landing-page
Explicit landing-page build and deploy operator. Loads marketing and frontend judgment, scaffolds the smallest suitable site, verifies it rendered, deploys to the configured target.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- landing-page
- kernel
- { "kind": "operator", "version": 2, "confirmation": "on_side_effect", "side_effects": "deploys" }
- description
- Explicit landing-page build and deploy operator. Loads marketing and frontend judgment, scaffolds the smallest suitable site, verifies it rendered, deploys to the configured target.
- allowed-tools
- Read, Write, Edit, Bash, Grep, Glob, Agent, WebSearch, WebFetch
- user-invocable
- true
- disable-model-invocation
- true
02 资源文件 1
- 参考文档agents/openai.yaml220 B
03 SKILL.md 正文
<skill id="landing-page">
<purpose> Build, verify, and optionally deploy a focused landing page. This is the explicit operator; strategy and aesthetics come from the methodology skills it composes. </purpose>
<skill_load>
Load skills/marketing-site/SKILL.md and skills/frontend/SKILL.md before writing.
</skill_load>
<inputs> Use answers already present in the request/repository. Resolve only what materially changes the build: audience, desired action, offer/proof, brand/assets, required content/legal pages, real CTA destination, domain, and deploy target. Never invent brand facts or proof.
For the unresolved inputs, run a structured interview with the AskUserQuestion tool (batched, up to 4 questions per round, recommended option first where evidence supports one) instead of guessing or asking loose prose questions. Bounded choices only; positioning and voice discussions stay prose. The interview method: skills/build/SKILL.md "The interview". </inputs>
<scaffold>
- Follow the existing repository and stack first. For a new simple page, prefer static HTML/CSS with JavaScript only for real behavior; add a framework only when requirements earn it.
- Build the content argument with
marketing-site; build the visual system withfrontend. - Add only the pages and integrations the brief needs. If forms, analytics, cookies, payments, embeds, or accounts touch data, create/update a privacy page that matches the real behavior.
- Keep secrets and deploy credentials out of source. </scaffold>
<verify-local>
- Render and do visual QA at 375 / 768 / 1440 widths unless the product defines better targets.
- Check hierarchy, realistic content, overflow, keyboard/focus, reduced motion, contrast, images, console errors, links, metadata, and CTA/form success plus error paths.
- Confirm the privacy policy matches actual collection and third parties.
- Run the repository's tests/build/lint and fix failures before deployment. </verify-local>
<deploy>
- Use the project's configured deploy command and provider. If none exists, choose the smallest provider-appropriate static deployment; Cloudflare Workers Static Assets is one option, not a universal default.
- If the user already named the deploy target and asked to deploy, that counts as confirmation. Otherwise surface the resolved account/project/domain before the side effect.
- After deploy, verify the live URL: status 200, headline/content marker, nested assets, legal page, and conversion path. Static assets can propagate briefly, so retry a short bounded check before diagnosing a successful deploy as broken. </deploy>
<hard-stops>
- No fabricated proof, shippable placeholders, fake form success, or dead CTA.
- No secrets in committed source.
- No “done” claim based only on source, build, commit, or deploy output; inspect the rendered page locally and the served page after deployment. </hard-stops>
<on_end> Report the live URL if deployed, target widths and paths checked, claims/proof source, privacy behavior, and any verification bar not observed. </on_end>
</skill>
04 同仓库更多 Skills
worktable-review-with-annotations
Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.
worktable-find-and-synthesize-context
Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.
worktable-create-or-update-docs
Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.
worktable-create-or-manage-records
Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.
worktable-create-or-manage-interactive-html
Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.
worktable-collaborate-threads
Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.