pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element…
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser
$ npx -y skills add pinchtab/pinchtab --skill pinchtab --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/pinchtabContext preview
The summary Claude sees to decide when to auto-load this skill.
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser
name: pinchtab
description: "Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API when the CLI is unavailable. Prefer this skill for token-efficient browser work driven by stable accessibility refs such as `e5` and `e12`."
metadata:
openclaw:
requires:
bins:
- pinchtab
anyBins:
- google-chrome
- google-chrome-stable
- chromium
- chromium-browser
homepage: https://github.com/pinchtab/pinchtab
install:
- kind: brew
formula: pinchtab/tap/pinchtab
bins: [pinchtab]
- kind: npm
package: pinchtab
bins: [pinchtab]CLI-first browser skill. Use `pinchtab` commands.
1. Create a session: `export PINCHTAB_SESSION=$(pinchtab session create --agent-id myagent)` — do this once before any browser command. 2. Navigate: `pinchtab nav <url> --snap` — auto-starts the local server if needed, then returns tab ID + interactive snapshot in one call. 3. Interact: `pinchtab click <ref> --snap-diff` — returns OK + only changed elements (most token-efficient).
4. For read-only observation: `pinchtab text` when you won't act on refs.
**Key optimization**: Use `--snap-diff` on `nav`, `click`, `fill`, `select`, `press`, `scroll`, `back`, `forward`, `reload` to get only added/changed/removed elements — most token-efficient for multi-step flows. Use `--snap` when you need the full snapshot (e.g., first navigation, or after major page changes). `--text` is available on `nav`, `click`, `fill`, `select`, `press`, `back`, `forward`, `reload` (but NOT on `scroll`) when you need prose content for verification (skips snap, returns page text directly). `dblclick` does not support any observation flag — run a separate `snap` after.
`--snap-diff` returns the same compact format as `snap`, but with change markers and a header showing counts:
# Page Title | URL | 57 nodes | +2 ~1 -0 e0:link "Home" e5:button "Submit" [+] e12:textbox val="updated" [~] # removed: e99
`[+]` = added, `[~]` = changed, removed refs listed at end. All valid refs are shown — no need to remember previous snapshot. Do not follow with redundant `snap`; only call `text` when you need prose content.
Fallback observation (when `--snap` wasn't used):
Rules: only `nav <url>` and `session create` auto-start the default local server; `snap`, `text`, `html`, `find`, and action commands operate on an already-running server/current tab. Explicit `--server` / `PINCHTAB_SERVER` targets are never auto-started. Never act on stale refs; screenshots only for visual/debug; choose the instance/profile up front for parallel or multi-site work.
For the handling rules for page code, files, cookies/state, network data, and artifacts, read [safety.md](./references/safety.md).
Unified selectors accepted by any element-targeting command:
Auto-detection: bare `eN`→ref, `#`/`.`/`[...]`→CSS, `//`→XPath. Use explicit `css:`/`xpath:`/`text:`/`find:` prefixes when ambiguous. HTTP API uses the same syntax in the `selector` field (legacy `ref` still accepted).
`&&` when you don't need intermediate output (`pinchtab nav <url> --snap && pinchtab click e3 --snap-diff`). Run separately when you must read refs before acting.
If a site requires a CAPTCHA, anti-bot challenge, or other human verification, stop and ask the user to complete it. Do not attempt to defeat, evade, or automate the protection.
Patterns: (1) one-off `pinchtab instance start`; (2) reuse a profile with `instance start --profile work`; (3) HTTP `POST /profiles` then `POST /profiles/<name>/start`. The `--profile` pattern requires the profile to exist first. Human setup: `pinchtab profiles create work`, authenticate headed; agents reuse headless. Agent sessions: `pinchtab session create --agent-id <id>` or `POST /sessions` → set `PINCHTAB_SESSION=ses_...`.
**Session reuse safety:** When reusing auth
High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element…
Develop and contribute to the PinchTab project. Use when working on PinchTab source code, adding features, fixing bugs, running tests, or preparing PRs.…
Run the PinchTab optimization loop (Docker, 3 blind subagents on the runner's HIGH model, 108 steps across 47 groups) against chrome, cloak, ghost-chrome, or…
Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan,…