brand-research

Name: brand-research
Author: gooseworks-ai

1.0kstars193forks

How to install brand-research?

gooseworks-ai/goose-skills/brand-research

$npx -y skills add gooseworks-ai/goose-skills --skill brand-research

Installs into the current project.

Summary

Kickoff research for a brand you haven't worked on before — web research, existing-ad analysis from the Meta Ad Library, editorial-grammar profiling, sourced + AI-generated brand assets, hook/CTA libraries, and an ad concept brief. Produces one reusable brand-context pack (brand-

Files · 1

View on GitHub

SKILL.md

1	# brand-research
2
3	## Purpose
4
5	Given a brand (name and/or URL) and a product, produce the full creative-prep package for
6	it: research the product, analyze the brand's running ads, measure their editorial DNA,
7	source logos and reference photos, generate brand-anchored product + lifestyle imagery, and
8	write the brand-context documents a downstream ad/video pipeline consumes.
9
10	The output is a brand-context pack — a self-contained set of artifacts:
11
12	- `brand-summary`, `visual-identity`, `competitors`, `audience` — the core brand context.
13	- `existing-ads` — what the brand's running ads reveal that web research misses.
14	- `brand-grammar` — the brand's editorial DNA (archetype, pacing, caption style).
15	- an asset manifest cataloging every sourced + generated asset with its kind, name, and
16	usage note, plus the binary assets themselves (logos, reference photos, generated stills).
17	- a concept brief of brand-level ad concept seeds.
18
19	Everything is written into a single brand-pack directory under `output_dir`.
20
21	## Inputs
22
23	- `brand` (required) — the brand, used as the pack's folder name, e.g. `amex`, `liquid-death`.
24	- `product` (required) — the specific product / SKU / offer to research, e.g. "Platinum
25	Card", "Sparkling Water". Disambiguates brands with many SKUs.
26	- `brand_url` (optional) — canonical homepage. Strongly recommended to avoid wrong-entity
27	confusion (e.g. Apple band vs. Apple Inc.).
28	- `output_dir` (optional) — directory to write the brand pack into. Defaults to `./<brand>/`.
29	Resolve the location from this input; never hardcode a path.
30	- `max_existing_ads` (optional, default 10) — cap on how many of the brand's running Meta
31	ads to pull for analysis.
32	- `brand_video_urls` (optional) — the brand's own video URLs (launch films, demos). If
33	provided, run `build-brand-clip-library` afterward to cut them into a reusable clip library.
34	- `concept_count` (optional, default 6–10) — number of social-ad concepts to draft.
35	- `skip_generation` (optional, default false) — skip image generation and ship research +
36	brief only (useful when no image budget is available).
37
38	## Composed Atoms
39
40	- `source-company-existing-ads` — download the brand's running ads from the **Meta Ad
41	Library** (via the Apify FB Ad Library scraper) into a `raw/` folder with provenance.
42	- `rename-and-index-ads` — watch each downloaded ad, semantically rename it, and write an
43	`INDEX.md` (per-ad strategy + cross-ad patterns).
44	- `analyze-reference-grammar` — measure each ad's editorial DNA (cut points, pacing curve,
45	archetype, audio mode) into a per-ad `grammar-profile.json`.
46	- `source-brand-assets` — scrape logos + reference hero photos from the brand's site / press kit.
47	- `understand-brand-assets` — distill web research + reference photos into the visual-identity
48	content (colors, typography, photography style).
49	- `analyze-ad-hooks` — extract recurring hooks/motifs from the downloaded ads.
50	- `generate-ad-concepts` — produce the concept list for the concept brief.
51	- `create-product-images-higgsfield-product-photoshoot` — 4–6 hero/end-card product stills
52	(Higgsfield product-photoshoot on `gpt_image_2`).
53	- `create-product-images-nanobanana` — 8–12 vertical 9:16 lifestyle stills (Nano Banana Pro).
54	- External tools: a video-watching capability (frame extraction + transcription — e.g.
55	`yt-dlp` + `ffmpeg` + Whisper), and web search + fetch.
56
57	## Workflow
58
59	1. Disambiguate. Confirm `brand` + `product` resolves to one entity. If `brand_url` is
60	missing and the name is ambiguous, stop and ask.
61	2. Scaffold the brand pack under `<output_dir>` — a `brand-research/` folder for the
62	markdown docs, a `brand-assets/` folder for the asset manifest + binaries (`logos/`,
63	`reference-photos/`, `generated-product-shots/`, `generated-lifestyle/`, `songs/`), and an
64	`existing-ads/` folder (`raw/` + renamed copies + a `grammar/` subfolder). Only create
65	subfolders that will be populated.
66	3. Web research via web search + fetch. Priority order: brand site → trade press
67	(Adweek/AdAge/Campaign) → reputable category reviewers. Capture: product overview,
68	mechanics/pricing, benefits, target audience, current named campaigns with dates, core
69	positioning, voice/tone. Record every URL with its access date.
70	4. Pull and study the brand's running ads. Mandatory — research without watching real
71	ads misses how the product is actually shown and talked about.
72	- Run `source-company-existing-a

