菜单
Add multi-layer validation to fix bugs caused by invalid data. Use when debugging data corruption, invalid input reaching deep execution, "defense in depth", or when a bug needs structural prevention at every layer.
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
Generate protocol-compliant adapter stubs for Bucket 3 operations requiring external services. Use when the user requests "adapter stub", "dry run", "Bucket 3", "Linear ticket stub", "Kafka stub", or needs a fail-soft fallback for unavailable services.
Refine rough ideas into validated design docs through collaborative dialogue. Use when the user says "brainstorm", "help me design", "explore a feature", "let's think about", or has a vague idea that needs structure before coding.
Capture session context for seamless continuity. Use when the user says "handoff", "wrap up", "end session", "pass the baton", "save progress", or needs to preserve working state for the next session.
Adversarial code review that iterates to convergence. Use when the user says "hostile review", "adversarial review", "tear this apart", "find all issues", or needs a thorough skeptical review of code or design.
Convert analysis results or review findings into actionable implementation plans. Use when the user says "turn insights into a plan", "prioritize findings", "action items from review", or has unstructured observations that need to become executable tasks.
Classify PRs and produce a priority-ordered merge plan. Use when the user says "merge order", "which PR first", "merge plan", or has multiple PRs targeting the same branch that need sequencing.
| name | defense-in-depth |
| description | Add multi-layer validation to fix bugs caused by invalid data. Use when debugging data corruption, invalid input reaching deep execution, "defense in depth", or when a bug needs structural prevention at every layer. |
Use this skill when fixing a bug caused by invalid data reaching deep into execution. The goal is to add validation at every layer the data passes through, making the bug structurally impossible to reproduce.
A single validation point feels sufficient but can be bypassed by different code paths, refactoring, or mocks. This skill ensures that invalid data is caught at every layer, not just one.
Trace the data flow. Start from where the bad value originates and follow it through every function and module until the failure. List each checkpoint the data passes through.
Add Layer 1: Entry point validation. At the API boundary or public function where data enters, reject obviously invalid input. Check for: empty values, wrong types, missing required fields, and values outside valid ranges.
Add Layer 2: Business logic validation. Inside the core logic that consumes the data, verify it makes sense for the specific operation. This catches cases where entry validation passed but the value is semantically wrong for this context.
Add Layer 3: Environment guards. Add context-specific protections. For example: refuse destructive operations outside temp directories during tests, block production writes in development mode, or reject paths outside the workspace root.
Add Layer 4: Debug instrumentation. Add logging at the point closest to the failure with enough context for forensics: the invalid value, the call stack, and the current environment. This layer catches whatever the other three missed.
Test each layer independently. Write tests that bypass Layer 1 and verify Layer 2 catches the bad data. Write tests that bypass both and verify Layer 3 catches it. Confirm Layer 4 logs the right context.
For each bug fix:
