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

Ugc Unboxing

by alecs5am in alecs5am/ralphy

How to make a generic UGC unboxing video for socials — generalized niche know-how, not a single video.

Apache-2.0Auto-check passedMarketing & SEO

Install Ugc Unboxing

skills CLI
$ npx skills add alecs5am/ralphy --skill ugc-unboxing -a claude-code

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

GitHub CLI
$ gh skill install alecs5am/ralphy ugc-unboxing --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/alecs5am/ralphy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ugc-unboxing .claude/skills/ugc-unboxing && 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
ugc-unboxing
GitHub stars
138
Token cost
~1.8k tokens
SKILL.md length
843 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
Apache-2.0

At a glance

How to make a generic UGC unboxing video for socials — generalized niche know-how, not a single video.

  • Works in 6 steps: Intake. Run the normal intake (target… → Reference gate. If the product is a… → Scenario. Hand the beat structure above… → …
  • The user asks for an unboxing / open the box / first look / haul / whats inside video for TikTok / Reels / Shorts
  • SKILL.md covers Trigger, What this skill is, Hard invariants and The niche, in one paragraph, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ugc Unboxing is an agent skill from alecs5am/ralphy. How to make a generic UGC unboxing video for socials — generalized niche know-how, not a single video. A domain overlay on the standard pipeline (intake → scenarist → art-director → editor): supplies the beat structure (cold-open hook → reveal → detail macro → reaction → CTA), hands-only framing and lens vocabulary, the ASMR-leaning SFX register, the default model stack, and the niche's common failure modes. Works for ANY product the user names — their coffee grinder, a no-name skincare set, a gadget — the skill…

Its SKILL.md is about 1.8k 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 Marketing & SEO, covering Influencer and creator marketing. It works with TikTok. The repository describes itself as: Open-source desktop app for content creation, with an agent runtime and standalone CLI. The licence is Apache-2.0.

When your agent uses it

  • The user asks for an unboxing / open the box / first look / haul / whats inside video for TikTok / Reels / Shorts
  • With no specific existing video to reproduce

Example prompts

  • “open the box”
  • “first look”
  • “s inside”
  • “/ugc-unboxing”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Intake. Run the normal intake (target language, aspect, duration, hard "no"s). Announce: "This is an unboxing — using the unboxing skill."…
  2. Reference gate. If the product is a named real brand item, the reference-required gate fires — get a ref photo or a logged…
  3. Scenario. Hand the beat structure above to the scenarist; produce STORYBOARD.md and get the user's "go".
  4. Surface master plate first, then product anchor, then per-beat anchors — one beat at a time with checkpoints (intake step 3 cadence).
  5. i2v per beat, then VO + SFX, then captions, then ralphy render .
  6. Hand off to /evaluator for the post-render quality gate.

What it can do on your machine

Read from SKILL.md and the folder at commit 8d139f0. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Ugc Unboxing loads about 1.8k tokens when it runs. Until then it costs about 239 tokens; SKILL.md has 843 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~239
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 passed

The automated check found no risky patterns in SKILL.md.

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

The full file from alecs5am/ralphy at commit 8d139f0, republished under its Apache-2.0 licence (© alecs5am). 843 words, ~1,766 tokens.

Download SKILL.mdSave it as .claude/skills/ugc-unboxing/SKILL.md (or your agent's skills folder).
name
ugc-unboxing
description
How to make a generic UGC unboxing video for socials — generalized niche know-how, not a single video. A domain overlay on the standard pipeline (intake → scenarist → art-director → editor): supplies the beat structure (cold-open hook → reveal → detail macro → reaction → CTA), hands-only framing and lens vocabulary, the ASMR-leaning SFX register, the default model stack, and the niche's common failure modes. Works for ANY product the user names — their coffee grinder, a no-name skincare set, a gadget — the skill supplies the know-how, the user supplies the subject. USE WHEN the user asks for an unboxing / "open the box" / "first look" / haul / "what's inside" video for TikTok / Reels / Shorts, with no specific existing video to reproduce. This is a niche SKILL (generalized), not a remix TEMPLATE (one specific video). For "remix this exact unboxing but swap X", that is the remix path in docs/skills-vs-templates.md, not this skill.
namespace
user

Trigger

FIRES on a generic unboxing brief: "make an unboxing of <product>", "open-the-box video", "first look at <X>", "haul video", "what's inside <package>". Any subject — the skill is subject-agnostic.

