gooseworks-ai/goose-skills / skills/shared/brand-research
brand-research
VerifiedResearch a company or brand from its website and produce a reusable Brand Core covering products, audience, competitors, positioning, offers, messaging evidence, voice, and visual identity. Use before growth, ad, content, creator, or product work when reliable brand context is missing.
| File | Kind | Size |
|---|---|---|
| .env.example | other | 607 B |
| README.md | markdown | 2.7 KB |
| SKILL.md | skill md | 6.4 KB |
| examples/notion-calendar-with-ads.md | markdown | 1.1 KB |
| examples/oatly-oat-milk.md | markdown | 997 B |
| references/output-contract.md | markdown | 3.1 KB |
| requirements.txt | manifest | 249 B |
| scripts/fetch_asset.py | script | 2.5 KB |
| scripts/lib.py | script | 3.7 KB |
| scripts/register_asset.py | script | 1.2 KB |
| scripts/render_product_shot.py | script | 2.5 KB |
| scripts/scaffold_brand.py | script | 2.7 KB |
| scripts/verify_pack.py | script | 7.0 KB |
| skill.meta.json | config | 296 B |
examples/notion-calendar-with-ads.md
View on GitHub# Example kickoff — Notion Calendar, with existing-ad analysis + imagery
Paste into your agent:
```
Research Notion (product: Notion Calendar, https://notion.so/product/calendar)
with the brand-research skill into ./notion. I've dropped three of their ads in
./notion/existing-ads/ — analyze each. This product has notable UI, so also write
ui-references.md. Then generate 4 product stills and 6 lifestyle stills with the
optional image step (FAL_KEY is in .env).
Phases: disambiguate, scaffold, web research → fill all four brand-research files
+ asset-urls.md + ui-references.md, analyze each existing ad and fold the patterns
into concept-brief.md, source the logo + reference photos, run the image step for
the stills, register everything in brand-assets/manifest.json, then verify_pack.py.
```
Expected: the four research files + `ui-references.md`, a `concept-brief.md`
whose "Observed patterns" cites specific moments from each of the three ads, a
populated `brand-assets/` (logo, reference photos, 4 product + 6 lifestyle
generated stills) all registered in `manifest.json`, and a PASS from
`verify_pack.py`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |