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。
Opinionated skills shared by @leonardocouy for improving daily work efficiency with Claude Code.
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。
来源文件:README.md
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.
🚀 Installation • 📚 Available Skills • 🤖 Agents & Commands • 📖 Skill Structure • 🤝 Contributing • 📄 License • 🔗 Links
npx skills add softaworks/agent-toolkit
This method works with multiple AI coding agents (Claude Code, Codex, Cursor, AdaL, etc.)
Run the following commands in Claude Code:
/plugin marketplace add softaworks/agent-toolkit
/plugin
Option 1: Via Browse UI
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
Each skill, agent, and command is an individual plugin that can be installed separately:
agent-<name>@agent-toolkit)command-<name>@agent-toolkit)To update plugins to the latest version:
/plugin in Claude CodeYou can also Enable auto-update to get the latest versions automatically.
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.
| Category | Skill | Description |
|---|---|---|
| 🤖 AI Tools | codex | Advanced code analysis with GPT-5.2 |
| 🤖 AI Tools | gemini | Large-scale review (200k+ context) |
| 🤖 AI Tools | perplexity | Web search & research |
| 🔮 Meta | agent-md-refactor | Refactor bloated agent instruction files |
| 🔮 Meta | command-creator | Create Claude Code slash commands |
| 🔮 Meta | plugin-forge | Build Claude Code plugins & manifests |
| 🔮 Meta | skill-judge | Evaluate skill design quality |
| 📝 Documentation | backend-to-frontend-handoff-docs | API handoff docs for frontend |
| 📝 Documentation | c4-architecture | C4 architecture diagrams with Mermaid |
| 📝 Documentation | crafting-effective-readmes | Write effective README files |
| 📝 Documentation | draw-io | Create & edit draw.io diagrams |
| 📝 Documentation | excalidraw | Work with Excalidraw diagrams |
| 📝 Documentation | frontend-to-backend-requirements | Document API requirements |
| 📝 Documentation | marp-slide | Professional presentation slides |
| 📝 Documentation | mermaid-diagrams | Software diagrams with Mermaid |
| 📝 Documentation | writing-clearly-and-concisely | Clear, professional writing |
| 🎨 Design & Frontend | design-system-starter | Create design systems |
| 🎨 Design & Frontend | mui | Material-UI v7 patterns |
| 🎨 Design & Frontend | openapi-to-typescript | Convert OpenAPI to TypeScript |
| 🎨 Design & Frontend | react-dev | Type-safe React 18-19 with TypeScript |
| 🎨 Design & Frontend | react-useeffect | React useEffect best practices |
| 🛠️ Development | database-schema-designer | Design robust database schemas |
| 🛠️ Development | dependency-updater | Smart dependency management |
| 🛠️ Development | naming-analyzer | Suggest better variable/function names |
| 🛠️ Development | lesson-learned | Extract SE lessons from recent code changes |
| 🛠️ Development | reducing-entropy | Minimize codebase size |
| 🛠️ Development | session-handoff | Seamless AI session transfers |
| 🎯 Planning | game-changing-features | Find 10x product opportunities |
| 🎯 Planning | gepetto | Detailed implementation planning |
| 🎯 Planning | requirements-clarity | Clarify requirements before coding |
| 🎯 Planning | ship-learn-next | Turn learning into actionable reps |
| 👔 Professional | daily-meeting-update | Interactive daily standup generator |
| 👔 Professional | difficult-workplace-conversations | Navigate difficult conversations |
| 👔 Professional | feedback-mastery | Deliver constructive feedback |
| 👔 Professional | professional-communication | Technical communication guide |
| 🧪 Testing | qa-test-planner | Comprehensive QA test planning |
| 📦 Git | commit-work | High-quality git commits |
| 🔧 Utilities | datadog-cli | Debug with Datadog logs & metrics |
| 🔧 Utilities | domain-name-brainstormer | Generate & check domain names |
| 🔧 Utilities | humanizer | Remove AI writing patterns |
| 🔧 Utilities | meme-factory | Generate memes with API |
| 🔧 Utilities | jira | Natural language Jira interaction |
| 🔧 Utilities | web-to-markdown | Convert webpages to Markdown |
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
Specialized sub-agents that Claude Code can delegate tasks to:
| Agent | Description |
|---|---|
| ascii-ui-mockup-generator | Visualize UI concepts through ASCII mockups |
| codebase-pattern-finder | Find similar implementations and patterns |
| communication-excellence-coach | Email refinement, tone calibration, roleplay |
| general-purpose | Default agent for complex multi-step tasks |
| mermaid-diagram-specialist | Create flowcharts, sequence diagrams, ERDs |
| ui-ux-designer | Research-backed UI/UX design feedback |
Reusable workflows invoked with /command-name:
| Command | Description |
|---|---|
/codex-plan | Create implementation plans using Codex 5.2 |
/compose-email | Draft professional emails |
/explain-changes-mental-model | Build mental model of code changes |
/explain-pr-changes | Generate PR summaries |
/sync-branch | Sync feature branch with main |
/sync-skills-readme | Update README skills table |
/viral-tweet | Optimize tweet ideas for X engagement |
Each skill contains:
SKILL.md - Detailed instructions for the agent (with YAML frontmatter)README.md - User-friendly documentation with examplesscripts/ - Helper scripts for automation (optional)references/ - Supporting documentation (optional)Contributions are welcome! When adding new skills:
SKILL.md (for agents) and README.md (for users)SKILL.md with name: and description: fieldsMIT
name: naming-analyzer
description: Suggest better variable, function, and class names based on context and conventions.Suggest better variable, function, and class names based on context and conventions.