DO NOT FIRE when:

  • The user points at one specific unboxing video to reproduce (@template:<slug>, "remix this one", names a slug) → that is the remix path (ralphy template use <slug>), not this skill. See docs/skills-vs-templates.md.
  • The request is a different niche (talking-head, tier-list, before/after) → match that niche's skill.

What this skill is

A generalized overlay, not a finished video. It does not name a product, a script, or a cast — it tells the pipeline HOW unboxing videos work so the scenarist and art-director produce a strong one for whatever the user is unboxing. It runs through the normal pipeline; it does not replace intake gates, the reference-required gate, or the quality gates.

Hard invariants

  • This skill never bypasses AGENTS.md invariants. The reference-required gate still fires for a named real brand product (an "iPhone 16", a "Dyson Airwrap") — refuse without a ref or logged --no-ref-consent. A no-name / generic product proceeds without a ref.
  • All generation routes through ralphy generate (no raw API). Renders go through ralphy render <id>.
  • Read MODELS.md before naming any model id — the stack below is a default, not a hardcode.

The niche, in one paragraph

Unboxing lives or dies on the reveal moment and on tactile credibility. The viewer must believe a real human hand is touching a real object. Hands-only or over-shoulder framing (face optional), macro detail on textures/seams, and crisp ASMR-register SFX (cardboard, tape peel, plastic crinkle, the product's own click/snap) do more for retention than any VO line. Hook in the first ~1.5s with the still-sealed box and a tension line ("I cannot believe what's inside this").

Beat structure (default ~15-25s, 9:16)

BeatRole~DurationWhat it does
1. Sealed-box hookhook1.5-3sBox still closed, hands entering frame, tension line. Scroll-stopper.
2. The openbody2-4sThe peel / cut / lid-lift. SFX carries this beat — VO optional.
3. Revealbody2-4sFirst full look at the product, lifted toward camera. The payoff.
4. Detail macrobody3-6sClose textures, materials, the one feature worth buying for.
5. Reaction / verdictbody2-4sGenuine reaction beat; the one honest opinion line.
6. CTActa1.5-3sWhere to get it / "should I keep it?" engagement bait.

Scale beats up/down with the user's duration. Keep the hook ≤3s regardless.

Framing + lens vocabulary

  • Default framing: hands-only, top-down or over-shoulder onto a clean surface. Face is optional — many top unboxing creators never show one.
  • Lens: 35-50mm look for the wide; push to a macro register (85-100mm, shallow DOF) for the detail beat.
  • Lighting: soft key + fill, slight specular highlight on the product to read material. Avoid flat phone-flash look.
  • Surface: one consistent surface across beats — generate a surface/location master plate first (per intake step 3) so every beat matches.
  • Anti-AI-slop: real-camera credibility on hands (skin texture, slight asymmetry, natural nail/knuckle detail). See MEMORY.md anti-ai-slop notes; fold the photoreal-hands guideline in if available (ralphy guideline list).
Show full SKILL.md (339 more words)Show less

Audio register

  • SFX is the star. Tape peel, cardboard, plastic crinkle, the product's own click/snap. Crisp, close, ASMR-leaning.
  • VO is sparse — 1-2 honest lines max (hook + verdict). Don't narrate the open; let SFX carry it.
  • Music: low instrumental bed under the SFX, or none. Per AGENTS invariant, Kling auto-music is banned in-prompt; music is a separate ElevenLabs Music post-mix in the editor stage.

