gooseworks-ai/goose-skills / skills/marketing/research-competitors
research-competitors
VerifiedCompetitor research: what every main rival is running, launching, charging and saying now, what works for them, and what that means for you. Use when the marketer asks for competitor research or a teardown, "what ads are my competitors running", "how do they price", "find gaps and angles", "what changed this week" (a weekly watch), or "X just launched / shut down / cut prices" (react now). Also builds a sales battlecard, checks a competitor page's tools/pixels, or studies who engages with their LinkedIn posts. Delivers a readable report saved to the brand, so the next run reports what changed. Never copies their words or disparages them. Not for what people say about you or your market — use research-market; not for who your buyers are — use research-audience.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.7 KB |
| references/angles-and-gaps.md | markdown | 7.4 KB |
| references/battlecard.md | markdown | 3.8 KB |
| references/focused-outputs.md | markdown | 2.7 KB |
| references/linkedin-engagers.md | markdown | 6.3 KB |
| references/page-technology.md | markdown | 2.7 KB |
| references/reading-ads-honestly.md | markdown | 8.6 KB |
| references/report-format.md | markdown | 10.0 KB |
| references/research-spec.md | markdown | 34.5 KB |
| references/rival-craft.md | markdown | 16.0 KB |
| references/run-memory.md | markdown | 6.6 KB |
| references/watch-and-react.md | markdown | 12.7 KB |
| skill.meta.json | config | 5.5 KB |
| tests/examples/2026-10-22/battlecard.md | markdown | 5.5 KB |
| tests/examples/2026-10-22/engagement-report.md | markdown | 3.7 KB |
| tests/examples/2026-10-22/engagers.csv | other | 1.7 KB |
| tests/examples/2026-10-22/excluded.csv | other | 1.0 KB |
| tests/examples/2026-10-22/technology.md | markdown | 3.2 KB |
| tests/fixtures/engagers.csv | other | 1.9 KB |
| tests/fixtures/focused-evidence.md | markdown | 3.8 KB |
| tests/fixtures/page-source.html | other | 614 B |
| tests/test-by-hand.md | markdown | 7.5 KB |
references/page-technology.md
View on GitHub# Human version
This checks what a competitor's public pages reveal about their tools and tracking tags. A tag in a page is evidence of that tag's presence, not evidence that it works or that the company spends on ads.
---
# Agent version
## Inspect the requested pages
1. Use the supplied URLs; if only a domain is supplied, inspect the homepage and one relevant pricing or campaign page. Record exact URL, redirects, read date, response/consent state and whether you read raw HTML, a rendered document or observed network requests. Reuse the rival record's messaging, CTA and customer evidence; the missing task here is technology evidence.
2. Read public HTML and, when the host supports it, the rendered page/scripts and requests. A cleaned-text fetch cannot inspect script tags: label technology **not checked** and name the missing source-reading capability. No login, consent bypass, form submission or paid vendor lookup. No shell requirement; a source-capable host fetch/browser is sufficient.
3. Record each detection with exact evidence and location: script/request hostname or path, signature in HTML, generator metadata, or a visible widget. Useful families: analytics (Google Analytics, PostHog, Mixpanel, Plausible), tag manager, ad tags (Meta, Google Ads, LinkedIn, TikTok, X), CRM/automation, chat, testing/recording, CMS/framework. Report other tools only when a signature supports them. A vague filename or product mention in article prose is not a detection. An HTML-commented or disabled historical script is possible historical configuration only, not an active loaded tag. A tag manager alone does not reveal the tags it might load.
4. Distinguish **detected** (specific observed signature), **possible** (ambiguous evidence, why), **not detected in this read** (the relevant source was inspected), and **not checked**. Source-read pages may omit deferred/consent-gated or server-side integrations. A blocked or uninspected page is never “no tools”. Do not output account/tag identifiers or secrets; retain only the signature needed to substantiate the tool.
## Output and check
Write the focused report with a brief summary and this table:
| Page | Tool/family | Status | Evidence and how read | Checked on | Limit / meaning for us |
|---|---|---|---|---|---|
Show page-level coverage, not an invented company-wide stack. Add the existing CTA/customer/message findings only if the ask requested them; do not repackage them as new discoveries. Recommendations must follow from the evidence: copying a tool is not a strategy. Inspect every supplied URL or name each unread one and its reason. Every detection must trace to the observed source, and missing signatures must retain the qualified wording above. Save/deliver through focused-outputs.md.
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 |