Verify file splits, function moves, module extractions, and renames by reproducing changes from a base commit and comparing files byte for byte. Generate repeatable proof scripts and reports that expose changes beyond relocation.
中文简介正在准备中。当前显示英语简介。
Make mechanical refactoring (file splits, function moves, module extractions, renames) machine-checkable instead of eyeballed. Reproduce a relocation commit byte-for-byte from faithful primitives, and split an extraction into a verifiable prepare + move + postpare. Use when doing or reviewing such changes.
安装前可以查看交给 AI 代理的指令内容。
guide-split.md).The skill takes an argument naming one of three commands; invoked without one, pick the row matching your task.
split <base>..<tip> — author a compliant refactor branch: split it into commits,
satisfy the contract (extract, move, file split) → guide-split.md: §1 splits the PR
into classified pieces (the chain contract: classification format, correct labeling,
proofs PASS, non-mechanical commits correctness-reviewed); §2 splits one piece into
prepare + move + postpare (the case recipes and the anti-patterns). The argument is the
chain to author (or a single commit / a description of the change to split).construct <base>..<tip> [--match REGEX] [--out DIR] — construct the proof, for
the chain or one commit → guide-construct-proof.md: §1 generates + publishes the
whole chain's proof folder (the flags are the generator's:
scripts/mechanical_refactor_proof_generator.py <base>..<tip> --match REGEX --out DIR);
§2 proves a single commit — pass just <commit> (the generator, or a hand-written
Repro when it reports UNSUPPORTED).verify --base <base> --branch <branch> --proof <folder> [--jobs N] [--skip-passed]
— verify someone's proof: a whole chain / PR branch → guide-verify-proof.md: run the
chain verifier with exactly these flags
(scripts/mechanical_refactor_reproduction_cli.py) — it checks every commit declares
mechanical_provable or non_mechanical_provable, runs every provable commit's
proof (never a sample), and writes one full report; then audit the authored surfaces
and the HUMAN_REVIEW rows. Re-running one commit's script is for diagnosis only.spec-reproduction-utils.md: the
property, the whole whitelist / not-allowed list, and each primitive's contract. The
source of truth for the reproduction module; if any other file disagrees, it wins.guide-modify-skill.md: the spec-leads rule, the faithfulness invariant, and the testing
bar a change must clear before it is trusted.guide-split.md — split the PR into classified pieces (§1, the
chain contract) and each piece into prepare + move + postpare (§2: case recipes, what
stays mechanical, anti-patterns).guide-construct-proof.md — produce the proof: the whole
chain's proof folder + publishing (§1), and a single commit's proof — generator or
hand-written Repro (§2).guide-verify-proof.md — consume the proof: the whole-chain
verifier, single-commit re-runs, verdicts, and the audit checklist for authored
surfaces.spec-reproduction-utils.md — the normative spec of the
clean-move property and the reproduction primitives.spec-reproduction-cli.md — the normative spec of the
verified-chain property: the classification word rule, the proof obligation, the report,
and the exit codes.guide-modify-skill.md — change the engine, the generator, or
the spec: the spec-leads rule, the byte-faithfulness invariant, and the testing bar.scripts/mechanical_refactor_proof_generator.py —
the generator: infers a reproduce recipe from a commit's diff and emits/runs a
standalone, auditable script per commit, with a PASS / RESIDUAL / UNSUPPORTED verdict.scripts/mechanical_refactor_reproduction_utils.py — the
proof engine: the Repro builder's faithful relocation primitives plus the worktree +
pre-commit + byte-diff scaffold. Self-contained — only git and the standard library.scripts/mechanical_refactor_reproduction_cli.py — the
chain verifier: classifies every commit in base..branch, runs every provable
commit's proof from the proof folder, and emits the full chain report.scripts/tests/ — pytest suites, one folder per module:
reproduction_utils/ for the proof engine, proof_generator/ for the generator,
reproduction_cli/ for the chain verifier.还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Develop lightweight CUDA operations for SGLang using JIT, which compiles code on first use. A tensor-scaling example explains implementation conventions, input validation, memory access helpers, and when to choose this approach.
中文简介正在准备中。当前显示英语简介。
Add a CUDA/C++ GPU operation to sgl-kernel using AOT, meaning compilation before use. Follow the implementation through PyTorch registration, Python API exposure, SGLang integration, correctness tests, and benchmarks that account for cache reuse.
中文简介正在准备中。当前显示英语简介。
Monitor selected GitHub Actions checks on an SGLang pull request until they pass on its latest commit. Diagnose failures, push small validated fixes, and retry only failed jobs within defined limits.
中文简介正在准备中。当前显示英语简介。
Review existing tests and CI, the automated checks run during development, for redundant coverage, misplaced tests, and opportunities to reduce runtime or cost. Receive file-specific recommendations based on documented improvement patterns, with uncertain findings separated.
中文简介正在准备中。当前显示英语简介。
Understand and modify SGLang's CI pipelines, including test stage order, start conditions, early stopping after failures, and workload splitting. Use the guide to add jobs and investigate failed, skipped, or cancelled checks.
中文简介正在准备中。当前显示英语简介。
Collect and review SGLang startup logs to identify unnecessary output and trace its source. Get saved logs and specific cleanup proposals while preserving useful diagnostics, with runtime changes left for user approval.
中文简介正在准备中。当前显示英语简介。