New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Reelclaw Ads

by dansugc in dansugc/reelclaw

Make short-form UGC video ads (TikTok, Reels, Shorts) for the product in the current repo with DansUGC ReelClaw and real human creator reactions from the DansUGC library.

MITAuto-check: notesMarketing & SEO

Install Reelclaw Ads

skills CLI
$ npx skills add dansugc/reelclaw --skill reelclaw-ads -a claude-code

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

GitHub CLI
$ gh skill install dansugc/reelclaw reelclaw-ads --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/dansugc/reelclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/reelclaw/skills/reelclaw-ads .claude/skills/reelclaw-ads && 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
reelclaw-ads
GitHub stars
145
Token cost
~3.9k tokens
SKILL.md length
1,837 words
Files
16 (incl. scripts, references)
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Make short-form UGC video ads (TikTok, Reels, Shorts) for the product in the current repo with DansUGC ReelClaw and real human creator reactions from the DansUGC library.

  • Works in 6 steps: Connect and costs → Pick the mode → Shared steps (both modes) → …
  • The user asks for UGC ads
  • SKILL.md covers 0. Connect and costs, 1. Pick the mode, 2. Shared steps (both modes) and 3. Volume mode (hosted engine), plus 3 more sections
  • Runs Shell and JavaScript scripts from its folder; calls codex, node and npx; reaches dansugc.com

What it does

Reelclaw Ads is an agent skill from dansugc/reelclaw. Make short-form UGC video ads (TikTok, Reels, Shorts) for the product in the current repo with DansUGC ReelClaw and real human creator reactions from the DansUGC library. Two modes. Volume mode drives the hosted ReelClaw engine over the dansugc MCP server (reelclaw tools) for many variations fast. Studio mode edits 1-5 polished ads locally with HyperFrames templates (TikTok Sans, safe-zone captions) and a mandatory look-at-the-frames QA loop, for creative control and specific edits. Use when the user asks for UGC…

Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/errors.md` and `references/footage.md`).

It sits in Marketing & SEO, covering Influencer and creator marketing and Motion graphics. It works with TikTok, Model Context Protocol and HeyGen. The repository describes itself as: UGC reel production engine for AI coding agents. Create scroll-stopping short-form videos at scale. The licence is MIT.

When your agent uses it

  • The user asks for UGC ads
  • TikTok/Reels ads
  • Make N ads for this app
  • HyperFrames reels

Example prompts

  • “make N ads for this app”
  • “/reelclaw-ads”

Requirements

  • Node.js
  • A Bash shell

Workflow steps

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

  1. Connect and costs
  2. Pick the mode
  3. Shared steps (both modes)
  4. Volume mode (hosted engine)
  5. Studio mode (local HyperFrames)
  6. When things go wrong

What it can do on your machine

Read from SKILL.md and the folder at commit 140e866. 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

    Ships 2 files in scripts/ (Shell and JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • codex
    • node
    • npx
    • ffmpeg
    • ffprobe
    • yt-dlp
    • claude
    • curl
    • brew
    • nvm
    • apt

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • dansugc.com

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Reelclaw Ads loads about 3.9k tokens when it runs, and up to ~24k if it reads all its reference files. Until then it costs about 187 tokens; SKILL.md has 1,837 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~187
When it runs · the whole SKILL.md, loaded when a task matches
~3.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~24k

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.

  • NoteRuns commands with sudoSKILL.md:133
    install node ffmpeg`, `nvm install 22`, `sudo apt install ffmpeg`)

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); the scripts in this folder are not scanned.

SKILL.md

The full file from dansugc/reelclaw at commit 140e866, republished under its MIT licence (© dansugc). 1,837 words, ~3,892 tokens.

