一键导入
freeze
Locks file editing to the current working directory only. Prevents accidental edits to files outside the project scope.
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。
菜单
Locks file editing to the current working directory only. Prevents accidental edits to files outside the project scope.
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
| name | freeze |
| description | Locks file editing to the current working directory only. Prevents accidental edits to files outside the project scope. |
When this skill is loaded, you are RESTRICTED to editing files only within the current working directory and its subdirectories.
${CWD}/**Before every Edit or Write operation, verify the target file is under the current working directory. If it's not:
User says "unfreeze" or "disable freeze mode".
On-demand safety gate that blocks destructive commands. Activate with /learn careful when working on production systems or sensitive data.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Reference guide for writing Claude Code skills that agents actually follow. Uses 7 persuasion principles to maximize compliance.
Gate that blocks success claims without fresh evidence. Enforces run-the-command-show-the-output before marking work done.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.