Agent skill

Carousel Benchmark

by nestyme in nestyme/awesome-prompts

Find the TikTok photo-mode carousels (slideshows) that actually go viral in a niche and the accounts behind them, rank them by organic quality (save-rate, like-rate, boost detection) instead of raw…

No licenceAuto-check: notesData & Analytics

Install Carousel Benchmark

skills CLI
$ npx skills add nestyme/awesome-prompts --skill carousel-benchmark -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nestyme/awesome-prompts carousel-benchmark --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nestyme/awesome-prompts.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/carousel-benchmark .claude/skills/carousel-benchmark && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
carousel-benchmark
GitHub stars
149
Token cost
~2.6k tokens
SKILL.md length
1,298 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
None found

At a glance

Find the TikTok photo-mode carousels (slideshows) that actually go viral in a niche and the accounts behind them, rank them by organic quality (save-rate, like-rate, boost detection) instead of raw…

  • Works in 6 steps: Frame the niche (5 min) → Discover candidates (3 sources, run in… → Profile-scan everything (the $5 step) → …
  • Ever the user wants to research viral carousels / slideshows / photo posts for their app
  • SKILL.md covers Why carousels need their own…, Operating principles, The procedure and Formats that carried the…, plus 2 more sections
  • Calls python3; needs APIFY_TOKEN

What it does

Carousel Benchmark is an agent skill from nestyme/awesome-prompts. Find the TikTok photo-mode carousels (slideshows) that actually go viral in a niche and the accounts behind them, rank them by organic quality (save-rate, like-rate, boost detection) instead of raw views, and turn the winners into a leaderboard + format breakdown you can copy. Trigger whenever the user wants to research viral carousels / slideshows / photo posts for their app or brand, asks 'who is winning with carousels in X', wants references before launching a carousel account, or asks whether a competitor's…

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Data & Analytics, covering Web scraping. It works with TikTok and Apify.

When your agent uses it

  • Ever the user wants to research viral carousels / slideshows / photo posts for their app
  • Asks who is winning with carousels in X
  • Wants references before launching a carousel account
  • Asks whether a competitors carousel numbers are organic

Example prompts

  • “who is winning with carousels in X”
  • “/carousel-benchmark”

Requirements

  • Python 3
  • A credential in APIFY_TOKEN

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Frame the niche (5 min)
  2. Discover candidates (3 sources, run in parallel)
  3. Profile-scan everything (the $5 step)
  4. Rank (carousel_leaderboard.py)
  5. Read the slides of the top 10
  6. Deliver

What it can do on your machine

Read from SKILL.md and the folder at commit faba220. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • x.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • APIFY_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Carousel Benchmark loads about 2.6k tokens when it runs. Until then it costs about 163 tokens; SKILL.md has 1,298 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~163
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:24
    Needs `APIFY_TOKEN` in `tools/.env`. A niche-wide benchmark (≈50 queries, ≈80

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,298 words (~2,590 tokens).

“Give me a niche — I return the carousel accounts that win there, ranked by organic quality, with the formats that carry them and a slide-by-slide read of the best posts. Made by @nestymee while launching a carousel account; the…”

— opening of SKILL.md by nestyme
name
carousel-benchmark

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/carousel-benchmark of nestyme/awesome-prompts.

Open the folder on GitHubat commit faba220

Compare with similar skills

Carousel Benchmark next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Carousel Benchmark compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Carousel Benchmark this skillnestyme/awesome-prompts149—~2.6kAutomated safety check: NotesNone
Apify Competitor Intelligencemajiayu000/claude-skill-registry6664 repos~1.3kAutomated safety check: NotesMIT
Apify Audience Analysismajiayu000/claude-skill-registry6663 repos~1.2kAutomated safety check: NotesMIT
Apify Content Analyticsmajiayu000/claude-skill-registry6663 repos~1.1kAutomated safety check: NotesMIT
Apify Trend Analysismajiayu000/claude-skill-registry6663 repos~1.1kAutomated safety check: NotesMIT
Apify Creator Emailsapify/awesome-skills262—~3.9kAutomated safety check: PassApache-2.0

Similar skills

  • Apify Competitor Intelligence

    majiayu000/claude-skill-registry

    Analyze competitor strategies, content, pricing, ads, and market positioning across Google Maps, Booking.com, Facebook, Instagram, YouTube, and TikTok.

    666 GitHub starsUsed in 4 repos~1.3k tokens
    Data & AnalyticsAuto-check: notes
  • Apify Audience Analysis

    majiayu000/claude-skill-registry

    Understand audience demographics, preferences, behavior patterns, and engagement quality across Facebook, Instagram, YouTube, and TikTok.

    666 GitHub starsUsed in 3 repos~1.2k tokens
    Data & AnalyticsAuto-check: notes
  • Apify Content Analytics

    majiayu000/claude-skill-registry

    Track engagement metrics, measure campaign ROI, and analyze content performance across Instagram, Facebook, YouTube, and TikTok.

    666 GitHub starsUsed in 3 repos~1.1k tokens
    Data & AnalyticsAuto-check: notes
  • Apify Trend Analysis

    majiayu000/claude-skill-registry

    Discover and track emerging trends across Google Trends, Instagram, Facebook, YouTube, and TikTok to inform content strategy.

