Nansen Web Fetcher
- 410 installs
- 127 repo stars
- Updated August 4, 2026
- nansen-ai/nansen-cli
nansen-web-fetcher is an agent skill that fetches and normalizes web pages through the Nansen CLI using Gemini 2.5 Flash for developers who need to extract or summarize external HTML and JSON during crypto and market res
About
nansen-web-fetcher is an agent skill in nansen-ai/nansen-cli that runs `nansen web fetch` against one or more URLs and analyzes page content with Gemini 2.5 Flash URL context. The manifest requires the `nansen` CLI binary and a `NANSEN_API_KEY` environment variable, and allows Bash commands scoped to `nansen:*`. Developers reach for nansen-web-fetcher when they already have specific URLs—often from `nansen web search`—and need extracted facts, summaries, or answers rather than raw HTML. Example usage fetches a site and asks a targeted question such as what products a company offers. The skill normalizes external web content so agents can ingest it during crypto and market research tasks.
- CLI web fetch
- Agent data intake
- Page retrieval
- Nansen toolkit
- External source access
Nansen Web Fetcher by the numbers
- 410 all-time installs (skills.sh)
- +3 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #134 of 550 CLI & Terminal skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/nansen-ai/nansen-cli --skill nansen-web-fetcherAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 410 |
|---|---|
| repo stars | ★ 127 |
| Last updated | August 4, 2026 |
| Repository | nansen-ai/nansen-cli ↗ |
How do you summarize crypto web pages with Nansen CLI?
Fetch and normalize web pages from the Nansen CLI so agents can ingest external HTML and JSON during crypto and market research tasks.
Who is it for?
Developers doing crypto or market research who already have target URLs and need AI-extracted summaries through the Nansen CLI.
Skip if: Developers who need broad web discovery without URLs first, or research outside the Nansen CLI and API-key workflow.
When should I use this skill?
Specific URLs are available and the task requires fetching, extracting, or summarizing external web content for crypto or market analysis.
What you get
Normalized page summaries, extracted facts, and question-answered research notes from fetched URLs.
- URL content summaries
- Question-answered extraction notes
By the numbers
- Uses Gemini 2.5 Flash for URL content analysis
- Requires 1 API key env var: NANSEN_API_KEY
- Installs 1 CLI binary: nansen
Files
Web Fetch
Fetch and analyze content from one or more URLs using Gemini 2.5 Flash with URL context.
nansen web fetch https://nansen.ai --question "What products does Nansen offer?"
nansen web fetch --url https://example.com --url https://other.com --question "Compare these two sites"
nansen web fetch https://docs.uniswap.org/contracts/v4/overview --question "What changed in v4?"Positional args and --url flags can be combined — all become URLs to fetch.
| Flag | Values | Default | Purpose |
|---|---|---|---|
--url | URL | — | URL to fetch (repeatable for multiple URLs, up to 20) |
--question | string | required | Question to answer about the URL content |
--pretty | flag | off | Human-readable JSON |
Returns:
analysis— AI-generated answer to your questionretrieved_urls— URLs successfully fetchedfailed_urls— URLs that could not be retrieved
Tip: Combine with web search — search first to find relevant URLs, then fetch to get full content.
# Find and analyze in two steps
nansen web search "uniswap v4 launch" --num-results 3 --fields link
nansen web fetch https://blog.uniswap.org/... --question "What are the key changes?"Note: 30s timeout. Paywalled or bot-blocked pages may appear in failed_urls.
Related skills
Lark SharedWire Feishu/Lark Open Platform auth, tokens, and shared API helpers into agent-built bots and internal tools.514k
Runcomfy CliLet their coding agent call any RunComfy model from the terminal or scripts without managing separate SDKs.298k30
Skills CliDiscover, install, update, and manage reusable agent capabilities from the open Skillselion ecosystem directly inside their coding agent.270k71TzstCreate, extract, list, and script `.tzst` / `.tar.zst` archives from the terminal with the right compression, streaming, and conflict flags.267k71XdropPull files from an Xdrop share URL, decrypt them locally, and land outputs in a chosen directory with optional JSON for automation.266k71
WizardAuthor interactive bash setup wizards that open URLs, capture secrets, write .env upserts, and set GitHub Actions secrets step by step.104k202kFAQ
What credentials does nansen-web-fetcher need?
nansen-web-fetcher requires the `NANSEN_API_KEY` environment variable and the `nansen` CLI binary installed from the `nansen-cli` npm package. The skill metadata marks `NANSEN_API_KEY` as the primary environment dependency.
Which model analyzes fetched pages in nansen-web-fetcher?
nansen-web-fetcher uses Gemini 2.5 Flash with URL context to fetch and analyze content from one or more URLs. Developers pass a `--question` flag to extract targeted answers from the page.