3.9K skills · sorted by relevance
Download YouTube captions and thumbnails from a URL or video ID. Save transcripts as Markdown or SRT subtitle files, select or translate languages, add chapters, and use AI processing to label speakers.
Manage a Kortix project from the terminal: start and monitor agent sessions, store secrets, open change requests for review, and call connected services. The skill points agents to the current command reference for detailed operations.
Helps fine-tune large language models with LoRA and QLoRA, methods that train small sets of additional parameters. Covers memory-conscious training, configuration choices, saving adapters, and switching task-specific adapters on a shared base model.
图片理解与数据提取 skill。当图片文件（.png/.jpg/.jpeg/.gif/.webp/.bmp）是主要输入且用户需要理解、提取数据或分析图片内容时使用。提供预配置的 caption 脚本（scripts/caption.py），通过 vision 模型将图片转为文本描述，无需额外配置 API Key。覆盖：(1) 通过 scripts/caption.py 对图表/表格/截图/流程图进行 caption，(2) 将 caption 文本解析为结构化 DataFrame，(3) 基于提取数据重新生成可视化图表，(4) 导出为 Excel/CSV。**遇到以下任一情况就主动使用本 skill，不要自行猜测图片内容**：①用户出现触发词：图片分析 / 图表提取 / 表格识别 / OCR / 图片描述 / 截图分析 / 图表数据 / 提取图片中的数据 / 图片转表格 / 识别图片 / image caption / extract data from image / chart analysis / table OCR；②用户上传或指定了图片文件（.png / .jpg / .jpeg / .gif / .webp / .bmp）并要求理解、提取数据或分析内容；③任务需要从图表截图、表格截图、UI 截图、流程图中提取结构化信息；④用户要求将图片中的数据转为 Excel/CSV 或重新生成可视化图表。仅不用于：图片编辑（裁剪、滤镜、缩放）、图片生成、不含数据的风景/人物照片描述。
The English summary is being prepared. Showing the original description.
Cultural adaptation for translated content. Run AFTER blog-translate completes. Adjusts brand examples, CTAs, legal references, and formality for the target market (German, French, Japanese, Spanish, etc.). Deep cultural adaptation of translated blog posts. Goes beyond translation to swap brand examples, adapt CTAs, substitute legal references, localize statistic sources where possible, and adjust formality (Sie/du, tu/vous, formal/informal). Built-in profiles for DACH, Francophone, Hispanic, and Japanese markets, plus a custom-locale template. Makes content feel locally authored, not translated. Use when user says "localize blog", "blog localize", "cultural adaptation", "adapt for Germany", "adapt for France", "lokalisieren", "localiser", "adaptar".
The English summary is being prepared. Showing the original description.
Use when a video needs its spoken words on screen through Scenario via MCP: burned-in styled captions for a TikTok, Reels, or Shorts cut, ad captions for sound-off feeds, YouTube subtitles, an SRT sidecar, transcription of a clip's audio, captions translated into another language, karaoke or word-by-word styles, or restyling and correcting an existing transcript. Keywords: captions, subtitles, SRT, transcribe, karaoke, word-by-word, burn in, closed captions, translate video, caption style.
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "write a chapter", "next chapter", "chapter outline", "draft chapter", "continue the story", "write a scene", "outline a chapter", or wants to write prose for a story project. NOT for planning a scene's structure, subtext, or outcome (use scene-craft), drafting without an outline (use discovery-drafting), or revising existing chapters (use revision-continuity).
The English summary is being prepared. Showing the original description.
Cultural adaptation for translated content. Run AFTER blog-translate completes. Adjusts brand examples, CTAs, legal references, and formality for the target market (German, French, Japanese, Spanish, etc.). Deep cultural adaptation of translated blog posts. Goes beyond translation to swap brand examples, adapt CTAs, substitute legal references, localize statistic sources where possible, and adjust formality (Sie/du, tu/vous, formal/informal). Built-in profiles for DACH, Francophone, Hispanic, and Japanese markets, plus a custom-locale template. Makes content feel locally authored, not translated. Use when user says "localize blog", "blog localize", "cultural adaptation", "adapt for Germany", "adapt for France", "lokalisieren", "localiser", "adaptar".
The English summary is being prepared. Showing the original description.
Capture outbound HTTP and telemetry from a CLI harness at runtime. Covers capture-channel selection (transcript file vs verbose-fetch stderr vs outbound proxy vs on-disk state), hook-driven per-event capture vs long-running session capture, JSONL output format for diff-friendly artifacts, and the observability table that maps each target to the cheapest channel that captures it. Use when a static finding needs runtime confirmation, when a payload shape is needed for a client re-implementation, or when dark-vs-live disambiguation requires watching what the binary actually sends.
The English summary is being prepared. Showing the original description.
