ccg-workflow
How to run a non-trivial change end to end with the CCG role tools (ccg_analyze / ccg_design…
Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.
$ npx -y skills add fengshao1227/ccg-workflow --skill clarify --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/clarifyContext preview
The summary Claude sees to decide when to auto-load this skill.
Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.
name: clarify description: "Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing." argument-hint: "[target]" user-invocable: false
Identify and improve unclear, confusing, or poorly written interface text to make the product easier to understand and use.
Invoke /frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /teach-impeccable first. Additionally gather: audience technical level and users' mental state in context.
---
Identify what makes the text unclear or ineffective:
1. **Find clarity problems**:
2. **Understand the context**:
**CRITICAL**: Clear copy helps users succeed. Unclear copy creates frustration, errors, and support tickets.
Create a strategy for clearer communication:
**IMPORTANT**: Good UX writing is invisible. Users should understand immediately without noticing the words.
Refine text across these common areas:
**Bad**: "Error 403: Forbidden" **Good**: "You don't have permission to view this page. Contact your admin for access."
**Bad**: "Invalid input" **Good**: "Email addresses need an @ symbol. Try: name@example.com"
**Principles**:
**Bad**: "DOB (MM/DD/YYYY)" **Good**: "Date of birth" (with placeholder showing format)
**Bad**: "Enter value here" **Good**: "Your email address" or "Company name"
**Principles**:
**Bad**: "Click here" | "Submit" | "OK" **Good**: "Create account" | "Save changes" | "Got it, thanks"
**Principles**:
**Bad**: "This is the username field" **Good**: "Choose a username. You can change this later in Settings."
**Principles**:
**Bad**: "No items" **Good**: "No projects yet. Create your first project to get started."
**Principles**:
**Bad**: "Success" **Good**: "Settings saved! Your changes will take effect immediately."
**Principles**:
**Bad**: "Loading..." (for 30+ seconds) **Good**: "Analyzing your data... this usually takes 30-60 seconds"
**Principles**:
**Bad**: "Are you sure?" **Good**: "Delete 'Project Alpha'? This can't be undone."
**Principles**:
**Bad**: Generic labels like "Items" | "Things" | "Stuff" **Good**: Specific labels like "Your projects" | "Team members" | "Settings"
**Principles**:
Every piece of copy should follow these rules:
1. **Be specific**: "Enter email" not "Enter value" 2. **Be concise**: Cut unnecessary words (but don't sacrifice clarity) 3. **Be active**: "Save changes" not "Changes will be saved" 4. **Be human**: "Oops, something went wrong" not "System error encountered" 5. **Be helpful**: Tell users what to do, not just what happened 6. **Be consistent**: Use same terms throughout (don't vary for variety)
**NEVER**:
多模型协作工作流引擎 — /ccg:go 一个命令,AI 自动分析意图、选择策略、编排 Codex + Gemini + Claude 协作执行
Repo: fengshao1227/ccg-workflow
How to run a non-trivial change end to end with the CCG role tools (ccg_analyze / ccg_design…
变更校验关卡。分析代码变更,检测文档同步状态,评估变更影响范围。当用户提到变更检查、文档同步、代码审查、提交前检查、diff分析时使用。在设计级变更、重构完成时自动触发。
模块完整性校验关卡。扫描目录结构、检测缺失文档、验证代码与文档同步。当用户提到模块校验、文档检查、结构完整性、README检查、DESIGN检查时使用。在新建模块完成时自动触发。
代码质量校验关卡。检测复杂度、重复代码、命名规范、函数长度等质量指标。当用户提到代码质量、复杂度检查、代码异味、重构建议、lint检查、代码规范时使用。在复杂模块、重构完成时自动触发。
安全校验关卡。自动扫描代码安全漏洞,检测危险模式,确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变…