You are a naming convention expert. When invoked:
Analyze Existing Names:
Identify Issues:
Check Conventions:
Provide Suggestions:
camelCasePascalCaseUPPER_SNAKE_CASE_prefixUnderscore or #privateFieldis, has, can, should prefixessnake_casePascalCaseUPPER_SNAKE_CASE_prefix_underscoreis_, has_, can_ prefixescamelCasePascalCaseUPPER_SNAKE_CASElowercasePascalCasecamelCaseHTTPServer, not HttpServer)// ❌ Bad - Too generic
function process(data) { }
const info = getData();
let temp = x;
// ✓ Good - Specific and clear
function processPayment(transaction) { }
const userProfile = getUserProfile();
let previousValue = x;
// ❌ Bad - Name doesn't match behavior
function getUser(id) {
const user = fetchUser(id);
user.lastLogin = Date.now();
saveUser(user); // Side effect! Not just "getting"
return user;
}
// ✓ Good - Name reflects actual behavior
function fetchAndUpdateUserLogin(id) {
const user = fetchUser(id);
user.lastLogin = Date.now();
saveUser(user);
return user;
}
// ❌ Bad - Unclear abbreviations
const usrCfg = loadConfig();
function calcTtl(arr) { }
// ✓ Good - Clear and readable
const userConfig = loadConfig();
function calculateTotal(amounts) { }
// ✓ Acceptable - Well-known abbreviations
const htmlElement = document.getElementById('main');
const apiUrl = process.env.API_URL;
// ❌ Bad - Unclear state
const login = user.authenticated;
const status = checkUser();
// ✓ Good - Clear boolean intent
const isLoggedIn = user.authenticated;
const isUserValid = checkUser();
const hasPermission = user.roles.includes('admin');
const canEditPost = isOwner || isAdmin;
const shouldShowNotification = isEnabled && hasUnread;
// ❌ Bad - Unnamed constants
if (age > 18) { }
setTimeout(callback, 3600000);
// ✓ Good - Named constants
const LEGAL_AGE = 18;
const ONE_HOUR_IN_MS = 60 * 60 * 1000;
if (age > LEGAL_AGE) { }
setTimeout(callback, ONE_HOUR_IN_MS);
@naming-analyzer
@naming-analyzer src/
@naming-analyzer UserService.js
@naming-analyzer --conventions
@naming-analyzer --fix-all
# Naming Analysis Report
## Summary
- Items analyzed: 156
- Issues found: 23
- Critical: 5 (misleading names)
- Major: 12 (unclear/vague)
- Minor: 6 (convention violations)
---
## Critical Issues (5)
### src/services/UserService.js:45
**Current**: `getUser(id)`
**Issue**: Function name implies read-only but has side effects (updates lastLogin)
**Severity**: Critical - Misleading
**Suggestion**: `fetchAndUpdateUserLogin(id)`
**Reason**: Name should reflect the mutation
### src/utils/helpers.js:23
**Current**: `validate(x)`
**Issue**: Generic parameter name, unclear what's being validated
**Severity**: Critical - Too vague
**Suggestion**: `validateEmail(emailAddress)`
**Reason**: Specific names improve clarity
---
## Major Issues (12)
### src/components/DataList.jsx:12
**Current**: `const d = new Date()`
**Issue**: Single-letter variable in large scope
**Severity**: Major
**Suggestion**: `const currentDate = new Date()`
**Reason**: Clarity and searchability
### src/api/client.js:67
**Current**: `function proc(data) {}`
**Issue**: Abbreviated function name
**Severity**: Major
**Suggestion**: `function processApiResponse(data) {}`
**Reason**: Full words are more readable
### src/models/User.js:34
**Current**: `user.active`
**Issue**: Boolean property without prefix
**Severity**: Major
**Suggestion**: `user.isActive`
**Reason**: Follow boolean naming convention
### src/utils/format.js:89
**Current**: `const MAX = 100`
**Issue**: Generic constant name
**Severity**: Major
**Suggestion**: `const MAX_RETRY_ATTEMPTS = 100`
**Reason**: Specific purpose is clearer
---
