SkillAtlasSkill 详情

lesson-learned

Opinionated skills shared by @leonardocouy for improving daily work efficiency with Claude Code.

审核状态:已审核Quality 80Security 100

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件:README.md

抓取于 2026年8月15日

Softaworks Agent Skills

Opinionated skills shared by @leonardocouy for improving daily work efficiency with Claude Code. Skills are packaged instructions and scripts that extend agent capabilities across development, documentation, planning, and professional workflows.

Skills follow the Agent Skills format.


🧭 Quick Navigation

🚀 Installation • 📚 Available Skills • 🤖 Agents & Commands • 📖 Skill Structure • 🤝 Contributing • 📄 License • 🔗 Links


🚀 Installation

Quick Install (Recommended)

npx skills add softaworks/agent-toolkit

This method works with multiple AI coding agents (Claude Code, Codex, Cursor, AdaL, etc.)

Register as Plugin Marketplace

Run the following commands in Claude Code:

/plugin marketplace add softaworks/agent-toolkit
/plugin

Install Plugins

Option 1: Via Browse UI

  1. Switch to Marketplaces tab (use arrow keys or Tab)
  2. Select agent-toolkit, press Enter
  3. Browse and select the plugin(s) you want to install
  4. Select Install now

Option 2: Direct Install

# Install specific skill
/plugin install codex@agent-toolkit
/plugin install humanizer@agent-toolkit

# Install specific agent
/plugin install agent-codebase-pattern-finder@agent-toolkit

# Install specific command
/plugin install command-codex-plan@agent-toolkit

Option 3: Ask the Agent

Simply tell Claude Code:

Please install Skills from github.com/softaworks/agent-toolkit

Available Plugins

Each skill, agent, and command is an individual plugin that can be installed separately:

  • Skills → See Available Skills for the full list
  • Agents → See Agents (install as agent-<name>@agent-toolkit)
  • Commands → See Slash Commands (install as command-<name>@agent-toolkit)

Update Plugins

To update plugins to the latest version:

  1. Run /plugin in Claude Code
  2. Switch to Marketplaces tab
  3. Select agent-toolkit
  4. Choose Update marketplace

You can also Enable auto-update to get the latest versions automatically.

Manual Installation

For Claude Code (Manual) — Skills only

cp -r skills/<skill-name> ~/.claude/skills/

For claude.ai — Skills only

Add skills to project knowledge or paste SKILL.md contents into the conversation.


