product-reel-generator

Generates Instagram-ready product reels from any e-commerce product page URL. Scrapes product images, classifies by type, generates AI-animated clips via Higgsfield API, creates text overlays with style presets, and composes a 15-20 second reel with music. Supports model-based and product-only reels.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, well-structured production pipeline with executable commands, real API specifics, cost estimates, and thoughtful failure-mode handling. The main gaps are the lack of concrete code for scraping and Pillow overlay generation, and no explicit final-output validation step.

Suggestions

Add concrete, copy-paste-ready code for the two underspecified steps: a jq/curl example for the Shopify `.json` scrape and a Pillow snippet (or bundled script) for generating transparent text-overlay PNGs.

Add a final validation step after Step 7, e.g. `ffprobe` the output to confirm 1080x1920, 25fps, 15-20s, and audio present, with a fix-and-retry loop if specs fail.

Move the style-preset table and prompt-guidance library into a `references/presets.md` file to slim the SKILL.md body and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational throughout — every section carries instructions Claude does not already know (model IDs, credit costs, zoompan expressions, prompt guardrails like "does not stop or turn around"), with no padding or explanation of known concepts. It is not 4 because there are no discernible instances of over-explanation to trim.	5 / 5
Actionability	Mostly executable: concrete FFmpeg commands (Ken Burns, overlay, concat, audio mix), exact API endpoints and model paths, and a real bundled script referenced as `scripts/higgsfield_video.py`. It is not 5 because Step 1's scraping methods ("append .json… extract images") and Step 5's Pillow overlay generation lack concrete, copy-paste-ready code.	4 / 5
Workflow Clarity	A clear 7-step sequence with explicit fallbacks ("Try these methods in order until one works", "If a generated AI clip looks bad… replace with Ken Burns"), a polling loop until `status: "completed"`, and dependency verification before starting. It is not 5 because there is no final validation of the output reel (e.g. verifying duration, resolution, or playability) after composition.	4 / 5
Progressive Disclosure	Good structure with well-organized sections and one clearly signaled, real bundle script (`scripts/higgsfield_video.py`, verified present). It is not 5 because the style-preset/font spec and prompt guidance are inlined in the SKILL.md body rather than split into reference files, and the referenced pack `fonts/` directory is not part of this bundle.	4 / 5
	Total	17 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, third-person description that fully covers what the skill does across the whole production pipeline, with excellent distinctiveness. Its main weakness is the absence of any explicit "Use when…" trigger clause, which caps completeness and leaves some natural trigger terms (product video, promo) uncovered.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user provides a product page URL and wants an Instagram reel, product video, or promo for it."

Add natural synonyms such as "product video", "promo video", or "short-form video" so users' phrasing matches the description.

Optionally mention supported platforms (e.g. Shopify, Zara) in the description to strengthen trigger matching for "make a reel for my Shopify product".

Dimension	Reasoning	Score
Specificity	The description enumerates the entire pipeline concretely — "Scrapes product images, classifies by type, generates AI-animated clips via Higgsfield API, creates text overlays with style presets, and composes a 15-20 second reel with music" — naming the external service, output format, and duration. It is not the level below (4) because coverage of capabilities is comprehensive rather than having minor gaps.	5 / 5
Completeness	The "what" is clearly and comprehensively answered (scrape, classify, animate, overlay, compose), but there is no "Use when…" clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the "what" is specific and multi-action, not vague.	3 / 5
Trigger Term Quality	"Instagram-ready product reels" and "e-commerce product page URL" are natural phrases users would say, giving good keyword coverage. It is not 5 because common variations like "product video", "promo video", "ad", or "short-form video" are absent.	4 / 5
Distinctiveness Conflict Risk	"Instagram-ready product reels from any e-commerce product page URL" via the Higgsfield API is a clear niche with distinct triggers and minimal overlap risk with other skills. Neighboring anchors describe broader skills with overlap risk, which does not fit.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/design/packs/video-production/product-reel-generator/SKILL.md
Commit: cc3e518

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.