菜单
This skill should be used when creating or organizing working files in the .claude/ directory. It enforces consistent structure, naming conventions, and required cross-references for plans, architecture docs, examples, research, and analysis files.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
This skill should be used when managing the file-based todo tracking system in the .claude/todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.
This skill should be used when writing code in any opinionated framework's distinctive style. It applies when writing framework-based applications, creating models/controllers/views, or any framework code. Triggers on code generation, refactoring requests, code review, or when the user mentions framework conventions. Embodies the philosophy of embracing framework conventions, fighting complexity, and choosing simplicity over cleverness.
This skill should be used when writing software libraries, packages, or modules following battle-tested patterns for clean, minimal, production-ready code. It applies when creating new libraries, refactoring existing ones, designing library APIs, or when clean, dependency-minimal library code is needed. Triggers on requests like "create a library", "write a package", "design a module API", or mentions of professional library development.
This skill should be used when building production LLM applications in any language. It applies when implementing predictable AI features, creating structured interfaces for LLM operations, configuring language model providers, building agent systems with tools, optimizing prompts, or testing LLM-powered functionality. Covers language-agnostic patterns for type-safe contracts, modular composition, multi-provider support, and production deployment.
| name | claude-workspace |
| description | This skill should be used when creating or organizing working files in the .claude/ directory. It enforces consistent structure, naming conventions, and required cross-references for plans, architecture docs, examples, research, and analysis files. |
| allowed-tools | ["Read","Write","Bash","Grep","Glob"] |
Maintain organized working files in the .claude/ directory with enforced structure, consistent naming, and required cross-references to codebase files and related documentation.
Use this skill when:
.claude/
├── plans/ # Implementation plans, migration plans, project plans
│ └── INDEX.md
├── architecture/ # ADRs, design decisions, system diagrams
│ └── INDEX.md
├── examples/ # Code examples, usage patterns, reference implementations
│ └── INDEX.md
├── research/ # Research notes, external findings, comparative analysis
│ └── INDEX.md
└── analysis/ # Code analysis, performance studies, security reviews
└── INDEX.md
Every working file MUST contain at least one link to a relevant codebase file. No orphan documentation.
Files should cross-reference related documents in other categories when relevant connections exist.
When creating or modifying files, always update the category's INDEX.md.
All files use YAML frontmatter with required fields per category. See frontmatter-schemas.md.
What would you like to do?
Wait for response before proceeding.
| Response | Workflow |
|---|---|
| 1, "create", "new", "add", "plan", "architecture", "example", "research", "analysis" | create-file.md |
| 2, "index", "update index", "refresh" | update-index.md |
| 3, "validate", "check", "verify" | validate-workspace.md |
| 4, "migrate", "organize", "cleanup", "move" | migrate-existing.md |
{category}/{YYYY-MM-DD}-{kebab-case-description}.md
Examples:
plans/2025-01-07-user-authentication-migration.mdarchitecture/2025-01-07-event-sourcing-design.mdresearch/2025-01-07-auth-library-comparison.mdexamples/2025-01-07-pagination-pattern.mdanalysis/2025-01-07-n-plus-one-audit.mdSee naming-conventions.md for details.
Every file MUST include a ## Related section:
## Related
### Codebase
- [user.rb](../../app/models/user.rb) - Primary model affected by this plan
### Related Documentation
- [Auth Architecture](../architecture/2025-01-07-auth-design.md) - Design decision this implements
See cross-reference-rules.md for full rules.
| Category | Purpose | Status Values |
|---|---|---|
| plans/ | Implementation plans, migration plans | draft, in-progress, approved, implemented, superseded |
| architecture/ | ADRs, design decisions | proposed, accepted, deprecated, superseded |
| examples/ | Code patterns, reference implementations | (no status) |
| research/ | External research, comparisons | in-progress, complete |
| analysis/ | Code analysis, performance studies | in-progress, complete |
See file-categories.md for detailed guidance.
Invoked by:
/workspace command (if configured)Works with:
file-todos - Todos can link to plans or architecture docscompound-docs - Solution docs can reference research or analysis files/workflows:plan - Plans created via workflow can use this organizationA workspace file is valid when ALL of the following are true:
YYYY-MM-DD-description.md pattern## Related > ### Codebase