Add SkimReaderTool: x402-native pay-per-call web reader
Open
Nobody has claimed this yet.
vendor-pitch
- Dominant language
- Python
- Stars
- 58.8k
- Forks
- 8.5k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 109
Description
Feature request
Add a new tool, `SkimReaderTool`, to `crewai-tools`.
**What it does:** given any URL, it returns clean, agent-ready Markdown (nav/ads/boilerplate stripped) plus structured metadata (title, byline, published date, language, excerpt).
**Why it's a good fit:** crewAI already ships several scraping/reader tools (e.g. `FirecrawlScrapeWebsiteTool`), but none are pay-per-call over an open payment rail. `SkimReaderTool` is built on the [x402](https://x402.org) protocol — each read costs $0.002 in USDC on Base, paid automatically by a wallet the user controls. No signup, no API keys; the wallet is the identity, and the private key never leaves the user's machine.
A working implementation already exists and is ready for review: #6264 (previously closed only because it predated the first-time-contributor issue-link requirement — reopening now to reference this issue).
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the existing implementation in pull request #6264 and compare it with FirecrawlScrapeWebsiteTool. Confirm that SkimReaderTool accepts a URL, returns cleaned Markdown and the listed metadata, and handles x402 payment on Base as described; done means the implementation is ready for review without duplicating the existing work.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api, backend, blockchain
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100