Guidelines
akash-network/node
Behavioral guidelines to reduce common LLM coding mistakes. An agent skill from akash-network/node.
Make mechanical refactoring (file splits, function moves, module extractions, renames) machine-checkable instead of eyeballed.
Install Mechanical Refactor Verify
$ npx skills add sgl-project/sglang --skill mechanical-refactor-verify -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sgl-project/sglang mechanical-refactor-verify --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/mechanical-refactor-verify .claude/skills/mechanical-refactor-verify && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mechanical-refactor-verify" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/mechanical-refactor-verify into .claude/skills/mechanical-refactor-verify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mechanical-refactor-verify", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sgl-project/sglang/tree/main/.agents/skills/mechanical-refactor-verifyType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sgl-project/sglang --skill mechanical-refactor-verify -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sgl-project/sglang mechanical-refactor-verify --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/mechanical-refactor-verify .agents/skills/mechanical-refactor-verify && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mechanical-refactor-verify" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/mechanical-refactor-verify into .agents/skills/mechanical-refactor-verify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mechanical-refactor-verify", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sgl-project/sglang --skill mechanical-refactor-verify -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sgl-project/sglang mechanical-refactor-verify --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/mechanical-refactor-verify .cursor/skills/mechanical-refactor-verify && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mechanical-refactor-verify" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/mechanical-refactor-verify into .cursor/skills/mechanical-refactor-verify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mechanical-refactor-verify", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sgl-project/sglang.git --path .agents/skills/mechanical-refactor-verify--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sgl-project/sglang --skill mechanical-refactor-verify -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sgl-project/sglang mechanical-refactor-verify --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/mechanical-refactor-verify .gemini/skills/mechanical-refactor-verify && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mechanical-refactor-verify" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/mechanical-refactor-verify into .gemini/skills/mechanical-refactor-verify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mechanical-refactor-verify", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sgl-project/sglang mechanical-refactor-verifyInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sgl-project/sglang --skill mechanical-refactor-verify -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/mechanical-refactor-verify .github/skills/mechanical-refactor-verify && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mechanical-refactor-verify" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/mechanical-refactor-verify into .github/skills/mechanical-refactor-verify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mechanical-refactor-verify", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sgl-project/sglang --skill mechanical-refactor-verify -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sgl-project/sglang mechanical-refactor-verify --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sgl-project/sglang.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/mechanical-refactor-verify .opencode/skills/mechanical-refactor-verify && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mechanical-refactor-verify" agent skill from https://github.com/sgl-project/sglang/tree/main/.agents/skills/mechanical-refactor-verify into .opencode/skills/mechanical-refactor-verify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mechanical-refactor-verify", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
mechanical-refactor-verify- GitHub stars
- 37k
- Used in
- 2 other repos
- Token cost
- ~1.4k tokens
- SKILL.md length
- 586 words
- Files
- 42 (incl. scripts)
- Skills in repo
- 31
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Make mechanical refactoring (file splits, function moves, module extractions, renames) machine-checkable instead of eyeballed.
- Works in 3 steps: Overview → Commands — what do you want to do? → Files
- Reviewing such changes
- SKILL.md covers 1. Overview, 2. Commands — what do you want… and 3. Files
- Runs Python scripts from its folder
What it does
Mechanical Refactor Verify is an agent skill from sgl-project/sglang. 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.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 45 other files, including scripts (for example `guide-construct-proof.md`, `guide-modify-skill.md` and `guide-split.md`).
It sits in Development, covering Refactoring. The repository describes itself as: SGLang is a high-performance serving framework for large language models and multimodal models. The licence is Apache-2.0.
When your agent uses it
- Reviewing such changes
- Tasks that involve Refactoring
Example prompts
- “/mechanical-refactor-verify”
Requirements
- Python 3
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit b7b2975. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 12 files in scripts/ (Python, from the files we listed), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Mechanical Refactor Verify loads about 1.4k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 586 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from sgl-project/sglang at commit b7b2975, republished under its Apache-2.0 licence (© sgl-project). 586 words, ~1,408 tokens.
Download SKILL.mdSave it as
.claude/skills/mechanical-refactor-verify/SKILL.md (or your agent's skills folder). This skill also uses 41 other files; get the full folder from GitHub.- name
- mechanical-refactor-verify
- description
- 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.
- user_invocable
- true
- argument
- split <base>..<tip> | construct <base>..<tip> [--match REGEX] [--out DIR] | verify --base <base> --branch <branch> --proof <folder> [--jobs N] [--skip-passed]
Mechanical Refactor — Machine-Checkable Verification
1. Overview
- The correctness of a mechanical change (file split, function move, module extraction, rename) must be machine-checkable, not eyeballed — the proof is something anyone can re-run, whoever made the change and whenever.
- One property: a commit is a pure relocation. One proof: reproduce — regenerate the move from the base commit with faithful primitives, run the formatter, byte-diff against the target.
- Empty diff = the proof. Any residual = a bundled non-move change, surfaced for review.
- A reshape must not ride along: split into optional prepare + certified move +
optional postpare (
guide-split.md).
2. Commands — what do you want to do?
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-writtenReprowhen it reportsUNSUPPORTED).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 declaresmechanical_provableornon_mechanical_provable, runs every provable commit's proof (never a sample), and writes one full report; then audit the authored surfaces and theHUMAN_REVIEWrows. Re-running one commit's script is for diagnosis only.- Decide whether a change counts as a clean move →
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. - Change this skill itself (edit the engine, the generator, or the spec) →
guide-modify-skill.md: the spec-leads rule, the faithfulness invariant, and the testing bar a change must clear before it is trusted.