Default model stack (verify against MODELS.md)

  • Keyframes: google/gemini-3-pro-image-preview (nano-banana-pro) for the product + hands anchors.
  • i2v: kwaivgi/kling-v3.0-pro — the hand-on-object motion and tactile micro-gestures are its strength. Each beat needs a distinct physical action (peel, lift, rotate) — start/end frames must show a real motion delta (see MEMORY.md start-end-frame note), or clips read static.
  • VO: Kling --audio for EN; ElevenLabs for non-EN (confirm target language at intake).
  • Captions: per-slot on the locked VO.

Workflow

  1. Intake. Run the normal intake (target language, aspect, duration, hard "no"s). Announce: "This is an unboxing — using the unboxing skill." Aspect defaults 9:16.
  2. Reference gate. If the product is a named real brand item, the reference-required gate fires — get a ref photo or a logged --no-ref-consent. No-name product → proceed.
  3. Scenario. Hand the beat structure above to the scenarist; produce STORYBOARD.md and get the user's "go".
  4. Surface master plate first, then product anchor, then per-beat anchors — one beat at a time with checkpoints (intake step 3 cadence).
  5. i2v per beat, then VO + SFX, then captions, then ralphy render <id>.
  6. Hand off to /evaluator for the post-render quality gate.

Cookbook

  • "Make an unboxing of my new coffee grinder" → no-name product, no ref needed. 9:16, ~20s, hands-only, SFX-forward. Match this skill, run the pipeline.
  • "First look at the iPhone 16" → named real product → reference gate fires; ask for a ref photo before any generation.
  • "Remix the gadget-unboxing-asmr video but use my product" → NOT this skill; this is the remix path → ralphy template use gadget-unboxing-asmr.

See also

© alecs5am, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/ugc-unboxing of alecs5am/ralphy.

Open the folder on GitHubat commit 8d139f0

Compare with similar skills

Ugc Unboxing 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.

Ugc Unboxing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ugc Unboxing this skillalecs5am/ralphy138—~1.8kAutomated safety check: PassApache-2.0
Reelclaw Adsdansugc/reelclaw145—~3.9kAutomated safety check: NotesMIT
Higgsfield Content FactoryDaanKieft/ai-influencer116—~15kAutomated safety check: PassNone
Scenario Ugcscenario-labs/skills946—~3.1kAutomated safety check: PassMIT
Audience ResearchScrapeCreators/social-media-research-skills3.4k—~635Automated safety check: NotesMIT
Influencer Discoverytigerless-labs/influencer-discovery212—~2.5kAutomated safety check: NotesNone

Similar skills

  • Reelclaw Ads

    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.

    145 GitHub stars~3.9k tokensUpdated 12 days ago
    Marketing & SEOAuto-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

  • Scenario Ugc

    scenario-labs/skills

    A skill your agent uses when producing UGC-style creator video with Scenario: a talking-head ad or testimonial from a portrait and a script, a founder clip, a product demo or unboxing, a reaction or…

    946 GitHub stars~3.1k tokensUpdated yesterday
    Marketing & SEOAuto-check passed

  • Audience Research

    ScrapeCreators/social-media-research-skills

    A skill your agent uses when the user wants to evaluate a creator, influencer, or brand audience using public profile signals, TikTok audience demographics, follower/following data, comments…

    3.4k GitHub stars~635 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check: notes

  • Influencer Discovery

    tigerless-labs/influencer-discovery

    Find the bloggers/creators who can help promote your work, capture their contact info, and append them to the target sheet in Google Sheets.

    212 GitHub stars~2.5k tokensUpdated 18 days ago
    Marketing & SEOAuto-check: notes

  • Gingiris Ugc Matrix

    Gingiris-1031/Competitor-analysis-tool

    🇺🇸 UGC Matrix Growth Playbook — Scale user-generated content with AI + real creators.

    110 GitHub stars~790 tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed

More from alecs5am/ralphy

All 28 skills in this repo

  • Gsap

    alecs5am/ralphy

    GSAP animation reference for HyperFrames. An agent skill from alecs5am/ralphy.