📚 Available Skills

CategorySkillDescription
🤖 AI ToolscodexAdvanced code analysis with GPT-5.2
🤖 AI ToolsgeminiLarge-scale review (200k+ context)
🤖 AI ToolsperplexityWeb search & research
🔮 Metaagent-md-refactorRefactor bloated agent instruction files
🔮 Metacommand-creatorCreate Claude Code slash commands
🔮 Metaplugin-forgeBuild Claude Code plugins & manifests
🔮 Metaskill-judgeEvaluate skill design quality
📝 Documentationbackend-to-frontend-handoff-docsAPI handoff docs for frontend
📝 Documentationc4-architectureC4 architecture diagrams with Mermaid
📝 Documentationcrafting-effective-readmesWrite effective README files
📝 Documentationdraw-ioCreate & edit draw.io diagrams
📝 DocumentationexcalidrawWork with Excalidraw diagrams
📝 Documentationfrontend-to-backend-requirementsDocument API requirements
📝 Documentationmarp-slideProfessional presentation slides
📝 Documentationmermaid-diagramsSoftware diagrams with Mermaid
📝 Documentationwriting-clearly-and-conciselyClear, professional writing
🎨 Design & Frontenddesign-system-starterCreate design systems
🎨 Design & FrontendmuiMaterial-UI v7 patterns
🎨 Design & Frontendopenapi-to-typescriptConvert OpenAPI to TypeScript
🎨 Design & Frontendreact-devType-safe React 18-19 with TypeScript
🎨 Design & Frontendreact-useeffectReact useEffect best practices
🛠️ Developmentdatabase-schema-designerDesign robust database schemas
🛠️ Developmentdependency-updaterSmart dependency management
🛠️ Developmentnaming-analyzerSuggest better variable/function names
🛠️ Developmentlesson-learnedExtract SE lessons from recent code changes
🛠️ Developmentreducing-entropyMinimize codebase size
🛠️ Developmentsession-handoffSeamless AI session transfers
🎯 Planninggame-changing-featuresFind 10x product opportunities
🎯 PlanninggepettoDetailed implementation planning
🎯 Planningrequirements-clarityClarify requirements before coding
🎯 Planningship-learn-nextTurn learning into actionable reps
👔 Professionaldaily-meeting-updateInteractive daily standup generator
👔 Professionaldifficult-workplace-conversationsNavigate difficult conversations
👔 Professionalfeedback-masteryDeliver constructive feedback
👔 Professionalprofessional-communicationTechnical communication guide
🧪 Testingqa-test-plannerComprehensive QA test planning
📦 Gitcommit-workHigh-quality git commits
🔧 Utilitiesdatadog-cliDebug with Datadog logs & metrics
🔧 Utilitiesdomain-name-brainstormerGenerate & check domain names
🔧 UtilitieshumanizerRemove AI writing patterns
🔧 Utilitiesmeme-factoryGenerate memes with API
🔧 UtilitiesjiraNatural language Jira interaction
🔧 Utilitiesweb-to-markdownConvert webpages to Markdown

🤖 Agents & Commands

Requires Claude Code CLI — These agents and commands are exclusive to Claude Code users.

For full access, add the marketplace and install plugins:

/plugin marketplace add softaworks/agent-toolkit
/plugin install codex@agent-toolkit

Agents

Specialized sub-agents that Claude Code can delegate tasks to:

AgentDescription
ascii-ui-mockup-generatorVisualize UI concepts through ASCII mockups
codebase-pattern-finderFind similar implementations and patterns
communication-excellence-coachEmail refinement, tone calibration, roleplay
general-purposeDefault agent for complex multi-step tasks
mermaid-diagram-specialistCreate flowcharts, sequence diagrams, ERDs
ui-ux-designerResearch-backed UI/UX design feedback

Slash Commands

Reusable workflows invoked with /command-name:

CommandDescription
/codex-planCreate implementation plans using Codex 5.2
/compose-emailDraft professional emails
/explain-changes-mental-modelBuild mental model of code changes
/explain-pr-changesGenerate PR summaries
/sync-branchSync feature branch with main
/sync-skills-readmeUpdate README skills table
/viral-tweetOptimize tweet ideas for X engagement

📖 Skill Structure

Each skill contains:

  • SKILL.md - Detailed instructions for the agent (with YAML frontmatter)
  • README.md - User-friendly documentation with examples
  • scripts/ - Helper scripts for automation (optional)
  • references/ - Supporting documentation (optional)

🤝 Contributing

Contributions are welcome! When adding new skills:

  1. Follow the Agent Skills format
  2. Include both SKILL.md (for agents) and README.md (for users)
  3. Add YAML frontmatter to SKILL.md with name: and description: fields
  4. Update this README.md with a link to your skill

📄 License

MIT


🔗 Links

开发与工程

低风险

  • 来源需自行核对维护者身份。
  • 未检测到明显脚本安装指令。
  • 未检测到明显外部权限要求。
  • 未检测到高风险命令。
  • 扫描发现:0 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/softaworks/agent-toolkit.git
  3. 将 "skills/lesson-learned" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/softaworks/agent-toolkit.git
  3. 将 "skills/lesson-learned" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/softaworks/agent-toolkit.git
  3. 将 "skills/lesson-learned" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/softaworks/agent-toolkit.git
  3. 将 "skills/lesson-learned" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/softaworks/agent-toolkit.git
  3. 将 "skills/lesson-learned" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: lesson-learned
description: "Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work."

