Competitor research
Skill hamza-ali-shahjahan/hamzaish/factory/skills/competitor-research
Your Claude Code setup that builds, launches, and learns — across the whole product lifecycle. Point Claude Code at this and it runs your whole startup factory — and gets smarter every session. Works with Cursor, Codex & Windsurf too.
npx -y skills add hamza-ali-shahjahan/hamzaish --skill competitor-researchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Map a product's competitive landscape — direct + adjacent competitors, their positioning, naming conventions, and white-space. Persists findings to a per-product competitors file so it compounds over time. Use before naming, positioning, pricing, or GTM — and as the collision baseline for name-clearance.
SKILL.md
2.4 KB, as published. Nobody here has run it
competitor-research
When you activate
- Before naming a product (this is phase 1 of
name-product— it seeds themes and the collision baseline). - Before positioning, pricing, or GTM.
- Whenever the user asks "who else does this", "competitors", "landscape", "who are we up against".
What you produce
- A competitor table — direct + adjacent + incumbents.
- A naming-conventions read — what patterns the category uses (to fit or to break).
- The white-space — positioning angles nobody owns.
- A persisted file:
products/<slug>/competitors.md(create/update, dedupe) so the picture compounds across sessions.
Protocol
- Frame. One line: what the product does · its category · its ICP. (Pull from the product config / positioning brief if it exists.)
- Find, three rings (WebSearch, a few angles each):
- Direct — same job-to-be-done for the same user.
- Adjacent — overlapping capability or audience (these still cause name collisions).
- Incumbents — the big, generic players everyone compares against.
- For each competitor, capture: name · URL · one-line what-they-do · positioning angle · naming pattern (coined? descriptive? founder-name? compound? suffix?).
- Synthesize:
- Naming conventions in the space — and whether to conform (legibility) or contrast (distinctiveness).
- Positioning white-space — angles/wording nobody owns.
- The collision baseline — the exact names/roots a new name must avoid (hand this to
name-clearance).
- Persist. Write/merge
products/<slug>/competitors.mdwith a dated section. Dedupe against prior entries; note what's new.
Output format
Markdown: a competitor table, then three short lists — naming patterns, white-space, names/roots to avoid. Keep it scannable. Cite URLs.
Notes
- This is a living asset — each run appends and refines, so coverage improves over time.
- Run it before generating names: it both inspires themes and defines what must be cleared.