返回技能列表

iterate-lessons-log

product-on-purpose
更新于 2 days ago
6 次查看
238
33
238
在 GitHub 上查看
general

关于

This skill creates structured lessons learned entries to capture organizational knowledge from projects or incidents. It focuses on preserving patterns, anti-patterns, and key insights for future teams beyond immediate retrospectives. Use it after significant initiatives or failures to document hard-won wisdom in a reusable format.

快速安装

Claude Code

推荐
主要方式
npx skills add product-on-purpose/pm-skills -a claude-code
插件命令备选方式
/plugin add https://github.com/product-on-purpose/pm-skills
Git 克隆备选方式
git clone https://github.com/product-on-purpose/pm-skills.git ~/.claude/skills/iterate-lessons-log

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->

Lessons Log

A lessons log entry captures significant learning from projects, incidents, or experiences in a format that's useful to future teams who weren't there. Unlike retrospectives (which focus on team improvement), lessons logs focus on organizational knowledge that transcends individual teams.patterns, anti-patterns, and hard-won wisdom.

When to Use

  • After completing a significant project or initiative
  • Following a major incident, outage, or failure
  • When you realize something important that others should know
  • After discovering a pattern that keeps recurring
  • When experienced team members leave (capture their knowledge)
  • During post-mortems to preserve learnings

Instructions

When asked to create a lessons log entry, follow these steps:

  1. Choose a Descriptive Title Write a title that someone searching for this topic would find. Include keywords that describe the situation and the learning. Avoid generic titles like "Project X lessons."

  2. Provide Context Explain the situation fully enough that someone who wasn't there can understand it. Include the project, timeline, team, and any relevant constraints. Future readers need this context to assess applicability.

  3. Describe What Happened Write a factual account of what occurred. Be specific about actions taken, decisions made, and outcomes observed. Avoid blame.focus on events and systems.

  4. Extract the Lesson Articulate what you learned clearly. The lesson should be actionable.something others can apply. Distinguish between what you observed and your interpretation of why it matters.

  5. Formulate Recommendations Provide specific guidance for future teams facing similar situations. What should they do? What should they avoid? What questions should they ask?

  6. Define Applicability Help readers know when this lesson applies. What situations trigger relevance? What context makes it more or less applicable?

  7. Add Tags for Searchability Include keywords and categories that will help future searchers find this entry. Think about what someone would search for when facing a similar situation.

Output Format

Use the template in references/TEMPLATE.md to structure the output.

Quality Checklist

Before finalizing, verify:

  • Title is descriptive and searchable
  • Context is complete enough for someone who wasn't there
  • Lesson is clearly articulated and actionable
  • Recommendations are specific, not vague
  • Entry stands alone (doesn't require external context)
  • Tags enable future discovery

Examples

See references/EXAMPLE.md for a completed example.

GitHub 仓库

product-on-purpose/pm-skills
路径: skills/iterate-lessons-log
0
agent-skillsai-skillsclaude-codeclaude-desktopdesign-sprintfoundation-sprint

相关推荐技能

content-collections

Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。

查看技能

polymarket

这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。

查看技能

creating-opencode-plugins

该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。

查看技能

sglang

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能