← 返回 Skills 市场
xammarie

landing-page-roast

作者 xammarie · GitHub ↗ · v1.0.1
cross-platform ✓ 安全检测通过
1311
总下载
1
收藏
3
当前安装
1
版本数
在 OpenClaw 中安装
/install landing-page-roast
功能描述
Audit a landing page for clarity, trust, offer strength, and conversion friction; return prioritized fixes and copy rewrites.
使用说明 (SKILL.md)

Landing Page Roast

Use this skill to diagnose why a page is not converting and produce concrete fixes.

Inputs

  • Page URL or pasted page copy
  • Target audience
  • Primary conversion action
  • Price point / offer details

Audit dimensions

  1. Clarity above the fold
    • Is the outcome obvious in 5 seconds?
  2. Audience fit
    • Is it clear who this is for (and not for)?
  3. Offer strength
    • Is the promise specific, measurable, believable?
  4. Trust layer
    • social proof, proof artifacts, risk reversal
  5. Friction
    • too many fields, weak CTA hierarchy, distractions
  6. Objection handling
    • price/time/risk doubts addressed?

Output

  • Overall score (0–10)
  • Top 5 blockers (ranked by impact)
  • Quick wins (\x3C30 min changes)
  • Structural rewrites (headline, subhead, CTA block)
  • 3 CTA variants
  • Optional A/B test matrix (what to test first)

Rewrite standards

  • Plain language
  • Specific outcomes over buzzwords
  • Fewer claims, more proof
  • Keep tone consistent with target audience

Example request

"Roast this AI automation service page for SMB owners and rewrite the hero + first CTA section to increase booked calls."

安全使用建议
This skill appears coherent and low-risk: it only needs a page URL or pasted copy and returns audit suggestions. Before using it, avoid pasting sensitive information (API keys, private customer data, auth tokens) into the input. If you provide a URL, confirm whether your agent will fetch the page directly (and whether it will send cookies or authenticated requests); prefer public pages or sanitized copies. Finally, review any suggested copy or A/B tests yourself before publishing — the skill aids decision-making but should not be treated as authoritative without human review.
功能分析
Type: OpenClaw Skill Name: landing-page-roast Version: 1.0.1 The skill defines a 'landing-page-roast' functionality, instructing the AI agent to audit a given page URL or copy for conversion effectiveness and suggest improvements. All instructions in SKILL.md are aligned with this stated purpose, focusing on analytical tasks and content generation. There are no indications of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent's intended behavior. The 'Page URL' input is a legitimate requirement for the skill's function and does not inherently imply malicious intent from the skill definition itself.
能力评估
Purpose & Capability
Name/description match the runtime instructions: the skill asks for a page URL or pasted copy and produces audit scores, prioritized fixes, and rewrites. It requests no binaries, env vars, or config paths—proportional for a copy/UX audit.
Instruction Scope
SKILL.md stays within the stated domain (clarity, audience fit, offer strength, trust, friction, objections) and defines concrete outputs. It does not instruct the agent to read unrelated files, environment variables, or send data to unknown endpoints. One minor ambiguity: it accepts a URL but doesn't specify whether the agent should fetch the page itself or expect pasted content; this is a usability note, not a security issue.
Install Mechanism
No install spec and no code files — instruction-only skill with no disk writes or downloaded artifacts, which is the lowest-risk installation profile.
Credentials
No credentials, tokens, or config paths are requested. The required inputs (URL/copy, audience, conversion action, offer details) are appropriate and minimal for the stated purpose.
Persistence & Privilege
Does not request always:true or any elevated persistence. Default autonomous invocation is permitted by platform policy but, on its own, does not introduce additional incoherence with the skill's purpose.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install landing-page-roast
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /landing-page-roast 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
Expanded detailed docs and practical frameworks
元数据
Slug landing-page-roast
版本 1.0.1
许可证
累计安装 3
当前安装数 3
历史版本数 1
常见问题

landing-page-roast 是什么?

Audit a landing page for clarity, trust, offer strength, and conversion friction; return prioritized fixes and copy rewrites. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1311 次。

如何安装 landing-page-roast?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install landing-page-roast」即可一键安装,无需额外配置。

landing-page-roast 是免费的吗?

是的,landing-page-roast 完全免费(开源免费),可自由下载、安装和使用。

landing-page-roast 支持哪些平台?

landing-page-roast 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 landing-page-roast?

由 xammarie(@xammarie)开发并维护,当前版本 v1.0.1。

💬 留言讨论