Download SKILL.mdSave it as .claude/skills/reelclaw-ads/SKILL.md (or your agent's skills folder). This skill also uses 15 other files; get the full folder from GitHub.
name
reelclaw-ads
description
Make short-form UGC video ads (TikTok, Reels, Shorts) for the product in the current repo with DansUGC ReelClaw and real human creator reactions from the DansUGC library. Two modes. Volume mode drives the hosted ReelClaw engine over the dansugc MCP server (reelclaw_* tools) for many variations fast. Studio mode edits 1-5 polished ads locally with HyperFrames templates (TikTok Sans, safe-zone captions) and a mandatory look-at-the-frames QA loop, for creative control and specific edits. Use when the user asks for UGC ads, reaction ads, TikTok/Reels ads, "make N ads for this app", ReelClaw, DansUGC videos, HyperFrames reels, editing or re-cutting an ad (caption style, position, timing), or checking/downloading ReelClaw batches.
license
MIT
metadata.author
DansUGC
metadata.version
1.2.0

DansUGC ReelClaw: UGC ads from your repo

You are the producer. Each ad = a real creator's reaction clip (the hook, with your text on top) cut into the product demo. DansUGC reactions are always real human creators, never AI; never claim or imply otherwise. Always write the brand as DansUGC (lowercase s, capital UGC).

<skill-dir> below means the directory that contains this SKILL.md (Claude Code prints it when the skill loads; a Codex script install puts it at ~/.agents/skills/reelclaw-ads).

0. Connect and costs

  • Tools live on the dansugc MCP server. Clients may prefix them (mcp__plugin_reelclaw_dansugc__… in Claude Code, mcp__dansugc__… when added by hand). This skill uses bare names: reelclaw_* (volume mode), search_videos, purchase_videos, tiktok_search_videos, get_media_upload_url, … (both modes). Map: references/tools.md.
  • No dansugc tools? Tell the user how to connect, then stop:
    • Claude Code: /plugin marketplace add dansugc/reelclaw + /plugin install reelclaw@dansugc (or claude mcp add --transport http dansugc https://dansugc.com/mcp), then /mcp → the server (plugin:reelclaw:dansugc, or dansugc if added by hand) → Authenticate.
    • Codex: codex plugin marketplace add dansugc/reelclaw + codex plugin add reelclaw@dansugc (or codex mcp add dansugc --url https://dansugc.com/mcp), then codex mcp login dansugc.
    • Auth is OAuth only (browser login with the DansUGC account). Never ask for or suggest an API key. If a tool says it "no longer accepts API keys — reconnect with OAuth", see references/errors.md.
  • Cost (say it when asked, and before anything is spent): needs a Growth or Scale plan (team members use their team owner's plan); if a tool returns reelclaw_plan_required, relay the message and the upgrade link and stop. On top of the plan, usage comes from DansUGC credits. Editing and rendering are included in both modes. Users pay only for (a) reaction clips they don't already own (library clips are 11 credits each, images 8, less the plan's discount; owned clips are never charged again) and (b) research queries through the MCP (TikTok/Instagram search, 0.02 credits per query, only on success). Top up at https://dansugc.com/dashboard/credits.
  • Talk in credits. Every price, quote, and balance is in DansUGC credits ("11 credits per clip", "Total: 104.50 credits", "Balance: 245.50 credits"). Never write "$" amounts; only convert to dollars if the user explicitly asks, and then say the credit amount first. Quote totals come from the tools (purchase_videos quote step, reelclaw_quote), never from multiplying per-clip prices yourself (owned clips are free and the plan discount is applied for you).
  • Accounts. A user has a Personal Account and may belong to teams (each with its own credits and plan discounts). When the user mentions a team, company, or teammate, or a spend fails for low personal balance, call list_accounts and pass that team's project_id to every account tool (search_videos, get_video, purchase_videos, list_purchases, get_balance, the research tools, reelclaw_create_batch / reelclaw_list_batches / reelclaw_options). Omit project_id for the Personal Account. A ReelClaw batch stays on the account it was created on. Never switch accounts on your own; before the first spend on a team in a conversation, name the team and the amount and get an explicit yes.
  • Tool results are JSON or Markdown; follow any next_action. Summarize; don't dump raw output.