    138 GitHub stars~2.4k tokensUpdated 18 days ago
    Auto-check passed

  • Researcher

    alecs5am/ralphy

    Deep-research workflow for UGC reference material — turns one or more URLs / handles / trend queries into a single cited research report (report.md + sources.json) that a scenarist or art-director…

    138 GitHub stars~1.9k tokensUpdated 18 days ago
    Auto-check passed

  • Editor

    alecs5am/ralphy

    Composition and render craft — assembles scenario.json plus asset-manifest.json into a HyperFrames HTML composition and renders the mp4.

    138 GitHub stars~3.6k tokensUpdated 18 days ago
    Auto-check passed

  • Evaluator

    alecs5am/ralphy

    Quality evaluation of rendered UGC mp4s — scene segmentation, audio loudness / dead-air, caption density, and per-scene visual analysis.

    138 GitHub stars~3.6k tokensUpdated 18 days ago
    Auto-check passed

  • Producer

    alecs5am/ralphy

    End-to-end orchestration — the wrapper that drives the whole production contract across roles, plus batch production.

    138 GitHub stars~4.7k tokensUpdated 18 days ago
    Auto-check passed

  • Scenarist

    alecs5am/ralphy

    Scenario and script craft — writes and reworks the scene-by-scene scenario.json: hook, beat structure, per-scene VO, on-screen text, pacing, and the language/aspect pre-flight.

    138 GitHub stars~3.2k tokensUpdated 18 days ago
    Auto-check passed

Works with

Categories

Questions about Ugc Unboxing

What does Ugc Unboxing do?

How to make a generic UGC unboxing video for socials — generalized niche know-how, not a single video. Ugc Unboxing is an agent skill from alecs5am/ralphy. How to make a generic UGC unboxing video for socials — generalized niche know-how, not a single video.

When should I use Ugc Unboxing?

Ugc Unboxing fits situations like: the user asks for an unboxing / open the box / first look / haul / whats inside video for TikTok / Reels / Shorts; with no specific existing video to reproduce.

How do I install Ugc Unboxing in Claude Code?

Run `npx skills add alecs5am/ralphy --skill ugc-unboxing -a claude-code`. Or copy the skill folder (.agents/skills/ugc-unboxing in alecs5am/ralphy) into .claude/skills/ugc-unboxing in your project. Claude Code loads it when a task matches its description.

How do I install Ugc Unboxing in Codex?

Run `npx skills add alecs5am/ralphy --skill ugc-unboxing -a codex`. Or copy the skill folder (.agents/skills/ugc-unboxing in alecs5am/ralphy) into .agents/skills/ugc-unboxing in your project. Codex loads it when a task matches its description.

Can I use Ugc Unboxing 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 alecs5am/ralphy --skill ugc-unboxing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ugc-unboxing, .gemini/skills/ugc-unboxing, .github/skills/ugc-unboxing and .opencode/skills/ugc-unboxing in your project.

What does Ugc Unboxing need to run?

SKILL.md names no scripts, command-line tools or credentials: Ugc Unboxing is instructions for the agent only.

Does Ugc Unboxing access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ugc Unboxing safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ugc Unboxing use?

Ugc Unboxing is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ugc Unboxing use?

About 1.8k tokens (SKILL.md is roughly 7.1k 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 Ugc Unboxing?

Skills that share tags, products or a category with Ugc Unboxing: Reelclaw Ads (dansugc/reelclaw, 145 stars), Higgsfield Content Factory (DaanKieft/ai-influencer, 116 stars), Scenario Ugc (scenario-labs/skills, 946 stars) and Audience Research (ScrapeCreators/social-media-research-skills, 3.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ugc Unboxing?

alecs5am (a GitHub user) maintains it in alecs5am/ralphy, which has 138 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on September 22, 2026.

Source: alecs5am/ralphy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.