Results for “flash”

Automate Apiflash tasks via Rube MCP (Composio). Always search tools first for current schemas.

The English summary is being prepared. Showing the original description.

agy(Google Antigravity CLI)経由で Gemini(既定 gemini-3.8-flash-high)に文章を渡し、推敲・校正・批評・セカンドオピニオンをテキストで受け取る。ユーザーが「Gemini に推敲させて」「別のモデルの意見も」「agy で見て」「セカンドオピニオン」「他の AI にも読ませて」と言ったとき、および日本語・英語の原稿(論文、記事、スライド原稿、メール、README、申請書)の推敲・校正・レビューを頼まれて別視点が有用なときに使う。Claude 自身の推敲に加えて第二の目が欲しい場面では、明示的に Gemini と言われなくても提案・使用してよい。ファイルは編集せず、結果はテキストで返る。

The English summary is being prepared. Showing the original description.

agy(Google Antigravity CLI)経由で Gemini(既定 gemini-3.8-flash-high)に文章を新しく書かせ、テキストだけを受け取る。ユーザーが「Gemini に書かせて」「agy で文章を作って」「別のモデルで下書きを」「Gemini 版の案も」「タイトル案を Gemini に何本か出させて」と言ったとき、および文章の下書き・メール文面・要約・翻訳・タイトルやキャッチコピーの複数案・FAQ・構造化 JSON を Gemini で生成したいときに使う。既存原稿の推敲・批評は agy-review、画像は agy-image を使う。ユーザーが Gemini や agy を指定していない普段の文章作成は Claude 自身が書くので、このスキルは使わない。

The English summary is being prepared. Showing the original description.

Gemini の画像生成モデル (nanobanana) で画像を生成する。`gemini-3.1-flash-image-preview` (デフォルト) と `gemini-3-pro-image-preview` に対応。

The English summary is being prepared. Showing the original description.

Nano Banana（Google Gemini）圖像生成 SKILL。用於呼叫 Gemini 系列圖像模型（gemini-2.5-flash-image, gemini-3.1-flash-image-preview, gemini-3-pro-image-preview）生成概念圖、UCUF 參考探索圖、UI 資產草稿、icon、badge、卡面母稿。需要在 tools_mcp/nano-banana-mcp/.env 設定 GOOGLE_AI_API_KEY。

The English summary is being prepared. Showing the original description.

Automate Apiflash tasks via Rube MCP (Composio). Always search tools first for current schemas.

The English summary is being prepared. Showing the original description.

あらゆる公開ソース向けの完全自動化AI駆動データ収集エージェントを構築 — 求人、価格、ニュース、GitHub、スポーツなどあらゆるデータに対応。スケジュールでスクレイピングし、無料LLM（Gemini Flash）でデータを強化し、Notion / Sheets / Supabaseに結果を保存し、ユーザーフィードバックから学習。GitHub Actionsで100%無料で稼働。ユーザーが自動的にデータを監視、収集、追跡したい場合に使用。

The English summary is being prepared. Showing the original description.

Research synthesis from sources — "summarize these URLs or papers", "research this topic with these sources", "create a podcast about", "audio overview", "mind map", "quiz from these sources", "flashcards", "deep research on". Wraps Google NotebookLM via notebooklm-py.

The English summary is being prepared. Showing the original description.

>-

The English summary is being prepared. Showing the original description.

IoT and embedded device security testing methodology. Covers hardware reconnaissance (UART, JTAG, SWD, SPI flash, I2C EEPROM, eMMC chip-off), firmware acquisition (vendor portals, OTA capture, flash dump, binwalk extraction), firmware analysis (filesystem mounting, binary triage, hardcoded secrets, default credential discovery), bootloader attacks (U-Boot console, secure-boot bypass, fault injection), runtime attacks on embedded Linux/RTOS (busybox CVEs, MTD writes, /dev/mem), wireless protocol attacks (Zigbee, BLE, Z-Wave, LoRaWAN, Thread/Matter, sub-GHz), MQTT/CoAP/Modbus/BACnet/OPC-UA exploitation, mobile companion app analysis, cloud-IoT API abuse, and side-channel/glitching basics. Use for IoT pentest, smart-home assessment, ICS/OT testing, or embedded vulnerability research.