1. Pick the mode

Volume mode (hosted)Studio mode (local HyperFrames)
Best for6-60 variations fast, testing many hooks1-5 polished ads, specific edits, creative control
RenderingDansUGC servers (reelclaw_* tools)This machine (npx reelclaw-templates + HyperFrames)
Needs locallynothingNode >= 22, ffmpeg/ffprobe (installed below)
Creative controlhooks, reactions, musiceverything: trims, timing, caption style/position, layout
You look at the resultoptionalmandatory QA loop on real frames

Default: the user asks for a number ≥ 6, "a batch", or speed → Volume. The user asks for 1-5, "polished", "high quality", a specific edit ("move the caption up", "cut on her reaction", "snapchat-style text"), a format the engine doesn't do (no-yapping tutorial, greenscreen), or wants to use their own footage → Studio. Unsure → ask ONE question with your pick pre-filled ("I'll make 3 polished ads locally (studio mode). OK, or do you want 10+ quick variations from the hosted engine?").

2. Shared steps (both modes)

  1. Understand the product from the repo, truthfully. Read README*, package.json, store listing (fastlane/metadata/**), landing copy, llms.txt, before asking anything. Show a 4-6 line brief: what it is, who it's for, the one painful problem, the aha moment on screen, proof you actually found. Never invent features, prices, results, testimonials. At most one question, with your best guess pre-filled. Details: references/product-brief.md.
  2. Find the demo. A 10-30 s screen recording that shows the aha early:
    sh
    find . -type f \( -iname '*.mp4' -o -iname '*.mov' \) -not -path '*/node_modules/*' \
  -not -path '*/.git/*' -not -path '*/reelclaw-output/*' -not -path '*/reelclaw-studio/*' 2>/dev/null | head -20
    None? Ask for one (phone screen recording, or QuickTime → File → New Screen Recording).
  3. Research real viral examples (optional, paid). tiktok_search_videos / instagram_search_reels cost 0.02 credits per successful query. Before the first query say how many you plan (default ≤ 5, 0.10 credits) and proceed only if the user agrees or already asked for research. Use it to pick the format and steal hook structures, never text verbatim. How: references/research.md.
  4. Write the hooks. Lowercase, first person or POV/"when", under 80 characters, specific to the pain or the aha, emotion matching the reaction, no invented claims, "this app" instead of the brand name. Vary formats. Show the user a table (# · hook · format · reaction emotion). Playbook: references/hooks.md.
  5. Choose reactions from the DansUGC library (real creators). Volume: the engine matches them; you review. Studio: you search, compare previews, and buy only after the user confirms the price. How: references/footage.md.
  6. Music. If the user gave no sound and didn't ask for silent videos, don't make them hunt for one: reelclaw_trending_music { category } returns trending TikTok sounds for the niche (0.02 credits per query, 1-2 per lookup, cached 6 h for free repeats; say it before the first call). Pick 3-5 that match the hook's energy (prefer rising, length ≥ the reel). Volume: pass its music_links to reelclaw_update_batch before quoting. Studio: download a song's preview_url and use it as music. Ads: relay license_note (paid ads and TikTok business accounts need Commercial Music Library tracks; never say a sound is cleared). How: references/music.md.

3. Volume mode (hosted engine)

Full procedure (create → advance → hooks → demo upload → quote → render → download): references/volume-mode.md. Read it before the first reelclaw_* call. Non-negotiables:

  • reelclaw_create_batch → loop reelclaw_advance_batch until done → rewrite hooks with reelclaw_update_batch (no music yet? reelclaw_trending_music → its music_links in the same update) → reelclaw_add_demo + curl -X PUT --data-binary → reelclaw_quote.
  • Show the quote and STOP for an explicit yes before reelclaw_render. Never treat the original request or silence as consent; any edit after a quote invalidates it (re-quote, re-confirm).
  • Poll reelclaw_get_batch every poll_after_seconds; download each ready video to ./reelclaw-output/<batch_id>/; finish with paths, hooks, credits spent, dashboard_url.
Show full SKILL.md (766 more words)Show less

