菜单
Use when implementing low-level or strict-constraint code (kernels, SIMD/intrinsics, alignment/padding rules, codegen/DSLs, strict ABI or hardware APIs), or when direct implementation repeatedly fails to compile/test.
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。
| name | staged-lowering |
| description | Use when implementing low-level or strict-constraint code (kernels, SIMD/intrinsics, alignment/padding rules, codegen/DSLs, strict ABI or hardware APIs), or when direct implementation repeatedly fails to compile/test. |
| metadata | {"short-description":"Staged lowering for constrained code"} |
Use this skill to implement constrained code reliably by reducing the problem before writing final code: define a small IR/DSL sketch, then translate it into production code in staged passes with verification after each pass.
Use this skill when:
Open references/staged-lowering.md and follow the template.
Write a Staged Lowering Plan:
Implement pass-by-pass:
Record a Per-pass Verification Log (commands + key results).
If runtime behavior changes, invoke $observability.
If you need help with comment/constant rules, invoke $code-readability.
Use when finishing a branch or PR after verification and review, including merge, PR publication, keep, discard, cleanup, local sync, and reporting merge or PR URLs with current git state.
Use when handling received code-review feedback on a PR or diff, including requested changes, inline comments, approvals, non-blocking notes, and disputed suggestions. Separates accepted fixes, refutations, deferrals, clarification needs, and merge handoff.
Use when preparing a focused code-review request for a PR or diff after implementation evidence exists, especially to package scope, reviewer focus, PR URL, verification, known risks, and deferred work without deciding final submit readiness.
Use before every submission to decide whether required checks, artifacts, and branch evidence are complete enough to submit.
Use when work is complex, long-running, multi-step, cross-boundary, likely to span multiple PRs/sessions, or needs handoff-ready planning under plans/.
Use when adding or changing Agent-facing workflows, generated prompts, collect plans, executable handoff artifacts, CLI workflows, controller/target-local workflow chains, or validation artifacts consumed by downstream reports. Do not use for ordinary code changes without an Agent-facing workflow or generated instruction surface.
