setup
Verify the playwright plugin's runtime prerequisites: the playwright-cli binary and a resolvable browser for this machine. Use when: 'set up playwright', 'configure playwright', 'is playwright working', 'install playwright-cli', a browser flow reports the CLI is missing, or before a first E2E run. Actions: check (read-only verification, default) | apply (resolve what check found; apply install-cli performs the global CLI install). Re-runnable and safe.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 30
- Forks
- 7
01 前言 Front Matter
- shell
- bash
- description
- Verify the playwright plugin's runtime prerequisites: the playwright-cli binary and a resolvable browser for this machine. Use when: 'set up playwright', 'configure playwright', 'is playwright working', 'install playwright-cli', a browser flow reports the CLI is missing, or before a first E2E run. Actions: check (read-only verification, default) | apply (resolve what check found; apply install-cli performs the global CLI install). Re-runnable and safe.
- allowed-tools
- [ "Bash(command -v playwright-cli*)" ]
- argument-hint
- [check|apply] [install-cli]
- user-invocable
- true
- disable-model-invocation
- true
02 资源文件 1
- 参考文档evals/evals.json5.6 KB
03 SKILL.md 正文
Pre-computed context
check's playwright-cli probe ran at load time. Read this row instead of re-issuing it; it shows
the tool's path when present, or absent when missing:
playwright-cli: !command -v playwright-cli 2>/dev/null || echo absent
A row reading [shell command execution disabled by policy] carries no result: run that tool's
command -v probe via Bash instead.
- Pointer: for the placeholder a skipped load-time command leaves, fetch skills § Inject dynamic context live.
- As of: 2026-11-11
- Recheck trigger: the placeholder text changes.
Purpose
Thin check-centric setup per the uniform setup contract (docs/plugin-philosophy.md
"Setup is explicit and repeatable" in the marketplace repository): check inspects and
reports, apply resolves. This plugin owns no consumer-project configuration and no
userConfig. It recommends @playwright/cli's own defaults, so the only tunable
prerequisite is the CLI binary itself. apply is guidance-and-verify with exactly one
write path: the explicitly invoked apply install-cli global npm install described
below.
Action routing: no argument or check runs the check; apply runs the check first, then
offers the resolution for each finding; apply install-cli additionally authorizes the global
CLI install. All are non-interactive. Never prompt when the action is given.
check (read-only)
The main skill and its reference files are the single source of truth for what the CLI
requires: ${CLAUDE_PLUGIN_ROOT}/skills/playwright/SKILL.md (Prerequisite + quick start) and
${CLAUDE_PLUGIN_ROOT}/skills/playwright/reference/ (commands.md, windows-quirks.md).
Read it first. Probe what it actually does, don't recite this file. Then read the
pre-computed playwright-cli row, run the remaining probes via Bash, and report a PASS/FAIL/INFO
table with one remediation line per FAIL. Do not modify anything.
playwright-clibinary. The pre-computedplaywright-clirow (the binary name the skill drives; the npm package is@playwright/cli). FAIL if absent. Remediation isapply install-clibelow. When present, report the version (playwright-cli --version).- Browser availability. The CLI needs a browser beyond its own install. Per the plugin's
own
skills/playwright/reference/windows-quirks.md, local sessions on Windows/macOS/Linux auto-detect system Chrome, while a sandboxed/cloud session must runplaywright-cli install-browserand that download can be egress-blocked. INFO: state whether a system browser is resolvable on this host and, when it is not, surface theplaywright-cli install-browserstep and the sandbox-egress caveat from that reference. Do not assert a browser requirement the shipped docs do not; read them and report what they say. - Artifact directory. INFO: artifacts land in
.playwright-cli/relative to the working directory; note whether it is gitignored in the current project (the skill recommends adding it). No write. Reporting only.
apply (idempotent)
Run check, then for each FAIL offer the resolution. apply install-cli is the one write
path. State the change before running it:
- CLI absent.
apply install-clirunsnpm install -g @playwright/cli. This is a global install that mutates the user's machine (the global npm prefix), stated before it runs; without theinstall-cliargument,applyonly prints this command for the user to run. After the install, re-runcommand -v playwright-cliand report the actual result. Never claim success on npm's exit code alone. - browser not resolvable. Point at
playwright-cli install-browserper the plugin's reference, and note the sandbox-egress caveat when relevant. Guidance only. This skill does not provision browsers. .playwright-cli/not gitignored. Suggest adding it to the project.gitignore; guidance only, no edit.
The vendored-baseline update flow (/playwright:playwright update) is not this skill's
job. Point at it, do not wrap it. Re-running apply when everything already passes changes
nothing and reports "already configured".
What this skill does NOT do
- Write the plugin cache, Claude Code user settings, or
pluginConfigs. Nor project files. The one explicitly invokedapply install-cliglobal npm install is the only write it performs. - Provision browsers, run E2E flows, or take screenshots. That is
/playwright:playwright. - Run or wrap the maintainer update flow (
/playwright:playwright update).
04 同仓库更多 Skills
track
Backlog reads through the bound tracker: search open and closed items, view one item with its comments and state history. Use when another skill searches or reads tracker items.
reviewer-media
Reviewer media for one pull request: decides whether it needs a narrated walkthrough, builds the storyboard from /review:explain-change's digest, has /explainer-video:produce render it and hands the manifest to /source-control:pull-request media. Use when asked for 'reviewer media', 'a walkthrough video for this PR', 'a produced video of this change', or when pull-request ready or monitor hands a PR over.
route
Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value. Use when asked 'which model for the subagents', 'route the roles' or 'model routing', or before a skill passes a role's model on a spawn.
route
Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value. Use when asked 'which model for the subagents', 'route the roles' or 'model routing', or before a skill passes a role's model on a spawn.
principles
Module-design vocabulary for architecture findings, and the checks built on it. Use when: 'what is a deep module', 'what is a seam', 'deep vs shallow module', 'what is the deletion test', 'leverage and locality', 'module design vocabulary', 'which word do we use for X in architecture findings'. Scanning a codebase for friction is /architecture:improve.
write
Structured five-field bug report (title, steps to reproduce, expected vs actual, justified severity, suggested fix location) from an informal description, read-only. Use when the user names a defect they observed, or asks for one written up ('report a bug', 'file a bug', 'write this up as a bug').