4. Studio mode (local HyperFrames)

Templates: reaction_demo (reaction + hook → hard cut → demo; the default for app ads), no_yapping (silent split-screen tutorial), greenscreen_reaction (creator cut out over a video). Inputs, flags, and when to use each: references/studio-templates.md.

a. Preflight (every session):

sh
node --version                                   # must be v22+; HyperFrames refuses to start on older Node
ffmpeg -version | head -n 1 && ffprobe -version | head -n 1
yt-dlp --version                                 # optional: only for TikTok/IG/YouTube page links as inputs

Missing → offer to install (brew install node ffmpeg, nvm install 22, sudo apt install ffmpeg) and wait. Can't install → offer Volume mode. First render also fetches HyperFrames and a headless Chrome through npx (one-time, a few minutes).

b. Install one template copy per reel (templates are not concurrency-safe):

sh
mkdir -p reelclaw-studio
npx --yes reelclaw-templates@latest reaction_demo reelclaw-studio/reaction_demo-<slug>

<slug> = short kebab-case concept name. The installer refuses a non-empty directory (pick a new slug). Hook variants of the same reel can run one after another in the same directory with different names; never run two generators or renders in one directory at the same time. Offer to add reelclaw-studio/ and reelclaw-output/ to .gitignore (ask first).

c. Footage. Reactions: search_videos (free) → shortlist 3-6 with price, duration, emotion, preview → purchase_videos WITHOUT expected_total_cents (a free quote: exact total + the account charged) → show it, wait for an explicit yes → purchase_videos again with the same ids + expected_total_cents (charges; owned clips are free) → curl -fL -o reelclaw-studio/footage/<file>.mp4 "<download_url>" within the hour. Skip clips with burned-in text. Choose the reaction's trim from a frame sheet so the peak expression lands in the first second. Demo: pre-trim it so the aha is on screen within ~2 s of the cut. Details, commands, and the no-purchase path: references/footage.md.

d. Write the params file with your file-writing tool (not echo; JSON-escape the text). Keys are the template's flag names without -- (exact list per template in studio-templates.md):

json
{
  "name": "pov-screen-time-v1",
  "reaction": "reelclaw-studio/footage/reaction-shocked-1.mp4",
  "trim": 0.4,
  "demo": "demo/aha.mp4",
  "hook": "pov: your phone won't open tiktok until you've walked 2k steps",
  "hook-position": "top"
}

Save it as reelclaw-studio/<template>-<slug>/params-<name>.json. Never put user text into a shell command line: the wrapper passes it to the generator without a shell and refuses values starting with -- (the generators would read them as flags).

e. Generate + render + QA frames (run from the repo root):

sh
node <skill-dir>/scripts/run-generator.mjs reelclaw-studio/reaction_demo-<slug> \
  reelclaw-studio/reaction_demo-<slug>/params-pov-screen-time-v1.json --render

The wrapper copies media into the template's assets/, runs new-reel.mjs, vendors GSAP locally (a CDN hiccup otherwise drops every animation while the render still "succeeds"), renders with the template's pinned HyperFrames version, then runs scripts/qa-frames.sh. Output: renders/<name>.mp4 + qa/<name>/ (frames, contact sheet, report.txt); the full HyperFrames log is in renders/<name>.render.log. HyperFrames exits 0 even when GSAP, a font, or a video failed to load: if the wrapper prints RENDER WARNINGS, fix them before anything else. A 10-15 s reel renders in roughly 25-30 s on a recent laptop.

f. QA loop (mandatory, max 3 passes). Open and look at every PNG listed in report.txt (Claude Code: the Read tool on the .png; Codex: view_image). Check each item in references/qa-checklist.md: TikTok Sans actually rendered (not a fallback font), every caption inside the green safe box, hook readable within 1 s, reaction ≤ 3 s and cut right after its peak, demo shows the aha within ~2 s of the cut, no black or frozen frames, audio present (or silent on purpose), duration on target, 1080×1920. Fix (params, trims, footage, or a composition edit), re-render (params change: step e again; composition edit: add --render-only instead of --render, since regenerating overwrites hand edits), look again. Never deliver a render you haven't looked at. After 3 passes, deliver the best one and list what's still off.

