This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Lore
Claude Code Plugin for Product Documentation
Open-source Claude Code plugin that writes product documentation from Figma designs, PRDs or a live product. A read-only validator checks every page before delivery, and hooks block delivery when a source was claimed but never actually fetched.
I was using Claude Code to write product docs (scenarios, business rules, screenshots for PMs, designers and QA) and kept rebuilding the same rules, review checklist and folder conventions in every repo. Lore packages that process once as a Claude Code plugin: install it, and every repo gets the same skills, the same Definition of Done and the same guardrails.
• a brief or PRD (scenarios from acceptance criteria, plus a list of every state a designer still has to draw)
• the live product (a real browser via Playwright, exact UI text, and bug drafts for anything broken)
What I'm proudest of is unglamorous: Lore doesn't take the AI's word for it. A hook records every fetch, and a source the model claims to have read but never fetched blocks delivery. It's not tamper-proof, and I say so in the docs, but it does catch a skipped step instead of trusting a sentence that says "confirmed".
It's free and MIT-licensed, with docs in English and Persian (RTL is supported out of the box). I'd love to hear which input you'd try first and what's missing for your team. 🙌
About Lore on Product Hunt
“Claude Code Plugin for Product Documentation”
Lore was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #228 on the daily leaderboard. Open-source Claude Code plugin that writes product documentation from Figma designs, PRDs or a live product. A read-only validator checks every page before delivery, and hooks block delivery when a source was claimed but never actually fetched.
On the analytics side, Lore competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how Lore performed against the three products that launched closest to it on the same day.
Who hunted Lore?
Lore was hunted by Hamid Ostadhashemi. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Lore including community comment highlights and product details, visit the product overview.
Hamid Ostadhashemi
Hi Product Hunt! I'm Hamid, and I built Lore.
I was using Claude Code to write product docs (scenarios, business rules, screenshots for PMs, designers and QA) and kept rebuilding the same rules, review checklist and folder conventions in every repo. Lore packages that process once as a Claude Code plugin: install it, and every repo gets the same skills, the same Definition of Done and the same guardrails.
You start from what you have:
• a Figma file (comments, Dev-Mode annotations, prototype flows, frame screenshots)
• a brief or PRD (scenarios from acceptance criteria, plus a list of every state a designer still has to draw)
• the live product (a real browser via Playwright, exact UI text, and bug drafts for anything broken)
What I'm proudest of is unglamorous: Lore doesn't take the AI's word for it. A hook records every fetch, and a source the model claims to have read but never fetched blocks delivery. It's not tamper-proof, and I say so in the docs, but it does catch a skipped step instead of trusting a sentence that says "confirmed".
It's free and MIT-licensed, with docs in English and Persian (RTL is supported out of the box). I'd love to hear which input you'd try first and what's missing for your team. 🙌