Skip to content
Recaply.
Sign inSubmit a tool

DirectorySkills

Full size
Run 1Social sentiment scan“Ask "What are reviewers saying about our headphones?" and rank Comfort, Battery and Price. About us: Review analysis tool Echo Notes; three sample reviews.”
Runs in
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • GitHub Copilot
  • OpenCode
Generates with
Your agent's model
Tested with
Claude Code 2.1.322Claude Sonnet 5.51 real run, 10 Nov
Needs
Node 22+Chromeffmpeg
Licence
Recaply licence

Social Sentiment Scan

Someone asks what people think, an agent reads and tags a row of posts, then ranks the themes it found.

$9.99once, yours to keep

Every premium skill and prompt, one plan$19.99 a month. Cancel any time. What you get when you buy

Payments are non-refundable. See our Terms of service.

Makes a short launch-film scene as an MP4 clip: someone asks what people think, an agent reads and tags a row of posts, then ranks the themes it found. It shows the person's own product, words, screenshots or pictures in real type and smooth motion (about 12 s), works alone as a social clip or as one scene in a longer launch film, at 16:9, 9:16, 1:1 or 4:5. Renders locally with Chrome and ffmpeg; no video model, no key and no cost. Use when a listening, research or feedback product turns posts or reviews into themes, or when someone asks for a "social sentiment scan" animation, motion graphic or product clip.

By RecaplyUpdated 11 Nov

Install Social Sentiment Scan

After the download, ask your agent to add it, or run the line yourself.

Read https://recaply.co/skills/social-sentiment-scan/install.md and follow it to install the social-sentiment-scan skill from social-sentiment-scan.zip.

Paste it into your agent. It reads our install steps, finds the ZIP you downloaded and adds the skill for you.

New to skills? How to install a skill

Similar skills

All 735 skills

Who Social Sentiment Scan is for

What you get

  • An MP4 scene of about 12 s at 16:9, 9:16, 1:1 or 4:5
  • Your product's words, screenshots and logo in real type
  • Works alone or as one scene in a longer film

Good fit

  • When a listening, research or feedback product turns posts or reviews into themes

Not for

  • A whole launch film in one go (use a launch film)
  • Filmed footage or people on camera

About this skill

You say

Ask "What are reviewers saying about our headphones?" and rank Comfort, Battery and Price. About us: Review analysis tool Echo Notes; three sample reviews.

It said back

The clip is rendered. It's at social-sentiment-scan/social-sentiment-scan.mp4: 12.06 s, 1920×1080 (16:9), 30 fps, 585 KB. It has no sound.

  • Look: studio (cool white with one blue). I didn't set a brand colour, so it uses the default blue.
  • Scene 1: An "Ask Echo Notes" box types "What are reviewers saying about our headphones?" and sends it.
  • Scene 2: The three reviews are read and tagged Comfort, Battery and Price. Comfort is ringed as "Top theme", and the ranking appears as 1. Comfort, 2. Battery, 3. Price.
  • Check: --check reported no layout problems, and I looked at the check frames.
Show more

What it did in run 1

  1. social-sentiment-scan
  2. S=.claude/skills/social-sentiment-scan; node $S/scripts/check.mjs && mkdir -p social-sentiment-scan && cat > social-sentiment-scan/film.json <<'EOF' { "look": "studio", "size": "16:9", "name": "Echo Notes", "out": "social-sentiment-scan.mp4", "scenes": [ { "scene": "composer", "label": "Ask Echo Notes", "ask": "What are reviewers saying about our headphones?", "result": "none" }, { "scene": "scan", "title": "Reading reviews", "items": [ { "title": "Sample review 1", "text": "Soft pads, I forget I'm wearing them", "tag": "Comfort" }, { "title": "Sample review 2", "text": "Lasts me the whole week", "tag": "Battery" }, { "title": "Sample review 3", "text": "Good sound for the price", "tag": "Price" } ], "pick": 0, "badge": "Top theme", "findings": ["1. Comfort", "2. Battery", "3. Price"] } ] } EOF node $S/scripts/film.mjs social-sentiment-scan/film.json --check && node $S/scripts/film.mjs social-sentiment-scan/film.json && ls -lh social-sentiment-scan
  3. ./social-sentiment-scan/film.json
  4. S=$PWD/.claude/skills/social-sentiment-scan; node $S/scripts/check.mjs && node $S/scripts/film.mjs social-sentiment-scan/film.json --check
  5. node .claude/skills/social-sentiment-scan/scripts/check.mjs && node .claude/skills/social-sentiment-scan/scripts/film.mjs social-sentiment-scan/film.json --check
  6. ./social-sentiment-scan/film-check.png
  7. node .claude/skills/social-sentiment-scan/scripts/film.mjs social-sentiment-scan/film.json && ls -lh social-sentiment-scan
  8. Done

10 Nov 2026 · Claude Code 2.1.322 with Claude Sonnet 5.5 · 52 s · $0.09 of API use

Questions

Is Social Sentiment Scan free?

No. Social Sentiment Scan costs $9.99 once and stays in your Recaply account, or it comes with the Recaply plan ($19.99 a month), which opens every premium skill and prompt.

Which agents can use Social Sentiment Scan?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

What do I get when I buy Social Sentiment Scan?

A ZIP of the whole skill folder (62 KB): the SKILL.md your agent follows and its 11 other files, the references, templates and scripts it uses. You download it from this page whenever you need it, and install it in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. The Recaply plan opens it too, with every other premium skill and prompt.

How do I install Social Sentiment Scan?

Buy it, then download the ZIP from this page. For Claude Code, unzip it into .claude/skills/ in your project. For Codex, Cursor and Gemini CLI, unzip it and run npx skills add ./social-sentiment-scan with your agent's flag.

What do I get from Social Sentiment Scan?

An MP4 scene of about 12 s at 16:9, 9:16, 1:1 or 4:5. Your product's words, screenshots and logo in real type. Works alone or as one scene in a longer film.

What does Social Sentiment Scan need?

Node 22+, Chrome and ffmpeg, and no API key. Each use costs nothing beyond your agent.

How big is Social Sentiment Scan?

12 files, about 44,097 tokens in all. The SKILL.md is about 2,437 tokens, and your agent reads it only when the job fits.

What does a run cost?

Our 1 runs took 52 s to 52 s and $0.09 to $0.09 of API use each, in Claude Code with claude-sonnet-5-5. On a Claude plan, a run counts toward your usage instead.

Do I have to name Social Sentiment Scan to use it?

Type /social-sentiment-scan first to make sure it loads. Without it, Claude Code may judge a small job simple enough to do without the skill.