跳到正文
cccskills
免费在 GitHub 公开

marketing-site

Honest marketing-site method: audience, offer, proof, objections, privacy, art direction, handoff. Triggers: marketing site, landing page, company website, portfolio, campaign page, conversion, positioning, value proposition, CTA, social proof, privacy policy.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(3)

  • SKILL.md4.8 KB
  • agents/openai.yaml202 B
  • references/client-delivery.md1.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

<skill id="marketing-site"> <purpose> Turn a product or service into a focused, credible website. The page should help a specific person understand the offer, trust it, and take the next useful action—without marketing theater or a generic template wearing different nouns. </purpose>

<skill_load>skills/frontend/SKILL.md</skill_load>

<inputs> Recover what the user and repository already supplied before asking questions:
  1. Audience: who arrives, what they know, and what situation brought them here.
  2. Desired action: install, buy, book, join, contact, learn, or compare.
  3. Offer: what changes for the visitor, how it works, and why this option is different.
  4. Friction: objections, risks, missing information, switching cost, and alternatives.
  5. Proof: product behavior, demo, screenshots, founder expertise, customer evidence, data.
  6. Brand and constraints: voice, assets, references, legal/privacy needs, stack, deadline.

Do not force an interview when the brief answers these. Ask only for a missing choice that would materially change the page; otherwise make a reversible assumption and label it. </inputs>

<truth-rules> Never invent customers, testimonials, metrics, guarantees, awards, integrations, press logos, scarcity, fake urgency, or “trusted by” claims. Placeholder proof must be visibly marked as a placeholder and cannot ship. Describe capabilities at the strength the evidence supports. Specific and modest beats impressive and false. </truth-rules> <strategy> Write a one-sentence positioning statement: “For [audience in situation], [offer] helps [outcome] by [mechanism/difference].”

Then choose a page argument that fits the buying decision. A useful default is: problem or desire → promise → mechanism → proof → objections → action. It is a diagnostic spine, not a mandatory section order. A familiar plugin may need one sharp idea and a demo; an expensive service may need process, proof, risk reduction, and detail.

Give each section one job. Prefer one primary CTA; secondary actions are allowed when they serve a genuinely different visitor state. CTA copy should name the next step, not “Submit.” </strategy>

<copy> - Lead with the visitor's outcome or tension, then make the mechanism concrete. - Use the user's language and real nouns. Delete adjectives that the page cannot prove. - Keep the headline, subhead, visual, and CTA mutually reinforcing. - Answer the strongest objection near the claim that creates it. - Let product screenshots, examples, demos, and specifics carry more weight than slogans. - Match detail to consequence: higher price/risk needs more explanation and reassurance. </copy> <art-direction> Use `skills/frontend/SKILL.md`. Derive the visual direction from audience, brand, offer, content, and references. A provocative page earns its tension through the idea; it does not need random visual aggression. Preserve an existing design system when present. </art-direction> <privacy-and-trust> The privacy page must describe the actual implementation: what data is collected, why, where it goes, retention/deletion, cookies or analytics, form/email providers, user choices, contact, and effective date. If the site collects nothing, say so plainly and still disclose hosting logs or third parties that may receive technical data. Do not copy a broad boilerplate policy that claims tools the site does not use. Flag jurisdiction-specific legal review when stakes require it; do not present generated copy as legal advice. </privacy-and-trust> <client-delivery> For client work, confirm who approves copy/design, who owns supplied assets, the domain and accounts, analytics/consent choices, editable-source handoff, launch/rollback plan, and who maintains the site. Keep credentials in the client's account or secure environment—not source. Read `skills/marketing-site/references/client-delivery.md` for the compact handoff checklist. </client-delivery> <verification> Check the rendered page at target widths and follow every conversion path. Verify all claims against supplied evidence, every CTA and legal link, keyboard/focus behavior, performance, metadata/share preview, form success/error states, and the deployed privacy behavior. </verification> <output> State the audience, desired action, positioning, page argument, proof used, art direction, assumptions/placeholders, privacy reality, and what was actually verified. </output> </skill>

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use AtomLane to compile and execute safe atomic parallel plans on macOS and native Windows Preview for worthwhile independent argv tasks, dependency DAGs, supported platform entrypoints, or Apple-silicon operators. Use at task start or an execution boundary when structured local work may contain two or more worthwhile units; skip plain answers, one quick command, and work whose effects cannot be safely bounded.

中文简介正在准备中。当前显示原文说明。

hashgraph-online/awesome-codex-plugins13812026年10月22日 更新

add

免费

Register a deferred decision in the debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you defer work, or when the user invokes $add. Over-register freely; the developer drops with "drop A", "drop A,C", or "drop all".

中文简介正在准备中。当前显示原文说明。

hashgraph-online/awesome-codex-plugins13812026年10月22日 更新

ADK 框架适配层。为 LangChain / EINO / AutoGen / AgentScope / CrewAI 提供框架特定的 代码模板、惯用模式、API 映射和项目结构,供 agent-dev-workshop Phase 5 代码生成使用。 每个框架 reference 文件标注 verified_date 用于版本锁定。

中文简介正在准备中。当前显示原文说明。

hashgraph-online/awesome-codex-plugins13812026年10月22日 更新

中文调试修复技能。用于报错、测试失败、页面异常、功能不符合预期、需要定位根因并做最小修复时。触发语包括"进入调试模式""帮我修问题""报错了""测试失败""页面坏了""找根因"。

中文简介正在准备中。当前显示原文说明。

hashgraph-online/awesome-codex-plugins13812026年10月22日 更新

交互式 AI Agent 开发工作坊:通过 6 阶段深度协作对话,引导用户完成 Agent 需求分析、架构设计、 工具定义、Prompt 与编排设计、代码生成、验证迭代,产出可直接运行的 Agent 项目。 框架无关设计优先,支持 LangChain / EINO / AutoGen / AgentScope / CrewAI 等 ADK 框架。

中文简介正在准备中。当前显示原文说明。

hashgraph-online/awesome-codex-plugins13812026年10月22日 更新

中文漂移审计技能。用于项目或学习过程变乱、上下文漂移、任务分叉、多个方案冲突、命名不一致、Codex 可能顺手改多了时。触发语包括"漂移检查""感觉跑偏了""项目变乱了""检查是否失控""分叉太多""上下文漂移"。

中文简介正在准备中。当前显示原文说明。

hashgraph-online/awesome-codex-plugins13812026年10月22日 更新

查看 hashgraph-online 的全部技能

报告此技能的问题