Expert coding skill for the full MapTiler platform — Cloud REST APIs, MapTiler SDK JS (built on MapLibre GL JS), native mobile SDKs, on-premise infrastructure, and vector tile schemas. USE WHEN the user wants to add a map to a web or mobile app, show locations or routes, display geographic data, build a store locator, create data visualizations on maps, add geocoding or address search, do reverse geocoding, look up elevation, do IP geolocation, fetch weather data, transform coordinates between CRS/EPSG, embed static map images, work with vector tilesets (Planet v4, Buildings, Contours, Outdoor, Ocean, Landcover, Cadastre), write MapLibre style expressions or data-driven styling, render 3D terrain, globe view, or 3D buildings extrusion, use satellite imagery, add markers, popups, heatmaps, or clustering, integrate maps in React, Vue, Svelte, Angular, Next.js, Leaflet, OpenLayers, Cesium, or deck.gl, build native maps on iOS (Swift), Android (Kotlin), Flutter, or React Native, self-host with MapTiler Server or generate tiles with MapTiler Engine CLI, or upload/manage tilesets via the Admin API. Also USE WHEN the user mentions MapLibre GL JS — the SDK extends MapLibre with built-in cloud services, helpers, and session billing.
The English summary is being prepared. Showing the original description.
Burn timed, styled captions into a finished video on the local machine, without re-rendering the source. This is the manual fallback to the API's captioning endpoint, POST /v1/captions, which stays the default path: come here when the style the user wants is outside the API's presets, when the wording has to be hand-corrected before it is burned into the pixels, or when the source was rendered with audio disabled and the API refuses it. Transcribes the audio with Whisper, groups words into reading phrases, renders the captions in a real browser via HyperFrames, and composites them over the source with ffmpeg using a real alpha channel. Use when the user has an MP4 with speech and asks to add captions, subtitles, burned-in text, TikTok-style captions or word-by-word text to it, and the API path has been ruled out. Runs out of band, so it costs no credits and works on any video file whoever generated it. Not for generating video (use the video skills) and not for a separate .srt/.vtt sidecar file.
The English summary is being prepared. Showing the original description.
Use when enabling, configuring, or monitoring Change Data Capture (CDC) entity selection, channel enrichment, and delivery usage limits from an admin perspective. Covers the PlatformEventChannel and PlatformEventChannelMember metadata, the standard ChangeEvents channel, custom __chn data channels, enrichedFields, filterExpression, destructive deselection, and PlatformEventUsageMetric / EventBusSubscriber monitoring. Trigger keywords: change data capture, CDC, entity selection, change event, platform event channel, channel member, enrichment, event delivery allocation. NOT for writing an Apex change-event trigger — use apex/change-data-capture-apex. NOT for subscribing an external system over Pub/Sub or CometD — use integration/change-data-capture-integration.
The English summary is being prepared. Showing the original description.
The frontend Error Inspector capture system (captureError, lib/diagnostics/**). Use when wiring a new CapturedErrorSource or adapter, calling captureError from a new site, picking a red/orange/yellow tier or errorTierRules downgrade, or turning a console.error or swallowed catch into a captured error.
The English summary is being prepared. Showing the original description.
1. GET the form/endpoint that shows a CAPTCHA to understand its field name (usually g-recaptcha-response, captcha, captcha_token, captcha_answer, h-captcha-response)
The English summary is being prepared. Showing the original description.
Turn verification recordings and pull request videos into captioned MP4 files with zoom and playback speed changes. Preserve the original recording as evidence while adding visual explanations that help viewers follow the demonstrated actions.
Build or modify adapters that connect Paperclip to AI agent runtimes. Covers server execution, configuration forms, terminal output, session persistence, and environment checks for CLI agents, HTTP endpoints, and custom processes.
Captures screenshots on registered computers and manages saved captures. Supports screen recording on macOS and timed screenshot sequences on HarmonyOS, checking available capabilities first and returning the finalized file path when recording stops.
Capture a public webpage through Latchshot and save a local PNG, JPEG, or PDF. Use viewport images, full-page screenshots, or website thumbnails for reports, visual checks, archives, and social previews.
Map threat groups and their attack techniques to MITRE ATT&CK, a catalog of adversary behavior. Generate Navigator visualization files, compare groups, and overlay detection coverage to identify gaps that can guide defensive planning.
Fine-tune large language models with LoRA and QLoRA while limiting GPU memory use. Guides training settings and adapter management, using small sets of task-specific weights that can be saved, switched, or merged into a base model.
Diagnose OpenCLI commands broken by website changes, collect execution traces, patch the adapter that connects to the site, and retry. After a verified repair, prepares a GitHub issue for submission with user approval.
Route requests for idea exploration, rough planning, time-boxed technical investigation, phase specifications, or thought capture to the appropriate GSD skill. It selects and invokes a skill based on the intended task.
Map wireless networks before a security assessment. Choose compatible adapters, configure packet capture, identify access points and clients, and record channels, encryption, and management frame protection across 2.4, 5, and 6 GHz bands.
Validate FASTQ sequencing files, run local quality checks, and interpret reports to decide whether trimming is needed. Optionally remove adapters or low-quality read ends while preserving original reads and their quality reports.