video-transcript-downloader
yt-dlp downloads: video, audio, subtitles, transcripts, clips, playlists.
577 skills
yt-dlp downloads: video, audio, subtitles, transcripts, clips, playlists.
Embed hierarchical data via npx ruvector@0.2.25 embed text and project into the Poincare ball in user code (no --model poincare flag in 0.2.25)
Use single-quoted strings for multiline git commit messages in the Shell tool. Prevents heredoc escaping failures that produce garbled commit messages.
Browse and discover SharePoint sites, lists, document libraries, and file contents — navigate your SharePoint world without leaving the CLI.
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
创建飞书云文档。从 Lark-flavored Markdown 内容创建新的飞书云文档,支持指定创建位置(文件夹/知识库/知识空间)。
Show real token usage and estimated savings for the current session, read from the session log. Trigger: /caveman-stats.
Generates professional slide deck images from content. Creates outlines with style instructions, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", "slide deck", or "PPT".
Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you shift content up to avoid. Load when adding captions/subtitles to a talking-head or launch video, when deciding whether a phrase should be dropped, ride the verbatim rail, or be promoted to a scarce embedded climax, when laying out a composition that will carry captions (do NOT reserve a keep-out band), or when centering a composition on the true frame center under captions. Quotes the rail+embed
Handles an incoming customer complaint end-to-end — pulls context, drafts a response, and suggests an operational fix. Accepts optional email or ticket ID argument.
Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO pairs from passing and failing runs.
Image renderer for json-render that turns JSON specs into SVG and PNG images via Satori. Use when working with @json-render/image, generating OG images from JSON, creating social cards, or rendering AI-generated image specs.
Twilio SMS CLI: buy/list/keep numbers, send/check messages, credential routing.
Cluster code by graph community detection via npx ruvector@0.2.25 hooks graph-cluster (spectral / Louvain)
Writes and edits Markdown without inserting manual hard line breaks at a fixed column (e.g. 72 or 80). GitHub, docs sites, and editors soft-wrap prose; artificial breaks make diffs noisy and reflow awkward. Use when creating or editing .md files, PR bodies, ADRs, READMEs, rulecards, or any Markdown where the user cares about readable source and clean diffs — or when the user asks to avoid "hard wrapping" or "80-column" line breaks in prose.
Search for tasks across all your Planner plans by keyword, assignee, status, or priority — unified cross‑plan task discovery in one view.
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
Lark/Feishu channel output rules. Always active in Lark conversations.
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.
Posts content to Weibo (微博). Supports regular posts with text, images, and videos, and headline articles (头条文章) with Markdown input via Chrome CDP. Use when user asks to "post to Weibo", "发微博", "发布微博", "publish to Weibo", "share on Weibo", "写微博", or "微博头条文章".
Generate a user-facing changelog for the next stable release. Reads git log between the last stable tag and HEAD, categorizes changes, and outputs formatted release notes. Use before triggering a stable release.
Delivers the Friday end-of-week pulse — revenue vs prior week, top sellers, wins and watches. Accepts optional lookback window of 7 or 14 days.
Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training run produces a checkpoint, when deciding whether a tuned model ships, or when a promoted model needs re-gating against updated goldens.
Pre-built custom directives for json-render — formatting, math, string manipulation, and i18n. Use when working with @json-render/directives, defining custom directives with defineDirective, or adding $format, $math, $concat, $count, $truncate, $pluralize, $join, or $t to specs.