Lesson Learned

Extract specific, grounded software engineering lessons from actual code changes. Not a lecture -- a mirror. Show the user what their code already demonstrates.

Before You Begin

Load the principles reference first.

  1. Read references/se-principles.md to have the principle catalog available
  2. Optionally read references/anti-patterns.md if you suspect the changes include areas for improvement
  3. Determine the scope of analysis (see Phase 1)

Do not proceed until you've loaded at least se-principles.md.

Phase 1: Determine Scope

Ask the user or infer from context what to analyze.

ScopeGit CommandsWhen to Use
Feature branchgit log main..HEAD --oneline + git diff main...HEADUser is on a non-main branch (default)
Last N commitsgit log --oneline -N + git diff HEAD~N..HEADUser specifies a range, or on main (default N=5)
Specific commitgit show <sha>User references a specific commit
Working changesgit diff + git diff --cachedUser says "what about these changes?" before committing

Default behavior:

  • If on a feature branch: analyze branch commits vs main
  • If on main: analyze the last 5 commits
  • If the user provides a different scope, use that

Phase 2: Gather Changes

  1. Run git log with the determined scope to get the commit list and messages
  2. Run git diff for the full diff of the scope
  3. If the diff is large (>500 lines), use git diff --stat first, then selectively read the top 3-5 most-changed files
  4. Read commit messages carefully -- they contain intent that raw diffs miss
  5. Only read changed files. Do not read the entire repo.

Phase 3: Analyze

Identify the dominant pattern -- the single most instructive thing about these changes.

Look for:

  • Structural decisions -- How was the code organized? Why those boundaries?
  • Trade-offs made -- What was gained vs. sacrificed? (readability vs. performance, DRY vs. clarity, speed vs. correctness)
  • Problems solved -- What was the before/after? What made the "after" better?
  • Missed opportunities -- Where could the code improve? (present gently as "next time, consider...")

Map findings to specific principles from references/se-principles.md. Be specific -- quote actual code, reference actual file names and line changes.

Phase 4: Present the Lesson

Use this template:

## Lesson: [Principle Name]

**What happened in the code:**
[2-3 sentences describing the specific change, referencing files and commits]

**The principle at work:**
[1-2 sentences explaining the SE principle]

**Why it matters:**
[1-2 sentences on the practical consequence -- what would go wrong without this, or what goes right because of it]

**Takeaway for next time:**
[One concrete, actionable sentence the user can apply to future work]

If there is a second lesson worth noting (maximum 2 additional):

---

### Also worth noting: [Principle Name]

**In the code:** [1 sentence]
**The principle:** [1 sentence]
**Takeaway:** [1 sentence]

What NOT to Do

AvoidWhyInstead
Listing every principle that vaguely appliesOverwhelming and genericPick the 1-2 most relevant
Analyzing files that were not changedScope creepStick to the diff
Ignoring commit messagesThey contain intent that diffs missRead them as primary context
Abstract advice disconnected from the codeNot actionableAlways reference specific files/lines
Negative-only feedbackDemoralizingLead with what works, then suggest improvements
More than 3 lessonsDilutes the insightOne well-grounded lesson beats seven vague ones

Conversation Style

  • Reflective, not prescriptive. Use the user's own code as primary evidence.
  • Never say "you should have..." -- instead use "the approach here shows..." or "next time you face this, consider..."
  • If the code is good, say so. Not every lesson is about what went wrong. Recognizing good patterns reinforces them.
  • If the changes are trivial (a single config tweak, a typo fix), say so honestly rather than forcing a lesson. "These changes are straightforward -- no deep lesson here, just good housekeeping."
  • Be specific. Generic advice is worthless. Every claim must point to a concrete code change.

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!