菜单
Audit all unsafe blocks in moon for soundness, missing SAFETY comments, and potential UB. Run after touching storage, io, or runtime code.
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。
ADD (AI-Driven Development) — a minimal, state-tracked workflow for building software where the AI writes the code and the human owns direction and verification. Drives every feature through one lean TASK.md: Specify → Scenarios → Contract → Tests → Build → Verify → Observe, with red/green TDD built in. Use this skill whenever working in a repo that has a `.add/` directory, when the user says "add", "start a task", "next phase", "specify this feature", "ADD method", or "AI-driven development", or when scaffolding a new feature and you want spec/tests-first discipline instead of vague-prompt coding. Also use it to resume work across sessions (it reads `.add/state.json` so you never re-read the whole repo).
Scaffold a new Redis command implementation with dispatch entry, handler, ACL, tests, and consistency test entry. Args: COMMAND_NAME [category].
Scan hot-path code for allocation violations, lock misuse, and performance anti-patterns. Zero-tolerance audit.
Scaffold a new CUDA kernel with Rust integration via cudarc. Args: kernel_name [f32|f16]. Creates .cu kernel, Rust wrapper, CPU fallback, and benchmark.
Verify code compiles and tests pass under both runtime-tokio and runtime-monoio feature sets. Run before committing runtime-adjacent changes.
Benchmark GPU-accelerated operations (vector distance, batch computation) against CPU baselines. Requires CUDA toolkit. Args: vector|distance|batch|all.
基于 SOC 职业分类
| name | unsafe-audit |
| description | Audit all unsafe blocks in moon for soundness, missing SAFETY comments, and potential UB. Run after touching storage, io, or runtime code. |
Comprehensive unsafe code audit for the moon codebase.
Find all unsafe blocks:
grep -rn 'unsafe' src/ --include='*.rs'
For each unsafe block, verify:
// SAFETY: comment is present and accurateHighlight any NEW unsafe blocks vs main:
git diff main -- '*.rs' | grep '+.*unsafe'
Output severity-ranked report with [SOUND/UNSOUND/NEEDS_REVIEW] per block.
src/storage/dashtable/segment.rs (30 occurrences)src/storage/compact_value.rs (18)src/io/uring_driver.rs (9)src/runtime/channel.rs (8)src/storage/compact_key.rs (7)src/storage/dashtable/simd.rs (6)src/shard/uring_handler.rs (7)