g. Custom edits beyond the flags (caption style, exact position, a pop-in, a second caption, a different demo fit): edit the generated compositions/<name>.html, then re-render with run-generator.mjs … --render-only, following references/hyperframes-editing.md. If the HyperFrames skills are installed (hyperframes, hyperframes-core, …), load them for bigger custom compositions; this skill does not require them.

h. Deliver. Copy finals to ./reelclaw-output/studio/<name>.mp4; summarize path, hook, length, footage used, credits spent (clips + research queries), and the QA result (pass / fixed / still off). Offer: more hook variants (one render each; media is already staged), another template, or publishing. Publishing via DansUGC Posting (get_media_upload_url → PUT → create_post, one unique video per account) only on request and after the user confirms account + caption: references/publishing.md.

5. When things go wrong

Ground rules

  • Real human creators only; never describe DansUGC reactions as AI.
  • Truthful hooks and captions only: nothing the repo or user didn't back up.
  • Never spend credits (render quote, clip purchase, research queries) without telling the user the cost first and getting a yes for purchases and renders.
  • Never deliver a studio render you haven't looked at frame by frame.
  • Demo uploads (volume mode) go to DansUGC private storage; only upload what the user is fine sharing. Studio mode keeps footage on this machine. Never upload secrets.
  • Don't dump raw JSON on the user; keep IDs out of chat unless asked.

© dansugc, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 15 other files (scripts, references) in plugins/reelclaw/skills/reelclaw-ads of dansugc/reelclaw.

  • SKILL.md
  • agents/openai.yaml
  • references/errors.md
  • references/footage.md
  • references/hooks.md
  • references/hyperframes-editing.md
  • references/music.md
  • references/product-brief.md
  • references/publishing.md
  • references/qa-checklist.md
  • references/research.md
  • references/studio-templates.md
  • references/tools.md
  • references/volume-mode.md
  • scripts/qa-frames.sh
  • scripts/run-generator.mjs

Open the folder on GitHubat commit 140e866

Compare with similar skills

Reelclaw Ads 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.

Reelclaw Ads compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Reelclaw Ads this skilldansugc/reelclaw145—~3.9kAutomated safety check: NotesMIT
Tiktok Launch Videocognyai/claude-code-marketing-skills104—~2.7kAutomated safety check: NotesNone
Higgsfield Content FactoryDaanKieft/ai-influencer116—~15kAutomated safety check: PassNone
ShowtimeFavioVazquez/showtime220—~3kAutomated safety check: PassMIT
Create VideoCuongyd196/auto-compare-video211—~2.8kAutomated safety check: NotesCustom licence
Super Video MakerBomx/super-video-maker-skill310—~11kAutomated safety check: NotesNone

Similar skills

  • Tiktok Launch Video

    cognyai/claude-code-marketing-skills

    Produce a 9:16 TikTok-native launch video for a product, feature, or campaign using HyperFrames.

    104 GitHub stars~2.7k tokensUpdated 3 mo ago
    Media & CreativeAuto-check: notes

  • Higgsfield Content Factory

    DaanKieft/ai-influencer

    A 5-stage AI content pipeline using Higgsfield MCP, focused on viral UGC content split evenly across 5 formats: UGC Entertainment (challenges), Street Interview, Unboxing, Product Review, ASMR.

