菜单
[BETA] Start the dev server, open the feature in a browser, and iterate on improvements together.
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。
基于 SOC 职业分类
Create structured plans for multi-step tasks -- software features, research workflows, events, study plans, or any goal that benefits from breakdown. Also deepens existing plans with interactive sub-agent review. Use when the user says 'plan this', 'create a plan', 'how should we build', 'break this down', or when a brainstorm doc is ready for planning. Use 'deepen the plan' or 'deepening pass' for the deepening flow. For exploratory requests, prefer lets-brainstorm first.
Document how an application works — its architecture, functionality, and business processes — as durable in-repo reference for teammates and contributors. Use when asked to 'document the architecture', 'write docs for this subsystem', 'explain how X works for the team', 'document our order/billing/auth process', or to produce onboarding docs people can read to understand the codebase. Name a topic for one focused doc, or omit one for a whole-app survey. Documents the system as it currently stands — not a change (lets-explain) or a solved problem (lets-compound).
Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.
Explain a change you didn't write — produce an orientation-first, teaching-depth walkthrough of a diff, PR, or commit range. Use when asked to 'explain this PR', 'walk me through this change', 'help me understand this diff', 'what does this change do', when getting oriented before reviewing, or when learning how a change works. Explains, does not critique.
Generate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting the AI to proactively suggest strong options before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on X', 'surprise me', 'what would you change', or any request for AI-generated suggestions rather than refining the user's own idea.
Explore requirements and approaches through collaborative dialogue, then write a right-sized requirements document. Use when the user says "let's brainstorm", "what should we build", or "help me think through X", presents a vague or ambitious feature request, or seems unsure about scope or direction -- even without explicitly asking to brainstorm.
| name | lets-polish-beta |
| description | [BETA] Start the dev server, open the feature in a browser, and iterate on improvements together. |
| disable-model-invocation | true |
| argument-hint | [PR number, branch name, or blank for current branch] |
Start the dev server, open the feature in a browser, and iterate. You use the feature, say what feels off, and fixes happen.
.claude/launch.jsonRun bash scripts/read-launch-json.sh. If it finds a configuration, use it — the user already told us how to start the project.
Run bash scripts/detect-project-type.sh to identify the framework.
Route by type to the matching recipe reference for start command and port defaults:
| Type | Recipe |
|---|---|
rails | references/dev-server-rails.md |
next | references/dev-server-next.md |
vite | references/dev-server-vite.md |
nuxt | references/dev-server-nuxt.md |
astro | references/dev-server-astro.md |
remix | references/dev-server-remix.md |
sveltekit | references/dev-server-sveltekit.md |
procfile | references/dev-server-procfile.md |
unknown | Ask the user how to start the project |
For framework types that need a package manager, run bash scripts/resolve-package-manager.sh and substitute the result into the start command.
Resolve the port with bash scripts/resolve-port.sh --type <type>.
Start the dev server in the background, log output to a temp file. Probe http://localhost:<port> for up to 30 seconds. If it doesn't come up, show the last 20 lines of the log and ask the user what to do.
Load references/ide-detection.md for the env-var probe table. Open the browser using the IDE's mechanism (Claude Code → open, Cursor → Cursor browser, VS Code → Simple Browser).
Tell the user:
Dev server running on http://localhost:<port>
Browse the feature and tell me what could be better.
This is the core loop. The user browses the feature and tells you what to improve. You fix it. Repeat until they're happy.
agent-browser to screenshot or inspect the pageNo checklist. No envelope. Just conversation.
Reference files (loaded on demand):
references/launch-json-schema.md — launch.json schema + per-framework stubsreferences/ide-detection.md — host IDE detection and browser-handoffreferences/dev-server-detection.md — port resolution documentationreferences/dev-server-rails.md — Rails dev-server defaultsreferences/dev-server-next.md — Next.js dev-server defaultsreferences/dev-server-vite.md — Vite dev-server defaultsreferences/dev-server-nuxt.md — Nuxt dev-server defaultsreferences/dev-server-astro.md — Astro dev-server defaultsreferences/dev-server-remix.md — Remix dev-server defaultsreferences/dev-server-sveltekit.md — SvelteKit dev-server defaultsreferences/dev-server-procfile.md — Procfile-based dev-server defaultsScripts (invoked via bash scripts/<name>):
scripts/read-launch-json.sh — launch.json readerscripts/detect-project-type.sh — project-type classifierscripts/resolve-package-manager.sh — lockfile-based package-manager resolverscripts/resolve-port.sh — port resolution cascade