unbrowse
Capture once, replay everywhere — Unbrowse turns websites into reusable API routes for agents. Resolve an intent + URL to a ranked endpoint shortlist, execute the chosen one for real data, or open a managed browser when capture is needed. Available as an MCP server, CLI, and SDK.
What this skill does
# Unbrowse
Unbrowse turns websites into reusable API routes for agents. Teach a route once, store sanitized metadata, replay it on later calls — typically 30× faster and 90× cheaper than a fresh browser session (peer-reviewed benchmark across 94 live domains: 3.6× mean speedup, 40× fewer tokens — [arXiv:2604.00694](https://arxiv.org/abs/2604.00694)).
This skill installs the instructions. The runtime (CLI binary + MCP server) comes from the `unbrowse` npm package — get it with `npx -y unbrowse`.
## Surfaces
| Surface | Reach for it when |
|---|---|
| **MCP server** | An MCP-host agent (Claude Code, Claude Desktop, Cursor, Codex, Windsurf). Tools like `unbrowse_resolve`, `unbrowse_execute`, `unbrowse_go` appear in the host. |
| **CLI** (`unbrowse`) | A shell or script that wants the same surface without an MCP host. |
| **SDK** (`unbrowse/sdk`) | A TypeScript program embedding Unbrowse; the SDK spawns its own local binary. |
## The workflow
Two tools, never one and never three:
- **resolve** — "is there an indexed route for this intent + URL?" Returns a ranked shortlist, or a hard handoff to a browser session.
- **execute** — pick one endpoint from the shortlist and run it. Returns the real data.
- **browse-session** — when the API is too dynamic to predict, open a managed browser; local capture indexes the route metadata for next time.
## Quickstart
Wire the MCP server into an MCP host:
```json
{
"mcpServers": {
"unbrowse": {
"command": "npx",
"args": ["-y", "unbrowse", "mcp"]
}
}
}
```
Then once:
```bash
npx unbrowse setup
```
From a shell:
```bash
unbrowse resolve --intent "search hacker news for openai" --url https://news.ycombinator.com
unbrowse execute --skill-id <id-from-resolve> --endpoint-id <id-from-shortlist>
```
From Node:
```bash
npm i unbrowse
```
```typescript
import { Unbrowse } from 'unbrowse/sdk';
const client = new Unbrowse({ apiKey: process.env.UNBROWSE_API_KEY });
const resolved = await client.resolve({ intent: 'search hn for openai', url: 'https://news.ycombinator.com' });
const result = await client.execute({ endpoint_id: resolved.available_operations![0].endpoint_id, params: { q: 'agents' } });
```
## Passive parallel indexing
While you browse, Unbrowse reverse-engineers the page's API traffic and indexes
it to publish — in the background, in parallel, so browsing stays fast. This is
**on by default**; each `sync` checkpoint returns immediately instead of blocking
on the page's network settle. Opt out per machine to index inline (slower
checkpoints, complete endpoints before each returns):
```bash
unbrowse settings --passive-index off # opt out; back on with: --passive-index on
```
Agents can toggle the same flag via the `unbrowse_settings` tool
(`passive_index: true|false`).
## Links
- npm: <https://www.npmjs.com/package/unbrowse>
- Docs: <https://www.unbrowse.ai>
- Source: <https://github.com/unbrowse-ai/unbrowse>
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.