competitor-discovery
Skill0 starsChanged 33 days agoMITView on GitHub
Find direct competitors, indirect alternatives and substitutes for a business or product using source-linked search and public company evidence. Use for competitor discovery, rival shortlists, product alternatives and competitor landscape research. Qualify audience and use-case fit before recommending a watchlist.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- kili-d/pmm-kittheir own version, first seen Jul 15, 2026
- anysiteio/agent-skillstheir own version, first seen Mar 28, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- anysiteio/agent-skills★ 20same name
- kili-d/pmm-kit★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Default to three relevant direct rivals, plus one useful substitute.
- Distinctive: line 18
Do not launch additional Actors merely to fill every field.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Competitor discovery
Produce a short, defensible competitor list with reasons for inclusion. Read existing approved rivals and exclusions first. Use supplied exports immediately; live collection follows the shared execution contract.
- Identify the buyer, problem, geography, language, product category and important constraints from the user's context. Mark uncertain inputs as assumptions; do not mistake a search-ranking overlap for a direct commercial competitor.
- Develop up to three distinct search queries: category plus audience, the target's alternatives, and the problem or substitute. Use the
scrape-google-serprecipe in actors.json, keeping query/page/result caps explicit. Inspect returned organic links and snippets with their query and date. Search ads are labelled separately. - For each candidate, verify public homepage and product evidence with
firecrawl-alternative. An optionalsimilarweb-alternativesample can suggest SEO rivals; those remain search competitors until buyer and use-case overlap is confirmed. - Classify each candidate as direct, indirect, substitute or aspirational. Retain brand aliases and canonical domain; do not collapse unrelated businesses with similar names. Store ambiguous entities as needing review.
- Default to three relevant direct rivals, plus one useful substitute. Exclude directories, publishers, resellers and affiliates unless the user's actual buying journey makes them relevant.
Return a table of competitor, canonical URL, relationship, audience/use-case fit, inclusion evidence, source date and confidence. Add excluded candidates with a brief reason when they could otherwise confuse the shortlist. Confidence is an explicitly explained research judgment, not a generated probability or demand score. Save the accepted list for subsequent skills; a proposed watchlist is not active monitoring.
Do not launch additional Actors merely to fill every field. If search is unavailable or empty, produce a provisional shortlist from the user's supplied evidence and explain the gap. A blocked provider does not mean the business has no competitors.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.