The English summary is being prepared. Showing the original description.

Train language models on pairs of preferred and rejected answers without a separate reference model. The skill guides training setup, model-specific configurations, parameter tuning, and troubleshooting for unstable training or memory limits.

• Train a base model using preferred and rejected answer pairs
• Further tune an instruction-following model
• Adjust training settings for math and coding tasks

Read local PDFs, scanned images, and Office documents for summaries, questions, and citations. Extract readable content, search indexed documents, and work through long files in sections while retaining precise page and block references.

• Reading scanned PDFs with optical character recognition
• Summarizing Office documents and answering questions
• Reading long documents a few pages at a time

Run a prepared set of test cases to check agent-booster success rates and routing decisions. Optionally compare results with Gemini or Claude models, then save detailed measurements and summaries as JSON records for later verification.

• Checking success rates before a release
• Verifying routing after adding test cases
• Checking performance claims against measurements

Check Tesla vehicles through Tessie, including current status, battery level, and range. Run explicitly requested vehicle commands through the connector, using current vehicle information and the required approval process for the requested action.

• Check battery level and remaining range
• Inspect the current vehicle state
• Choose a vehicle from multiple registered cars

Turn supplied data or optional research into infographic drafts for reports, presentations, or social posts. Choose layouts and visual styles, generate PNG images, and use automated reviews to guide revisions while retaining review logs.

• Turning report statistics into an infographic
• Creating a timeline of project milestones
• Comparing product features visually

Summarize web articles, YouTube videos, podcasts, and local files with the summarize command-line tool. Extract available text or transcripts from URLs, choose a summary length, and request JSON output for use in other workflows.

• Get the main points of a web article
• Summarize a YouTube video
• Extract an available video transcript

Analyze firmware from routers, cameras, and other IoT devices, from extracting internal files to running services in an emulator. Follow a staged workflow to investigate vulnerabilities and reproduce findings with firmware analysis and testing tools.

• Auditing router or camera firmware
• Inspecting firmware update packages
• Running firmware without physical hardware

Check ten recurring problems before or during machine learning runs on NVIDIA DGX Spark. Diagnose startup failures, out-of-memory errors, and falling throughput, with guidance on compatible environments, resource use, numeric formats, and training across two devices.

• Checking a DGX Spark before a long training run
• Diagnosing memory errors despite apparent free capacity
• Investigating throughput drops during training

Integrate or upgrade cache-dit in SGLang diffusion, the image generation system. Follow guidance for resolving code conflicts, adding cache settings, testing feature combinations, and comparing generated images using quality measurements and logs.

• Upgrading cache-dit in SGLang diffusion
• Resolving conflicts when porting upstream changes
• Adding per-request cache settings

Develop lightweight CUDA operations for SGLang using JIT, which compiles code on first use. A tensor-scaling example explains implementation conventions, input validation, memory access helpers, and when to choose this approach.

• Add a lightweight CUDA operation to SGLang
• Choose between JIT and ahead-of-time compilation
• Validate tensor inputs in a kernel launcher

Investigate malware that survives OS reinstallation by checking UEFI firmware, boot files, and Secure Boot settings. Use chipsec and supporting tools to compare trusted baselines, identify bootkit indicators, and document findings.

• Investigating reinfection after OS reinstallation
• Checking unexpected Secure Boot changes
• Comparing firmware against a trusted vendor baseline

Generate or modify images through the Luma AI API using Photon models. The skill gathers image descriptions and options, supports reference images for visual guidance, and uses a bundled Python script to wait for completion and download results.

• Creating a landscape image for a website
• Generating square product images
• Guiding image style or composition with a reference

Train language models with SimPO using pairs of preferred and rejected answers. Configure preference training without a separate reference model, adapt settings for base or instruction models, and address unstable training, memory limits, or lost capabilities.

• Training a base model with preferred and rejected answers
• Further tuning an instruction model with preference data
• Adjusting training settings for math and code tasks

Extend the amount of text a language model can process at once. Compares RoPE, YaRN, ALiBi, and position interpolation, with implementation examples, additional training guidance, and memory optimization approaches for long document processing.

• Extend an existing model to handle longer inputs
• Compare methods for representing token positions
• Plan additional training with long documents