People who liked this also viewed

6 picks

Type

brand-research

1.0kstars193forks

View on GitHub

How to install brand-research?

gooseworks-ai/goose-skills/brand-research

$npx -y skills add gooseworks-ai/goose-skills --skill brand-research

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# brand-research
2
3	## Purpose
4
5	Given a brand (name and/or URL) and a product, produce the full creative-prep package for
6	it: research the product, analyze the brand's running ads, measure their editorial DNA,
7	source logos and reference photos, generate brand-anchored product + lifestyle imagery, and
8	write the brand-context documents a downstream ad/video pipeline consumes.
9
10	The output is a brand-context pack — a self-contained set of artifacts:
11
12	- `brand-summary`, `visual-identity`, `competitors`, `audience` — the core brand context.
13	- `existing-ads` — what the brand's running ads reveal that web research misses.
14	- `brand-grammar` — the brand's editorial DNA (archetype, pacing, caption style).
15	- an asset manifest cataloging every sourced + generated asset with its kind, name, and
16	usage note, plus the binary assets themselves (logos, reference photos, generated stills).
17	- a concept brief of brand-level ad concept seeds.
18
19	Everything is written into a single brand-pack directory under `output_dir`.
20
21	## Inputs
22
23	- `brand` (required) — the brand, used as the pack's folder name, e.g. `amex`, `liquid-death`.
24	- `product` (required) — the specific product / SKU / offer to research, e.g. "Platinum
25	Card", "Sparkling Water". Disambiguates brands with many SKUs.
26	- `brand_url` (optional) — canonical homepage. Strongly recommended to avoid wrong-entity
27	confusion (e.g. Apple band vs. Apple Inc.).
28	- `output_dir` (optional) — directory to write the brand pack into. Defaults to `./<brand>/`.
29	Resolve the location from this input; never hardcode a path.
30	- `max_existing_ads` (optional, default 10) — cap on how many of the brand's running Meta
31	ads to pull for analysis.
32	- `brand_video_urls` (optional) — the brand's own video URLs (launch films, demos). If
33	provided, run `build-brand-clip-library` afterward to cut them into a reusable clip library.
34	- `concept_count` (optional, default 6–10) — number of social-ad concepts to draft.
35	- `skip_generation` (optional, default false) — skip image generation and ship research +
36	brief only (useful when no image budget is available).
37
38	## Composed Atoms
39
40	- `source-company-existing-ads` — download the brand's running ads from the **Meta Ad
41	Library** (via the Apify FB Ad Library scraper) into a `raw/` folder with provenance.
42	- `rename-and-index-ads` — watch each downloaded ad, semantically rename it, and write an
43	`INDEX.md` (per-ad strategy + cross-ad patterns).
44	- `analyze-reference-grammar` — measure each ad's editorial DNA (cut points, pacing curve,
45	archetype, audio mode) into a per-ad `grammar-profile.json`.
46	- `source-brand-assets` — scrape logos + reference hero photos from the brand's site / press kit.
47	- `understand-brand-assets` — distill web research + reference photos into the visual-identity
48	content (colors, typography, photography style).
49	- `analyze-ad-hooks` — extract recurring hooks/motifs from the downloaded ads.
50	- `generate-ad-concepts` — produce the concept list for the concept brief.
51	- `create-product-images-higgsfield-product-photoshoot` — 4–6 hero/end-card product stills
52	(Higgsfield product-photoshoot on `gpt_image_2`).
53	- `create-product-images-nanobanana` — 8–12 vertical 9:16 lifestyle stills (Nano Banana Pro).
54	- External tools: a video-watching capability (frame extraction + transcription — e.g.
55	`yt-dlp` + `ffmpeg` + Whisper), and web search + fetch.
56
57	## Workflow
58
59	1. Disambiguate. Confirm `brand` + `product` resolves to one entity. If `brand_url` is
60	missing and the name is ambiguous, stop and ask.
61	2. Scaffold the brand pack under `<output_dir>` — a `brand-research/` folder for the
62	markdown docs, a `brand-assets/` folder for the asset manifest + binaries (`logos/`,
63	`reference-photos/`, `generated-product-shots/`, `generated-lifestyle/`, `songs/`), and an
64	`existing-ads/` folder (`raw/` + renamed copies + a `grammar/` subfolder). Only create
65	subfolders that will be populated.
66	3. Web research via web search + fetch. Priority order: brand site → trade press
67	(Adweek/AdAge/Campaign) → reputable category reviewers. Capture: product overview,
68	mechanics/pricing, benefits, target audience, current named campaigns with dates, core
69	positioning, voice/tone. Record every URL with its access date.
70	4. Pull and study the brand's running ads. Mandatory — research without watching real
71	ads misses how the product is actually shown and talked about.
72	- Run `source-company-existing-a

People who liked this also viewed

6 picks

Type