メニュー
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating browser actions.
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
Reviews and removes unsupported, non-idiomatic code and UI/design changes introduced on a branch. Use when implementing or reviewing a feature or fix before handoff.
Design principles for REST and GraphQL APIs in 2025. Enforces OpenAPI-first, versioning strategies, and standardized error responses.
Use the `fm` CLI (Apple Foundation Models) for on-device and Private Cloud Compute LLM inference on macOS. Use when the user wants to prompt, chat, serve, or count tokens with Apple's built-in foundation models. Also use for structured output generation (`fm schema`), checking model availability (`fm available`), or checking quota usage (`fm quota-usage`). Trigger on phrases like 'run fm', 'Apple Foundation Model', 'on-device LLM', 'Apple AI', 'fm respond', 'fm chat', 'fm serve', 'fm token-count', 'fm schema', or any task involving Apple's local AI models.
This skill should be used when the user asks to "trigger a build", "check build status", "watch a build", "view build logs", "retry a build", "cancel a build", "list builds", "download artifacts", "upload artifacts", "manage secrets", "create a pipeline", "list pipelines", or "interact with Buildkite from the command line". Also use when the user mentions bk commands, bk build, bk job, bk pipeline, bk secret, bk artifact, bk cluster, bk package, bk auth, bk configure, bk use, bk init, bk api, or asks about Buildkite CLI installation, terminal-based Buildkite workflows, or command-line CI/CD operations.
Buildkite CI/CD pipeline setup, migration, validation, hardening, and live pipeline management. Use when Codex needs to create, review, debug, or update Buildkite pipelines, .buildkite/pipeline.yml files, steps, queues, triggers, artifacts, annotations, secrets, OIDC, or deployment stages.
This skill should be used when the user asks to "write a pipeline", "add caching", "make this build faster", "show test failures in the build page", "add annotations", "only run tests when code changes", "set up dynamic pipelines", "add retry", "parallel steps", "matrix build", "add plugins", or "work with artifacts in pipeline YAML". Also use when the user mentions .buildkite/ directory, pipeline.yml, buildkite-agent pipeline upload, step types (command, wait, block, trigger, group, input), if_changed, notify, concurrency, or asks about Buildkite CI configuration.
| name | agent-browser |
| description | Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating browser actions. |
| allowed-tools | Bash(agent-browser:*) |
Before starting a session, verify the tool is installed and check whether a reusable session already exists.
agent-browser --version
agent-browser session list
Every browser automation follows this pattern:
agent-browser open <url>agent-browser snapshot -i@e1# Navigation
agent-browser open <url>
agent-browser back
agent-browser forward
agent-browser reload
agent-browser close
# Snapshot
agent-browser snapshot -i
agent-browser snapshot -i -C
agent-browser snapshot -s "#selector"
# Interaction
agent-browser click @e1
agent-browser fill @e2 "text"
agent-browser type @e2 "text"
agent-browser select @e1 "option"
agent-browser check @e1
agent-browser press Enter
agent-browser scroll down 500
# Get information
agent-browser get text @e1
agent-browser get value @e1
agent-browser get url
agent-browser get title
# Wait
agent-browser wait @e1
agent-browser wait --load networkidle
agent-browser wait --url "**/page"
agent-browser wait 2000
# Capture
agent-browser screenshot
agent-browser screenshot --full
agent-browser pdf output.pdf
# Debugging
agent-browser console
agent-browser errors
Use --json when you need machine-readable output from snapshots or getters.
agent-browser open https://example.com/signup
agent-browser snapshot -i
agent-browser fill @e1 "Jane Doe"
agent-browser fill @e2 "jane@example.com"
agent-browser select @e3 "California"
agent-browser check @e4
agent-browser click @e5
agent-browser wait --load networkidle
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "$USERNAME"
agent-browser fill @e2 "$PASSWORD"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
agent-browser state save auth.json
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard
agent-browser open https://example.com/products
agent-browser snapshot -i
agent-browser get text @e5
agent-browser get text body > page.txt
agent-browser snapshot -i --json
agent-browser get text @e1 --json
agent-browser --session site1 open https://site-a.com
agent-browser --session site2 open https://site-b.com
agent-browser --session site1 snapshot -i
agent-browser --session site2 snapshot -i
agent-browser session list
agent-browser --headed open https://example.com
agent-browser highlight @e1
agent-browser record start demo.webm
agent-browser --allow-file-access open file:///path/to/document.pdf
agent-browser --allow-file-access open file:///path/to/page.html
agent-browser screenshot output.png
agent-browser device list
agent-browser -p ios --device "iPhone 16 Pro" open https://example.com
agent-browser -p ios snapshot -i
agent-browser -p ios tap @e1
agent-browser -p ios fill @e2 "text"
agent-browser -p ios swipe up
agent-browser -p ios screenshot mobile.png
agent-browser -p ios close
Requirements: macOS with Xcode, Appium (npm install -g appium && appium driver install xcuitest).
Refs are invalid after navigation, reloads, form submissions, and major DOM changes. Re-snapshot before the next targeted interaction.
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser find role button click --name "Submit"
agent-browser find placeholder "Search" type "query"
agent-browser find testid "submit-btn" click