How do I install the Rote Onboard Rote Browse skill?

Run npx skillmds@latest add modiqo/rote-onboard-rote-browse in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Rote Onboard Rote Browse safe to use?

SkillMD's automated safety review verdict for this skill is WARNING. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Rote Onboard Rote Browse?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Rote Onboard Rote Browse free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Rote Onboard Rote Browse?

modiqo (@modiqo) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Rote Onboard Rote Browse by modiqo — Agent Skill

Name: Rote Onboard Rote Browse
Author: modiqo

Rote Onboard Rote Browse

Use for browser automation through rote, especially headed/headless exploration or attaching to logged-in Chrome/Edge sessions. Use for rote-browse, browse, Chrome, Edge, snapshot, Gmail, login and browser flow. Use for use rote browser primitives for browser automation, live attach, snapshots, waits, page slices, stale ref recovery, authenticated replay, private hub sharing, and Gmail safety. Requires `skillspec decide` before substrate tools or overlapping low-level skills. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports

modiqo Updated Sep 17, 2026

File contents

rote-browse

Use rote browser primitives for browser automation, live attach, snapshots, waits, page slices, stale ref recovery, authenticated replay, private hub sharing, and Gmail safety.

Use the directory that contains this loaded SKILL.md as <skill_dir>. The SkillSpec contract is <skill_dir>/skill.spec.yml; do not assume the user's current working directory contains the spec.

Start the SkillSpec guide with the user's task:

skillspec run-loop <skill_dir>/skill.spec.yml --input '<user task>' --trace-dir "${PWD}/.skillspec/traces" --guide agent

Resume an existing guided run:

skillspec run-loop <skill_dir>/skill.spec.yml --resume <run_dir> --guide agent

Follow the printed current gate. The selected route, matched rules, forbids, allowed commands, open requirements, resume command, and end proof from the CLI guide are authoritative.

Use skillspec query and skillspec refs only for handles named by the guide. Do not read the full spec unless the guide, a blocker, or the user asks for it.

Before the final response, follow the guide's end anchor: record final-response evidence, run the printed skillspec trace align ... --summary command as the completion summary source, and report result, evidence, alignment summary, token usage, selected route, and run directory.

If the skillspec CLI is not installed, report that this skill requires SkillSpec and ask the user to install it before continuing:

curl -fsSL https://raw.githubusercontent.com/modiqo/skillspec/main/install.sh | sh
# or, with Rust installed:
cargo install skillspec

If the user declines or installation is impossible, read <skill_dir>/skill.spec.yml directly and manually follow the same route, rule, phase, dependency, forbid, proof, and completion contract. Report that CLI guidance was unavailable and alignment proof is partial.

---name: rote-onboard-rote-browsedescription: Use for browser automation through rote, especially headed/headless exploration or attaching to logged-in Chrome/Edge sessions. Use for rote-browse, browse, Chrome, Edge, snapshot, Gmail, login and browser flow. Use for use rote browser primitives for browser automation, live attach, snapshots, waits, page slices, stale ref recovery, authenticated replay, private hub sharing, and Gmail safety. Requires `skillspec decide` before substrate tools or overlapping low-level skills. Preserves evidence with SkillSpec routes, forbids, dependencies, traces, and token-savings reports---# rote-browseUse rote browser primitives for browser automation, live attach, snapshots, waits, page slices, stale ref recovery, authenticated replay, private hub sharing, and Gmail safety.Use the directory that contains this loaded `SKILL.md` as `<skill_dir>`.The SkillSpec contract is `<skill_dir>/skill.spec.yml`; do not assume the user's current working directory contains the spec.Start the SkillSpec guide with the user's task:`skillspec run-loop <skill_dir>/skill.spec.yml --input '<user task>' --trace-dir "${PWD}/.skillspec/traces" --guide agent`Resume an existing guided run:`skillspec run-loop <skill_dir>/skill.spec.yml --resume <run_dir> --guide agent`Follow the printed current gate. The selected route, matched rules, forbids, allowed commands, open requirements, resume command, and end proof from the CLI guide are authoritative.Use `skillspec query` and `skillspec refs` only for handles named by the guide. Do not read the full spec unless the guide, a blocker, or the user asks for it.Before the final response, follow the guide's end anchor: record final-response evidence, run the printed `skillspec trace align ... --summary` command as the completion summary source, and report result, evidence, alignment summary, token usage, selected route, and run directory.If the `skillspec` CLI is not installed, report that this skill requires SkillSpec and ask the user to install it before continuing:```bashcurl -fsSL https://raw.githubusercontent.com/modiqo/skillspec/main/install.sh | sh# or, with Rust installed:cargo install skillspec```If the user declines or installation is impossible, read `<skill_dir>/skill.spec.yml` directly and manually follow the same route, rule, phase, dependency, forbid, proof, and completion contract. Report that CLI guidance was unavailable and alignment proof is partial.

Frequently asked questions