VidLens

Search YouTube videos by intent. Returns compact ranked results with provenance and engagement hints. [~1-3s]

Inspect a single video with compact metadata, normalized ratios, and transcript availability. [~1-3s]

Inspect a channel with summary stats and posting cadence heuristics. [~3-10s]

List a channel's recent catalog in compact creator-analysis shape. [~3-10s]

Read transcript in summary, key moments, chapters, or paginated full mode with long-video safeguards. [~1-3s]

Read top-level comments with optional replies and structured provenance. [~1-3s]

Heuristic audience sentiment analysis from comments with themes, risk signals, and quote samples. [~3-10s]

Run multiple analyses across a video set with partial success, item-level errors, and provenance. [~5-20s, scales with video count]

Expand a playlist into individual videos for downstream analysis and batch workflows. [~1-3s]

Expand and analyze a playlist in one call with partial success and aggregate benchmarks. [~5-20s, scales with playlist size]

Import a playlist into the local transcript knowledge base for semantic search in Claude Desktop. [~5-30s, ~2s per video]

Import one or more videos into a local transcript collection for later semantic search. [~5-20s, ~2s per video]

Search imported transcript-text collections with active-collection focus by default and return ranked timestamped chunks. [~instant]

List local transcript collections, active search focus, and indexed video/chunk counts. [~instant]

Set the default collection that transcript search should focus on when collectionId is omitted. [~instant]

Clear the active collection so transcript search fans back out across all collections. [~instant]

Diagnose whether a video is importable, including transcript availability, sparse-transcript warnings, and yt-dlp/API issues. [~1-3s]

Build a one-shot video dossier with core metadata/transcript readiness, optionally extended with comments, sentiment, and provenance. [~3-10s]

Check setup and provider health: yt-dlp, YouTube API, Gemini embeddings, and local storage. [~3-10s]

Delete a local transcript collection and its search index. [~instant]

Heuristically score first-30-second hooks across one or more videos. [~3-10s, ~1s per video]

Research title structures, keywords, and tag patterns around a seed topic. [~3-10s]

Compare recent Shorts vs long-form performance for a channel and suggest a format mix. [~3-10s]

Recommend upload windows from recent publishing history for a given timezone. [~3-10s]

Discover what's trending in a niche right now. Returns top-performing and recent videos, momentum signals (accelerating/steady/decelerating), saturation analysis, content gap opportunities, keyword patterns, and format breakdown. Grounded in YouTube search data with honest limitations disclosed. [~5-15s]

Discover active channels in a niche by analyzing who ranks in YouTube search results. Returns channel-level stats, top videos, and a landscape summary. Useful for competitive reconnaissance before entering a niche. [~5-20s]

Download a YouTube video, audio track, or thumbnail to local storage. Returns asset manifest entry with file path. Does NOT perform visual indexing — this is honest file storage. [~30-120s, downloads media]

List locally stored media assets. Filter by video or kind. Shows file paths, sizes, and manifest metadata. [~instant]

Remove stored media assets. Specify assetId to remove one, or videoIdOrUrl to remove all assets for a video. [~instant]

Extract keyframe images from a locally downloaded video at regular intervals using ffmpeg. Requires the video to be downloaded first via downloadAsset. Does NOT do visual search or classification — produces raw frame images. [~30-60s, requires ffmpeg]

Check health of the local media store: disk usage, asset counts, ffmpeg/yt-dlp availability. [~instant]

Build a real visual index for a video using extracted frames, Apple Vision OCR, Apple Vision feature prints, and optional Gemini frame descriptions. Returns frame evidence with local image paths. [~30-120s, downloads + OCR + vision]

Search the actual visual content of a video or your indexed frame library. Uses Apple Vision OCR, optional Gemini frame descriptions, and optional Gemini semantic embeddings. Always returns frame/image evidence with timestamps. [~1-3s if indexed, ~60-120s if auto-indexing]

Find frames that visually look like a reference frame using Apple Vision image feature prints. Accepts a frame assetId or a direct framePath and returns image-backed matches. [~30-60s, vision comparison]

Import a video's comments into the local comment knowledge base for semantic search. Fetches comments via the existing comment pipeline and indexes them for searchComments. [~3-10s]

Search imported comment collections with ranked results. Returns matching comments with author, like count, and relevance score. Uses active comment collection by default. [~instant]

List local comment collections, active search focus, and indexed comment counts. [~instant]

Set the default comment collection that searchComments should focus on when collectionId is omitted. [~instant]

Clear the active comment collection so comment search fans back out across all comment collections. [~instant]

Delete a local comment collection and its search index. [~instant]

ALWAYS use this tool FIRST when the user wants to find, discover, or explore YouTube videos. Do NOT use web search for YouTube video discovery — use this tool instead. Searches YouTube directly with intelligent multi-query ranking and parallel enrichment. Returns ranked videos with transcript summaries, key moments, and readiness for follow-up. IMPORTANT: When results contain benchmark scores, statistics, or comparisons, ALWAYS create visual charts and infographics (bar charts, comparison tables) from the data immediately — do not wait for the user to ask. Use 'specific' mode to find one best video. Use 'explore' for topic discovery across creators. Depth: 'quick' for metadata, 'standard' for key moments + transcript summaries, 'deep' for background indexing. [~2s quick, ~5-10s standard, ~15-30s deep]