fuse-browser-usage
starsforks
How to install fuse-browser-usage?
fusengine/agents/fuse-browser-usage
$npx -y skills add fusengine/agents --skill fuse-browser-usageEfficient fuse-browser usage: web fetch, crawl, SERP, browser session, screenshot, webapp testing, console errors. Read this BEFORE any mcp__fuse-browser__* tool call — it routes fetch/crawl/serp vs live session vs visual capture and enforces the 4 ZERO-TOLERANCE rules.
SKILL.md
| 1 | # fuse-browser — Efficient Usage |
| 2 | |
| 3 | Canonical doctrine for every `mcp__fuse-browser__*` call. Read this skill FIRST, then load the one reference matching your goal. Default engine is **patchright** (stealth identity auto-generated); the Chromium binary comes from `setup.sh`. |
| 4 | |
| 5 | ## 4 Rules (ZERO TOLERANCE) |
| 6 | |
| 7 | 1. **Fast-path FIRST (no browser launch, ~10× faster)** — `browser_fetch` / `browser_fetch_batch` / `browser_crawl` / `browser_serp_batch` to read a page, bulk-fetch, crawl a site, or scrape Google SERP. Open a live session ONLY when you need interaction, JS rendering, or pixels. |
| 8 | 2. **One session, always closed** — `browser_open` once → reuse the `sessionId` across `browser_navigate` calls → `browser_close` when done. Never leak sessions; the 2-min TTL is a safety net, not a substitute for closing. |
| 9 | 3. **Batch over loops** — `browser_serp_batch` (N queries), `browser_fetch_batch` / `browser_shots_batch` (N URLs), `browser_screenshot { viewports:[...], colorScheme }` (responsive + dark in ONE call). Never write a per-URL loop. |
| 10 | 4. **Deterministic extraction** — `browser_extract_schema` with `containerSelector` (card-by-card, correlated fields) over manual `browser_snapshot` parsing. |
| 11 | |
| 12 | ## Routing — pick the profile, load the reference |
| 13 | |
| 14 | | Goal | Profile | Reference | |
| 15 | |------|---------|-----------| |
| 16 | | Read docs, bulk-fetch, crawl, scrape SERP (no pixels) | Research / docs | `references/research-docs.md` | |
| 17 | | Test a running webapp (console, network, interactions) | Webapp testing | `references/webapp-testing.md` | |
| 18 | | Screenshots, responsive + dark, visual regression | Visual / design | `references/visual-design.md` | |
| 19 | |
| 20 | - **No live session for reading** — if you only need text/HTML/data, the answer is always fast-path (profile 1). Never `browser_open` to read. |
| 21 | - **Validation tools** (any profile): `browser_visual_diff` (regression vs baseline), `browser_metrics` (real Core Web Vitals), `browser_console` / `browser_network` / `browser_cookies` (runtime + security checks). |
| 22 | - **Full design pipeline** is NOT here — for identity → generate → audit, use `fuse-design:design-web` then the `fuse-design:design-review` gate. This skill only covers the raw browser tooling. |
People who liked this also viewed
6 picksType
- hyperframes-cliUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, SkillsJul 2026
- request-refactor-planSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- analyze-projectRigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrSkillsMay 2026
- explore-codeRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated braSkillsMay 2026
- ubiquitous-languageSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- scaffold-exercisesSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
