Back to Details

lenny-skillpack-creator

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Lenny Skillpack Creator

Lenny Skill Pack 生成器

Your job is to refactor “insight-heavy” Refound/Lenny skills into agent-executable skill packs: boundary-clear, artifact-driven, and testable.
This skill is designed to be compatible with both:
  • OpenAI Codex (Codex CLI / IDE skills)
  • Claude Code (Agent Skills)
You are NOT writing a blog post. You are producing an installable folder with SKILL.md + 
references/
(+ optional 
scripts/
).
Language requirement: The generated skill pack (SKILL.md and all referenced templates/checklists) must be written in English.
你的任务是将“富含洞见的”Refound/Lenny Skill重构为可由Agent执行的Skill Pack：边界清晰、以产出物为导向且可测试。
本技能兼容以下两种环境：
  • OpenAI Codex（Codex CLI / IDE技能）
  • Claude Code（Agent Skills）
你并非要撰写博客文章，而是要生成一个可安装的文件夹，包含SKILL.md + 
references/
（可选包含
scripts/
）。
语言要求：生成的Skill Pack（SKILL.md及所有参考模板/检查表）必须以英文撰写。

What you produce

产出内容

For a given source skill, output an installable skill directory:
  • <skill-slug>/SKILL.md
    (short, executable, high-signal)
  • <skill-slug>/references/
    (templates, checklists, rubrics, question bank, examples, source notes)
  • <skill-slug>/scripts/
    (optional: lint, scaffolding, batch tools)
  • <skill-slug>/README.md
    (install + invoke + examples)
Follow the spec in references/SKILL_PACK_SPEC.md.
针对给定的源Skill，输出一个可安装的Skill目录：
  • <skill-slug>/SKILL.md
    （简洁、可执行、高信息密度）
  • <skill-slug>/references/
    （模板、检查表、评估标准、问题库、示例、源笔记）
  • <skill-slug>/scripts/
    （可选：代码检查、脚手架、批量处理工具）
  • <skill-slug>/README.md
    （安装 + 调用 + 示例）
请遵循references/SKILL_PACK_SPEC.md中的规范。

Inputs you need

所需输入

Ask for the minimum information needed to proceed. If missing, proceed with explicit assumptions.
Required:
  1. The source skill content (SKILL.md or copied text from the Refound page)
  2. The intended user / agent context (e.g., “PM agent”, “Hiring assistant”, “Founder operator”, etc.)
  3. The intended outputs (what artifacts should exist at the end)
Optional but helpful:
  • Tool constraints (read-only? allowed to write files? allowed to run shell?)
  • House style / terminology (company-specific sections, metric names, etc.)
仅询问完成任务所需的最少信息。若信息缺失，需基于明确假设推进。
必填项：
  1. 源Skill内容（SKILL.md或从Refound页面复制的文本）
  2. 目标用户/Agent场景（例如：“PM Agent”、“招聘助手”、“创始人运营者”等）
  3. 预期产出（最终应生成哪些产出物）
可选但有帮助的信息：
  • 工具限制（仅可读？允许写入文件？允许运行Shell命令？）
  • 内部风格/术语（公司专属模块、指标名称等）

Core principle: Convert insights into an execution contract

核心原则：将洞见转换为执行契约

Every generated SKILL.md must include:
  • When to use / When NOT to use
  • Input contract (minimum inputs + missing-info strategy)
  • Output contract (explicit deliverables)
  • Workflow (5–9 steps; each step: inputs → actions → outputs → checks)
  • Quality gate (checklist/rubric + “risks / open questions / next steps”)
  • Examples (2 positive + 1 boundary/negative)
Use references/TRANSFORMATION_RULES.md as the canonical conversion playbook.
每个生成的SKILL.md必须包含：
  • 适用场景/不适用场景
  • 输入契约（最小输入要求 + 缺失信息处理策略）
  • 输出契约（明确的交付物）
  • 工作流（5-9个步骤；每个步骤：输入 → 操作 → 输出 → 检查项）
  • 质量把关（检查表/评估标准 + “风险/待解决问题/下一步行动”）
  • 示例（2个正面示例 + 1个边界/负面示例）
请以references/TRANSFORMATION_RULES.md作为标准转换指南。

Progressive disclosure (keep SKILL.md short)

渐进式披露（保持SKILL.md简洁）

Keep SKILL.md operational. Move long content into 
references/
and cite the files.
Heuristic:
  • SKILL.md: 1–2 pages
  • references/
    : everything else (templates, deep notes, long checklists)
确保SKILL.md具备可操作性。将冗长内容移至
references/
目录并在SKILL.md中引用对应文件。
参考准则：
  • SKILL.md：1-2页
  • references/
    ：其余所有内容（模板、深度笔记、长检查表）

Safety + reliability rules

安全与可靠性规则

  • Default to least privilege. Only request tools you need.
  • Never ask for credentials or secrets.
  • If the skill writes/modifies code or makes irreversible changes, require explicit confirmation and add rollback guidance.
Use references/SECURITY_GUIDE.md.
  • 默认采用最小权限原则。仅请求完成任务所需的工具权限。
  • 绝不索要凭据或机密信息。
  • 若该技能会写入/修改代码或做出不可逆更改，需要求明确确认并提供回滚指导。
请遵循references/SECURITY_GUIDE.md。

Packaging

打包方式

If the environment supports file operations, create the folder structure and write files. Otherwise, output a complete file tree in-chat (one file at a time), clearly labeled.
Optional helper scripts (in this skill folder):
  • scripts/init_skillpack.py to generate a skeleton
  • scripts/lint_skillpack.py to validate structure
  • scripts/package_skillpack.py to zip a skill pack
  • scripts/fetch_refound_skills.py to download Refound SKILL.md sources from a URL list/manifest
若环境支持文件操作，创建文件夹结构并写入文件。 否则，在对话中输出完整的文件树（一次一个文件），并清晰标注。
本技能文件夹中的可选辅助脚本：
  • scripts/init_skillpack.py：用于生成Skill Pack骨架
  • scripts/lint_skillpack.py：用于验证结构合规性
  • scripts/package_skillpack.py：用于将Skill Pack打包为Zip文件
  • scripts/fetch_refound_skills.py：用于从URL列表/清单下载Refound SKILL.md源文件