Find Alternatives
Skill35 starsChanged 4 days agoMITView on GitHub
Discover and vet replacement options for a product, tool, or site. 1. Capture the baseline: what the user has now, and WHY they want out (price, features, platform, privacy). The "why" drives selection. 2. search "<name> alternative" AND "<name> open source" (or the dimension that matters). Open 2–3 promising results with new_tab. 3. For each candidate verify on its own page: what it is, platform, pricing model, the killer differentiator, URL. Discard dead/megated projects. 4. Pick 3–5 finalists that genuinely…
In this repository11 other files it gives its agents.
- Compare PricesSkill
- Deep ResearchSkill
- Extract DataSkill
- Fill FormSkill
- Manage BookmarksSkill
- Monitor PageSkill
- Organize TabsSkill
- Read LaterSkill
- Save PageSkill
- Screenshot WalkthroughSkill
- Summarize PageSkill
The file
Files
Find Alternatives
Discover and vet replacement options for a product, tool, or site.
Procedure
- Capture the baseline: what the user has now, and WHY they want out (price, features, platform, privacy). The "why" drives selection.
search"<name>alternative" AND "<name>open source" (or the dimension that matters). Open 2–3 promising results withnew_tab.- For each candidate verify on its own page: what it is, platform, pricing model, the killer differentiator, URL. Discard dead/megated projects.
- Pick 3–5 finalists that genuinely differ from each other.
Tool discipline
- Aggregate lists (e.g. "top alternatives" articles) are LEADS, not answers — always confirm on the candidate's own site.
- Skip sponsors/ads in results; prefer independent mentions.
Answer format
1. <Name> — <one-line what> · <pricing> · why it fits: <reason> (<url>)
...
**Recommendation:** <one, matched to the user's stated reason>Mirror the list in data: { "alternatives": [...] }.
Verify before done
- Each alternative was confirmed on its own page (not just a listicle claim).
- Recommendation addresses the user's actual motivation.
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.

