菜单
Use when the task requires automating a real browser from the terminal through Playwright CLI: navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging, or local web app inspection via the bundled `.codex/skills/playwright/scripts/playwright_cli.sh` wrapper.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Analyze one DrowAI pentesting tool through repository-discovered mature references and its real registered, Kali-installed, official CLI, and LLM-visible paths before implementation. Use when evaluating a milestone tool, choosing proven in-repo wiring patterns such as Nmap for network-scanning responsibilities, proving the executable exists in the task Kali runtime, reconciling old definitions with current official documentation, or identifying the exact foundation work required before an implementation guide is created.
Deliver exactly one DrowAI pentesting tool selected from the Phase 01 milestone description on one Codex branch through repository-discovered mature wiring references, real-Kali installation proof, official CLI drift correction, reviewed implementation guide, phase-reviewed commits, safe Kali and GUI mechanics, branch-scoped quality work, push, and a milestone-attached pull request. Use when starting or continuing the milestone’s selected-tool backlog; a per-tool issue is optional and multiple tools must never share one branch or PR.
Mechanically validate one implemented DrowAI tool through its real Kali schema path and current web UI. Use after implementation review to verify parameters, execution/result states, deterministic compression, artifacts, knowledge, model/tool selection, and cleanup without judging prompt prose or answer quality.
Run DrowAI's repo-local state-driven feature implementation workflow from `.codex/agents/implementation-state.md`. Use when the user says implement, implement-this, continue implementation, run the implementation guide, advance to next task, go next, or wants the existing feature-implementer plus implementation-review-loop workflow to continue automatically until completion or a hard stop.
Run a state-driven review/fix loop for implementation-guide documents only (not code), using `.codex/agents/implementation-guide-state.md` and `.codex/agents/implementation-guide-review-state.md`. Use when the user asks to review an implementation guide, run blocker-only guide review, or loop reviewer/fixer until guide blockers are resolved.
Pure handoff router for DrowAI programs from `.codex/agents/program-workflow-state.md`. Discovers all numbered phase files under doc_root and runs the full create→guide-review→implement→final-implementation-review→quality-review cycle for every remaining item in one session until program_complete or hard_stop. Does not stop after one phase. Does not create, review, or implement itself.
| name | playwright |
| description | Use when the task requires automating a real browser from the terminal through Playwright CLI: navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging, or local web app inspection via the bundled `.codex/skills/playwright/scripts/playwright_cli.sh` wrapper. |
Drive a real browser from the terminal using playwright-cli. Prefer the bundled wrapper script so the CLI works even when it is not globally installed.
Treat this skill as CLI-first automation. Do not pivot to @playwright/test unless the user explicitly asks for test files.
Before proposing commands, check whether npx is available because the wrapper depends on it:
command -v npx >/dev/null 2>&1
If it is not available, pause and ask the user to install Node.js/npm, which provides npx. Provide these steps verbatim:
# Verify Node/npm are installed
node --version
npm --version
# If missing, install Node.js/npm, then:
npm install -g @playwright/cli@latest
playwright-cli --help
Once npx is present, proceed with the wrapper script. A global install of playwright-cli is optional.
From the project root, point to this skill's wrapper:
export PWCLI=".codex/skills/playwright/scripts/playwright_cli.sh"
If the skill is installed personally under ~/.codex/skills/playwright/:
export PWCLI="$HOME/.codex/skills/playwright/scripts/playwright_cli.sh"
On Windows, the wrapper playwright_cli.sh is a Bash script. Use either PowerShell with npx or run the script from Git Bash if available.
PowerShell prerequisite check:
npx --version
If npx is missing, install Node.js, then run the check again.
Option A - use npx directly:
function PWCLI { npx --yes --package @playwright/cli playwright-cli @args }
Then run:
PWCLI open https://playwright.dev --headed
PWCLI snapshot
PWCLI click e15
PWCLI type "Playwright"
PWCLI press Enter
PWCLI screenshot
Option B - wrapper via Git Bash:
export PWCLI=".codex/skills/playwright/scripts/playwright_cli.sh"
"$PWCLI" open https://playwright.dev --headed
"$PWCLI" snapshot
Use forward slashes in paths when setting them in Bash on Windows. First run will trigger npx to fetch @playwright/cli; install browsers once with npx playwright install if prompted.
Use the wrapper script:
"$PWCLI" open https://playwright.dev --headed
"$PWCLI" snapshot
"$PWCLI" click e15
"$PWCLI" type "Playwright"
"$PWCLI" press Enter
"$PWCLI" screenshot
If the user prefers a global install, this is also valid:
npm install -g @playwright/cli@latest
playwright-cli --help
Minimal loop:
"$PWCLI" open https://example.com
"$PWCLI" snapshot
"$PWCLI" click e3
"$PWCLI" snapshot
Snapshot again after:
Refs can go stale. When a command fails due to a missing ref, snapshot again.
"$PWCLI" open https://example.com/form
"$PWCLI" snapshot
"$PWCLI" fill e1 "user@example.com"
"$PWCLI" fill e2 "password123"
"$PWCLI" click e3
"$PWCLI" snapshot
"$PWCLI" open https://example.com --headed
"$PWCLI" tracing-start
# interactions...
"$PWCLI" tracing-stop
"$PWCLI" tab-new https://example.com
"$PWCLI" tab-list
"$PWCLI" tab-select 0
"$PWCLI" snapshot
The wrapper script uses npx --package @playwright/cli playwright-cli so the CLI can run without a global install:
"$PWCLI" --help
Prefer the wrapper unless the repository already standardizes on a global install.
Open only what you need:
references/cli.mdreferences/workflows.mde12.eval and run-code unless needed.eX and say why; do not bypass refs with run-code.--headed when a visual check will help.output/playwright/ and avoid introducing new top-level artifact folders.