メニュー
Automate websites with the agent-browser CLI for navigation, form flows, screenshots, extraction, and repeatable browser tasks. Use when users ask to interact with web apps, gather evidence from pages, or run browser-based QA steps.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Update this junior-prod app to the latest published Junior release. Use when asked to self-update Junior, bump @sentry/junior and @sentry/junior-* dependencies, run safety checks, and open a draft PR.
Work with GitHub repositories, source code, branches, commits, pushes, pull requests, reviews, diffs, and CI runs. Use for repo implementation tasks, source-code investigation, cloning/fetching, branch and push workflows, PR creation, PR updates, PR review feedback, and GitHub Actions checks. Prefer this skill for repository and code tasks even when the repo concerns Sentry products.
Validate Junior changes through local app-facing paths. Use for local client or agent QA, dashboard mock reporting UI QA, PR readiness, plugin CLI commands, skill/tool/prompt/plugin behavior, and behavior that tests do not cover well but can be exercised with `pnpm cli -- chat ...`, `pnpm cli -- <command> ...`, or `JUNIOR_DASHBOARD_MOCK_CONVERSATIONS=true pnpm dev`.
Query read-only Amplitude product analytics. Use when users ask about active users, product usage, events, segmentation, funnels, conversion, retention, charts, dashboards, experiments, cohorts, taxonomy, session replay, feature flags, guides, surveys, feedback, agent analytics, or individual user activity in Amplitude. Do not use for changing Amplitude charts, dashboards, experiments, cohorts, flags, taxonomy, or project configuration.
Use for subscribed GitHub pull request events involving the local headless PR fixture repository.
Create, update, comment on, label, and inspect GitHub issues with concise, evidence-backed content. Use when users ask to open, edit, view, close, reopen, or triage GitHub issues — including tracking bugs, features, or tasks. Prefer this skill over generic repository tools for issue operations; do not use for pull requests, branches, pushes, or PR creation order questions.
| name | agent-browser |
| description | Automate websites with the agent-browser CLI for navigation, form flows, screenshots, extraction, and repeatable browser tasks. Use when users ask to interact with web apps, gather evidence from pages, or run browser-based QA steps. |
| allowed-tools | bash sendMessage |
Use this skill when work requires real browser interaction instead of API-only lookups.
agent-browser open <url>agent-browser snapshot -iagent-browser click @e1agent-browser fill @e2 "value"agent-browser snapshot -iagent-browser screenshot --annotate <file.png>agent-browser directly; do not use npx agent-browser.agent-browser --session <name> ...&& only when no intermediate output is needed.@e*), run snapshot -i first and use fresh refs.agent-browser wait --load networkidlesendMessage with the screenshot path in files so the image is included in the active conversation.sendMessage returned success in this turn.sendMessage is unavailable or file attachment fails, state the failure clearly and include the saved screenshot path or error instead of claiming success.agent-browser --session demo open https://example.com/signup
agent-browser --session demo wait --load networkidle
agent-browser --session demo snapshot -i
agent-browser --session demo fill @e1 "user@example.com"
agent-browser --session demo click @e2
agent-browser --session demo wait --load networkidle
agent-browser --session demo screenshot --annotate /tmp/signup-result.png
agent-browser open https://example.com
agent-browser snapshot --json > /tmp/page.json
agent-browser get text body > /tmp/page.txt
Read only what is needed: