nevibecode/tag/ios.md) · [markdown](https://affpapa.org/en/nevibecode/tag/markdown.md) · [animation](https://affpapa.org/en/nevibecode/tag/animation.md) · [documentation](https://affpapa.org/en/nevibecode/tag/documentation.md) · [node](https://affpapa.org/en/nevibecode/tag/node.md) · [research](https://affpapa.org/en/nevibecode/tag/research.md) ## Narrow this list Parameters: `?platform=`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md --- NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md