    116 GitHub stars~15k tokensUpdated 4 mo ago
    Marketing & SEOAuto-check passed

  • Showtime

    FavioVazquez/showtime

    A skill your agent uses when the user wants a video made, edited or finished: a launch or promo, product demo, explainer, trailer or teaser, tutorial or walkthrough, a screen recording turned into a…

    220 GitHub stars~3k tokensUpdated yesterday
    Media & CreativeAuto-check passed

  • Create Video

    Cuongyd196/auto-compare-video

    Tạo một video MỚI cho series "so sánh / phân biệt kiến thức" của repo này — clip dọc TikTok/Reels/Shorts 30-40s, layout 3-zone cố định theo DESIGN.md, voiceover tiếng Việt sinh bằng VieNeu TTS…

    211 GitHub stars~2.8k tokensUpdated 17 days ago
    Media & CreativeAuto-check: notes

  • Super Video Maker

    Bomx/super-video-maker-skill

    End-to-end AI video production skill for agentic frameworks.

    310 GitHub stars~11k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes

  • Kinocut

    KyaniteLabs/kinocut

    Use Kinocut for guarded video editing, source-backed planning, FFmpeg operations, media analysis, subtitles, audio workflows, Hyperframes or Revideo rendering, repurposing packages, and release…

    198 GitHub stars~5.7k tokensUpdated yesterday
    Media & CreativeAuto-check passed

More from dansugc/reelclaw

  • Reelclaw

    dansugc/reelclaw

    Create, produce, and publish UGC-style short-form video reels at scale.

    145 GitHub starsUsed in 1 repo~8.2k tokens
    Auto-check: notes

Works with

Categories

Questions about Reelclaw Ads

What does Reelclaw Ads do?

Make short-form UGC video ads (TikTok, Reels, Shorts) for the product in the current repo with DansUGC ReelClaw and real human creator reactions from the DansUGC library. Reelclaw Ads is an agent skill from dansugc/reelclaw. Make short-form UGC video ads (TikTok, Reels, Shorts) for the product in the current repo with DansUGC ReelClaw and real human creator reactions from the DansUGC library.

When should I use Reelclaw Ads?

Reelclaw Ads fits situations like: the user asks for UGC ads; tikTok/Reels ads; make N ads for this app; hyperFrames reels.

How do I install Reelclaw Ads in Claude Code?

Run `npx skills add dansugc/reelclaw --skill reelclaw-ads -a claude-code`. Or copy the skill folder (plugins/reelclaw/skills/reelclaw-ads in dansugc/reelclaw) into .claude/skills/reelclaw-ads in your project. Claude Code loads it when a task matches its description.

How do I install Reelclaw Ads in Codex?

Run `npx skills add dansugc/reelclaw --skill reelclaw-ads -a codex`. Or copy the skill folder (plugins/reelclaw/skills/reelclaw-ads in dansugc/reelclaw) into .agents/skills/reelclaw-ads in your project. Codex loads it when a task matches its description.

Can I use Reelclaw Ads 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 dansugc/reelclaw --skill reelclaw-ads -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reelclaw-ads, .gemini/skills/reelclaw-ads, .github/skills/reelclaw-ads and .opencode/skills/reelclaw-ads in your project.

What does Reelclaw Ads need to run?

Going by SKILL.md and its folder, Reelclaw Ads needs a shell and JavaScript for the scripts in its folder and the command-line tools its instructions call (codex, node, npx, ffmpeg, ffprobe and yt-dlp). Our summary lists: Node.js; A Bash shell.

Does Reelclaw Ads access the network?

SKILL.md names 1 domain. In commands or code: dansugc.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Reelclaw Ads safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Reelclaw Ads use?

Reelclaw Ads is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Reelclaw Ads use?

About 3.9k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 20k tokens, read only when the agent opens those files.

What are the alternatives to Reelclaw Ads?

Skills that share tags, products or a category with Reelclaw Ads: Tiktok Launch Video (cognyai/claude-code-marketing-skills, 104 stars), Higgsfield Content Factory (DaanKieft/ai-influencer, 116 stars), Showtime (FavioVazquez/showtime, 220 stars) and Create Video (Cuongyd196/auto-compare-video, 211 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reelclaw Ads?

dansugc (a GitHub organization) maintains it in dansugc/reelclaw, which has 145 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 28, 2026.

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