    666 GitHub starsUsed in 3 repos~1.1k tokens
    Data & AnalyticsAuto-check: notes
  • Apify Creator Emails

    apify/awesome-skills

    Official

    Find creators and their published contact emails in one run.

    262 GitHub stars~3.9k tokensUpdated 14 days ago
    Data & AnalyticsAuto-check passed
  • Official

    Scrapes public data from social, maps, search and review platforms by choosing from about a hundred Apify Actors and running them through the Apify CLI.

    2.4k GitHub starsUsed in 2 repos~1.4k tokens
    Data & AnalyticsAuto-check: notes

More from nestyme/awesome-prompts

All 9 skills in this repo
  • Carousel Conveyor

    nestyme/awesome-prompts

    Turn trendwatched hook ideas into finished TikTok/Instagram photo carousels for a recurring AI persona, then schedule them via a posting tool (e.g.

    149 GitHub stars~4.2k tokensUpdated 7 days ago
    Auto-check passed
  • Influencer Outreach

    nestyme/awesome-prompts

    Build and run a paid micro-influencer outreach pipeline end to end — scrape creators by niche hashtags, verify their real reach, score who to write first, draft outreach in the creator's language…

    149 GitHub stars~4.3k tokensUpdated 7 days ago
    Auto-check passed
  • Tiktok Shadowban Check

    nestyme/awesome-prompts

    Tell whether TikTok accounts are shadowbanned / throttled, how likely, why, and what to do.

    149 GitHub stars~971 tokensUpdated 7 days ago
    Auto-check passed
  • Viral Content Factory

    nestyme/awesome-prompts

    Create viral social media content (TikTok/Instagram carousels and outfit-change videos) for app promotion.

    149 GitHub stars~3.4k tokensUpdated 7 days ago
    Auto-check: notes
  • Voice Realism

    nestyme/awesome-prompts

    Rewrite AI video / text-to-speech prompts so the generated VOICE sounds like a real human, not a robot.

    149 GitHub stars~2.3k tokensUpdated 7 days ago
    Auto-check passed
  • Trendwatch

    nestyme/awesome-prompts

    Reverse-engineer viral organic TikTok/Instagram content from competitor accounts and generate adapted hook ideas for the user's app.

    149 GitHub stars~10k tokensUpdated 7 days ago
    Auto-check passed

Works with

Questions about Carousel Benchmark

What does Carousel Benchmark do?

Find the TikTok photo-mode carousels (slideshows) that actually go viral in a niche and the accounts behind them, rank them by organic quality (save-rate, like-rate, boost detection) instead of raw…. Carousel Benchmark is an agent skill from nestyme/awesome-prompts. Find the TikTok photo-mode carousels (slideshows) that actually go viral in a niche and the accounts behind them, rank them by organic quality (save-rate, like-rate, boost detection) instead of raw views, and turn the winners into a leaderboard + format breakdown you can copy.

When should I use Carousel Benchmark?

Carousel Benchmark fits situations like: ever the user wants to research viral carousels / slideshows / photo posts for their app; asks who is winning with carousels in X; wants references before launching a carousel account; asks whether a competitors carousel numbers are organic.

How do I install Carousel Benchmark in Claude Code?

Run `npx skills add nestyme/awesome-prompts --skill carousel-benchmark -a claude-code`. Or copy the skill folder (skills/carousel-benchmark in nestyme/awesome-prompts) into .claude/skills/carousel-benchmark in your project. Claude Code loads it when a task matches its description.

How do I install Carousel Benchmark in Codex?

Run `npx skills add nestyme/awesome-prompts --skill carousel-benchmark -a codex`. Or copy the skill folder (skills/carousel-benchmark in nestyme/awesome-prompts) into .agents/skills/carousel-benchmark in your project. Codex loads it when a task matches its description.

Can I use Carousel Benchmark in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nestyme/awesome-prompts --skill carousel-benchmark -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/carousel-benchmark, .gemini/skills/carousel-benchmark, .github/skills/carousel-benchmark and .opencode/skills/carousel-benchmark in your project.

What does Carousel Benchmark need to run?

Going by SKILL.md and its folder, Carousel Benchmark needs the command-line tools its instructions call (python3) and credentials named APIFY_TOKEN. Our summary lists: Python 3; A credential in APIFY_TOKEN.

Does Carousel Benchmark access the network?

SKILL.md names 1 domain. As links in the text: x.com. This is read from the text; nothing was executed.

Is Carousel Benchmark safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Carousel Benchmark use?

No licence was found for Carousel Benchmark or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Carousel Benchmark use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Carousel Benchmark?

Skills that share tags, products or a category with Carousel Benchmark: Apify Competitor Intelligence (majiayu000/claude-skill-registry, 666 stars), Apify Audience Analysis (majiayu000/claude-skill-registry, 666 stars), Apify Content Analytics (majiayu000/claude-skill-registry, 666 stars) and Apify Trend Analysis (majiayu000/claude-skill-registry, 666 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Carousel Benchmark?

nestyme (a GitHub user) maintains it in nestyme/awesome-prompts, which has 149 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 30, 2026.

Source: nestyme/awesome-prompts on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.