Unboxing & Comparison Review

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites: none for the install itself: no account, no API key, no paid service, and nothing else to install first. For using the skill afterwards, read this first: its only bundled script, scripts/make_cards.py, is local-only and needs Python 3 with Pillow (PIL), plus a CJK font — the script searches system font paths for Noto Sans CJK Bold / Source Han Sans Bold / PingFang / Microsoft YaHei Bold / WenQuanYi Zen Hei and exits with "No CJK font found; pass --font /path/to/font.ttf" if it finds none. Pillow is not part of the Python standard library and is not installed by this install; the repository root requirements.txt lists pillow>=10 (the only entry relevant to this skill) and numpy>=1.24 and edge-tts>=6.1 (both belong to other skills in the repository and are never imported by this skill). No generation API, no key and no online link are used by this skill at all, and no ffmpeg is needed by this skill's script. Install "unboxing-comparison-review" for me. It gives reusable templates for the two most credible ecommerce video forms, unboxing and comparison review: Template A, an unboxing video of 30–45 seconds in 7 segments (hook on the parcel close-up, packaging contents, first impression, one strongest selling-point demonstration, one real flaw, who it is and is not for, call-to-action end card); Template B, a comparison review of 45–60 seconds (both products side by side, contenders introduced without naming and disparaging a competitor, test design with the same environment, same start and same duration stated in the subtitles, item-by-item comparison, a check/cross summary table, honest who-it-is-for and call to action); fair-comparison rules (test under the same conditions, show the test process and not only the result, no retouching and no speed-up, keep the raw test records, no competitor named and disparaged, no absolute claims); a shot checklist; a prompt template for writing the voice-over script and storyboard; output as a storyboard table plus storyboard.json; and local product cards (end cards, selling-point cards, comparison or summary cards) drawn by scripts/make_cards.py. Repository: https://github.com/xianyu110/ecommerce-video-skills (the skill is the whole skills/unboxing-comparison-review/ folder at the pinned commit: SKILL.md plus its scripts/ folder, 2 files) Pinned version: install the code at commit 96c49b349b7d975bda8f05ce6669c1d33500c269 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/xianyu110/ecommerce-video-skills into a temporary folder, check out commit 96c49b349b7d975bda8f05ce6669c1d33500c269, and copy the skills/unboxing-comparison-review/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-19: [FINGERPRINTS] - SKILL.md: SHA-256 750618cc7b5ebec53b36415b0749c2410d3a6062059d4dc9ca6b4ee7effec881 - scripts/make_cards.py: SHA-256 b6173bebd9a9a3d69d14688b091d3328f0e4792c72e6fde7530205babc2136d5 If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full and read the only script in scripts/ (make_cards.py), and tell me in plain words: what the skill does when used, which services it connects to, whether it reads or sends any personal information or keys, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 2 files only: SKILL.md (4,819 bytes) and one Python script in scripts/ (make_cards.py, 8,184 bytes). That script is a byte-identical copy of the same-named script at the repository root (scripts/make_cards.py, same SHA-256): the skill is self-contained in its own folder and needs no file from elsewhere in the repository — not the other 12 skills, not the root scripts/, not the README, and not the repository requirements.txt at install time. SKILL.md only ever calls the script sitting next to it (make_cards.py, relative to the skill folder). SKILL.md says the storyboard can be turned into a renderable storyboard.json, but no renderer is in this skill's folder: producing that JSON is a local text output, and rendering it into a video is not done by this skill. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit. No script is run during installation, no key is asked for, and there is no telemetry in the folder. - What leaves this machine at use time, disclosed here before it ever happens: nothing. Using the skill is a separate step that only starts when I ask for an unboxing or comparison review, and it sends nothing to anyone: scripts/make_cards.py makes no network call at all — it imports only argparse, glob, os and Pillow (PIL), contains no URL, no API client, no key handling and no subprocess call, and SKILL.md defines no API-key route and no online-link route for this skill. The prompt template in SKILL.md is text I use with you locally in our conversation. Two mentions in SKILL.md are not sends by the skill: the link to the sister repository ecommerce-image-skills (named only as an optional way to make a comparison infographic) is a plain GitHub link that nothing opens during installation or use, and publishing the finished video and disclosing a sponsored or gifted review as an ad/cooperation per the platform's own rules happen manually, by me, on the platform I choose — the skill itself never contacts any platform. - The local-only parts at use time: scripts/make_cards.py runs entirely on this machine — it takes a required --name, --points separated by |, and optional --cta, --kicker, --image, --size (default 1080x1920, or 1920x1080 for a side-by-side landscape card), --theme (sage, night, peach or mono; default sage) and --font; with --image it opens my product image locally with Pillow, otherwise it draws a placeholder product silhouette, draws the gradient background, product panel, name, selling points and call-to-action button locally with the CJK font it finds (or the one I pass with --font), and writes the card PNG to the local output file (default card.png, -o/--out). The two templates, the fair-comparison rules, the shot checklist, the prompt template, the storyboard table and storyboard.json, and the final checklist in SKILL.md also stay local, between you and me. Rules from SKILL.md: all data come from tests actually run, with the test conditions shown on screen and the raw records kept; include at least 1 real flaw and a who-it-is-not-for line; never name and disparage a competitor and never use absolute claims; label a sponsored or gifted review as ad/cooperation where the platform requires it. - Do not install Pillow or anything else during this install, do not run make_cards.py, and do not generate any card: setup of the use-time dependencies is my decision, later, when I actually ask for a review. 3. When I say "yes, install", install it as a skill: copy the whole unboxing-comparison-review folder into the agent's skills directory, in a folder named "unboxing-comparison-review", keeping all 2 files (SKILL.md at its root and the one script in its scripts/ subfolder). A manual clone followed by copying the skills/unboxing-comparison-review folder into ~/.claude/skills/ is the route described here; any other route is fine only as long as every installed file matches its fingerprint. 4. Verify with no network calls: frontmatter valid (name: unboxing-comparison-review), all 2 files in place with matching fingerprints. Do not run make_cards.py to verify. 5. Report what was installed, where, and what I still need to do myself (for example: provide the product and any comparison object, the real tests I can run and their actual results, the duration, platform and on-camera style myself; install Python 3 with Pillow and have a CJK font available or pass --font, if I want the script to render cards; using the skill is a separate step that only starts when I ask for it, and no use-time send happens on it at all, as disclosed above). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.