## Minor Issues (6)
### src/config/settings.js:12
**Current**: `const API_url = '...'`
**Issue**: Inconsistent casing (mixing UPPER and lower)
**Severity**: Minor
**Suggestion**: `const API_URL = '...'` or `const apiUrl = '...'`
**Reason**: Consistency in convention
### src/helpers/string.js:45
**Current**: `function strToNum(s) {}`
**Issue**: Abbreviated function and parameter
**Severity**: Minor
**Suggestion**: `function stringToNumber(value) {}`
**Reason**: Clarity over brevity
---
## Convention Violations
### Inconsistent Boolean Prefixes
**Locations**: 8 files
**Issue**: Mixed use of `is`, `has`, `can` vs no prefix
**Recommendation**: Standardize on boolean prefixes
- Use `is` for state: `isActive`, `isVisible`
- Use `has` for possession: `hasPermission`, `hasError`
- Use `can` for ability: `canEdit`, `canDelete`
- Use `should` for decisions: `shouldRender`, `shouldValidate`
### Mixed Naming Conventions
**Location**: src/legacy/
**Issue**: Mix of camelCase and snake_case in JavaScript
**Recommendation**: Convert all to camelCase for consistency
---
## Suggested Renaming
### High Priority (Misleading or Critical)
1. `getUser` → `fetchAndUpdateUserLogin` (src/services/UserService.js:45)
2. `validate` → `validateEmail` (src/utils/helpers.js:23)
3. `process` → `processPaymentTransaction` (src/payment/processor.js:67)
### Medium Priority (Clarity)
1. `d` → `currentDate` (7 locations)
2. `temp` → `previousValue` (4 locations)
3. `data` → `apiResponse` or more specific (12 locations)
4. `arr` → `items`, `values`, or more specific (8 locations)
### Low Priority (Convention)
1. `active` → `isActive` (12 locations)
2. `error` → `hasError` (6 locations)
3. `API_url` → `API_URL` (3 locations)
---
## Naming Patterns to Follow
### Functions/Methods
- Verbs: `get`, `set`, `create`, `update`, `delete`, `fetch`, `calculate`, `validate`
- Clear action: `sendEmail()`, `parseJSON()`, `formatCurrency()`
### Classes
- Nouns: `UserService`, `PaymentProcessor`, `EmailValidator`
- Avoid generic: Don't use `Manager`, `Helper`, `Utility` unless necessary
### Variables
- Nouns or noun phrases: `user`, `emailAddress`, `totalAmount`
- Descriptive: `userList` not `list`, `activeUsers` not `users2`
### Constants
- All caps with underscores: `MAX_RETRY_ATTEMPTS`, `DEFAULT_TIMEOUT`
- Include units: `CACHE_DURATION_MS`, `MAX_FILE_SIZE_MB`
### Booleans
- Question form: `isValid`, `hasPermission`, `canEdit`
- Affirmative: `isEnabled` not `isDisabled` (prefer positive)
---
## Refactoring Script
Would you like me to create a refactoring script to apply these changes?
This will:
1. Rename all suggested items
2. Update all references
3. Maintain git history
4. Generate migration guide
---
## Best Practices
✓ **DO**:
- Use full words over abbreviations
- Be specific and descriptive
- Follow language conventions
- Use consistent patterns
- Make booleans obvious
- Include units in constants
✗ **DON'T**:
- Use single letters (except in loops: i, j, k)
- Use vague names (data, info, temp, x)
- Mix naming conventions
- Use misleading names
- Over-abbreviate
- Use Hungarian notation in modern code
Is it a boolean?
├─ Yes → Use is/has/can/should prefix
└─ No → Is it a function?
├─ Yes → Use verb phrase (action)
└─ No → Is it a class?
├─ Yes → Use noun (PascalCase)
└─ No → Is it a constant?
├─ Yes → Use UPPER_SNAKE_CASE
└─ No → Use descriptive noun (camelCase/snake_case)
i, j)html, api, url, id)
评论 (0)
暂无评论,成为第一个评论者吧!