Menu

Individual skill

research-competitors-category-pass

0upvotes

Step of the research-competitors playbook: the worker brief covering the whole category, including searches, AI answers, community threads and category ad winners. Run research-competitors instead; not for direct use.

skills/marketing/research-competitors-category-pass/SKILL.md

Read pinned source

Source commit df8298140d434a6363de0c265eb6af2e571d97a5

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,314
Repository last updated
Nov 6, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# category-pass

You cover what no single rival pass sees: how buyers search and choose in this category, and where our brand stands. Do every section; never stop to ask whether to go deeper. Same rules as the `research-competitors-rival-pass` skill (`../research-competitors-rival-pass/SKILL.md`): don't load any skill or start subagents; about 12 searches and 10 fetches in a standard run; public pages only; every fact with its link and date inline; how sure in words; "Needs the browser" and "Couldn't read" lists. The main run has already done the field searches and chosen the rivals — you go deeper on the category: sections 3–7 (and 1–2 only to add what it missed).

**Inputs:** our brand, what it sells, its category in buyers' words, the rival list, company type, today's date.

## 1. Money searches

Search, in a clean browser or web search where possible: `best <category>` · `<category> software / tool / app` · `<rival> alternative` (each main rival) · `<rival> vs <rival>` · `<our brand> vs <rival>` · `<our brand> reviews` · our brand name alone. Record who ranks in the top results, who runs search ads on each query (including on our brand name — a rival bidding on us is a threat), and which "vs" and "alternatives" pages exist and who wrote them. Results vary by location; say where you searched from.

## 2. AI-answer presence

Ask the same prompts each time — `best <category> tool`, `alternatives to <main rival>`, `<our brand> vs <main rival>`, `what is <our brand>` — in every AI answer engine the host can reach (Google's AI Overview in search results counts; others as available). Record who is named, in what order, and how our brand is described, with the date. Where none can be reached, say so, and read improve-search-visibility's latest `search/visibility/<date>.md` if it exists.
Back to top