kar2phi/video-lens/video-lens-gallery

Claude Code and agent skill by kar2phi/video-lens

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Open or rebuild the video-lens gallery index — your personal library of saved video summaries. Use this whenever the user wants to browse, open, or search saved video reports: "show my gallery", "open video library", "browse saved videos", "build gallery", "what videos have I saved", "show my video notes", "my video summaries", "find my saved summary for [topic]", "rebuild the index", "show video-lens index", "backfill metadata", "update index".

Install

npx vskill@latest install kar2phi/video-lens/video-lens-gallery

SKILL.md

video-lens-gallery

Manage and browse your saved video-lens reports.

Step 1 — Locate skill scripts

Discover both video-lens/scripts ($_sd) and video-lens-gallery/scripts ($_gd) using the standard 8-agent discovery loop:

bash
_sd=$(for d in ~/.agents ~/.claude ~/.copilot ~/.gemini ~/.cursor ~/.windsurf ~/.opencode ~/.codex; do
  [ -d "$d/skills/video-lens/scripts" ] && echo "$d/skills/video-lens/scripts" && break
done)
_gd=$(for d in ~/.agents ~/.claude ~/.copilot ~/.gemini ~/.cursor ~/.windsurf ~/.opencode ~/.codex; do
  [ -d "$d/skills/video-lens-gallery/scripts" ] && echo "$d/skills/video-lens-gallery/scripts" && break
done)
[ -z "$_sd" ] && echo "video-lens skill not found — install it first: npx skills add kar2phi/video-lens" && exit 1
[ -z "$_gd" ] && echo "video-lens-gallery skill not found — install it first: npx skills add kar2phi/video-lens" && exit 1

Step 2 — Backfill metadata (only if requested)

If the user's request mentions "backfill", run:

bash
python3 "$_gd/backfill_meta.py" --dir ~/Downloads/video-lens --channel-ids

--channel-ids adds channel ids to older reports by name; add --lookup when the user asks to fill the rest from YouTube (one yt-dlp call per channel).

Step 3 — Rebuild index

Check that the reports directory exists before running:

bash
[ -d ~/Downloads/video-lens ] || { echo "No reports directory found — save some videos first with the video-lens skill."; exit 1; }
python3 "$_gd/build_index.py" --dir ~/Downloads/video-lens

Tell the user the number of reports indexed, from the script's output.

Step 4 — Serve gallery

bash
bash "$_sd/serve_report.sh" ~/Downloads/video-lens/index.html ~/Downloads/video-lens

If serve_report.sh prints an ERROR: line (e.g. ERROR:SERVE_PORT_BUSY when port 8765 is held by another program), report the message and stop. Otherwise — confirmed by its HTML_REPORT: line — tell the user the gallery is now available at http://localhost:8765/index.html.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
80
Repository forks
11
7-day trend score
22

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/kar2phi/video-lens/video-lens-gallery/badge)](https://verified-skill.com/skills/kar2phi/video-lens/video-lens-gallery)

Something wrong with this skill or its page? Tell us.