Show full SKILL.md (210 more words)Show less
3. Files
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-writtenRepro(§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 aPASS/RESIDUAL/UNSUPPORTEDverdict.scripts/mechanical_refactor_reproduction_utils.py— the proof engine: theReprobuilder'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 inbase..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.
© sgl-project, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 41 other files (scripts) in .agents/skills/mechanical-refactor-verify of sgl-project/sglang.
- SKILL.md
- guide-construct-proof.md
- guide-modify-skill.md
- guide-split.md
- guide-verify-proof.md
- scripts/mechanical_refactor_proof_generator.py
- scripts/mechanical_refactor_reproduction_cli.py
- scripts/mechanical_refactor_reproduction_utils.py
- scripts/tests/proof_generator/conftest.py
- scripts/tests/proof_generator/generator_testlib.py
- scripts/tests/proof_generator/test_infer_extract_functions.py
- scripts/tests/proof_generator/test_infer_extracts.py
- scripts/tests/proof_generator/test_infer_imports.py
- scripts/tests/proof_generator/test_infer_moves.py
- scripts/tests/proof_generator/test_main_single_commit.py
- scripts/tests/proof_generator/test_script_and_diff.py
- scripts/tests/reproduction_cli/cli_testlib.py
- … and 25 more
Open the folder on GitHubat commit b7b2975
Used in 2 other repositories
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in sgl-project/sglang, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Mechanical Refactor Verify next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mechanical Refactor Verify this skillsgl-project/sglang | 37k | 2 repos | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Guidelinesakash-network/node | 1.1k | 22 repos | ~577 | Automated safety check: Pass | MIT | |
| Component Refactoringlangflow-ai/langflow | 156k | — | ~3.5k | Automated safety check: Pass | MIT | |
| Migrate Core Code to Submodulestinyhumansai/openhuman | 42k | — | ~2.6k | Automated safety check: Pass | GPL-3.0 | |
| Systematic Code Refactoringluongnv89/claude-howto | 42k | — | ~3k | Automated safety check: Pass | MIT | |
| Codexskills-directory/skill-codex | 1.5k | 3 repos | ~1.8k | Automated safety check: Pass | MIT |
Similar skills
Component Refactoring
langflow-ai/langflow
Refactor high-complexity React components in Langflow frontend.
Migrate Core Code to Submodules
tinyhumansai/openhuman
Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.
Systematic Code Refactoring
luongnv89/claude-howto
Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.
Codex
skills-directory/skill-codex
A skill your agent uses when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
Ponytail
DavidObando/gsharp
Forces the laziest solution that actually works, simplest, shortest, most minimal.
More from sgl-project/sglang
All 31 skills in this repoSglang Prod Incident Triage
sgl-project/sglang
Replay-first debug flow for SGLang serving problems. An agent skill from sgl-project/sglang.
LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
Babysit PR To Pass CI
sgl-project/sglang
Start and persistently pursue a goal to babysit an SGLang pull request until selected GitHub Actions workflows pass on the latest PR head.
Compute Mamba Ratio
sgl-project/sglang
Compute the optimal --mamba-full-memory-ratio (or --max-mamba-cache-size pin) for a hybrid attention + linear-attention (Mamba / GDN / KDA) model's two serving memory pools, from the workload and…
Debug Distributed Hang
sgl-project/sglang
Debug hanging issues in SGLang distributed inference (TP/PP/DP/EP).
Env Var Conventions
sgl-project/sglang
Conventions for SGLang environment variables — where to define, how to access, how to name, and how to deprecate.
Related
Categories
Questions about Mechanical Refactor Verify
What does Mechanical Refactor Verify do?
Make mechanical refactoring (file splits, function moves, module extractions, renames) machine-checkable instead of eyeballed. Mechanical Refactor Verify is an agent skill from sgl-project/sglang. Make mechanical refactoring (file splits, function moves, module extractions, renames) machine-checkable instead of eyeballed.
When should I use Mechanical Refactor Verify?
Mechanical Refactor Verify fits situations like: reviewing such changes; tasks that involve Refactoring.
How do I install Mechanical Refactor Verify in Claude Code?
Run `npx skills add sgl-project/sglang --skill mechanical-refactor-verify -a claude-code`. Or copy the skill folder (.agents/skills/mechanical-refactor-verify in sgl-project/sglang) into .claude/skills/mechanical-refactor-verify in your project. Claude Code loads it when a task matches its description.
How do I install Mechanical Refactor Verify in Codex?
Run `npx skills add sgl-project/sglang --skill mechanical-refactor-verify -a codex`. Or copy the skill folder (.agents/skills/mechanical-refactor-verify in sgl-project/sglang) into .agents/skills/mechanical-refactor-verify in your project. Codex loads it when a task matches its description.
Can I use Mechanical Refactor Verify in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sgl-project/sglang --skill mechanical-refactor-verify -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mechanical-refactor-verify, .gemini/skills/mechanical-refactor-verify, .github/skills/mechanical-refactor-verify and .opencode/skills/mechanical-refactor-verify in your project.
What does Mechanical Refactor Verify need to run?
Going by SKILL.md and its folder, Mechanical Refactor Verify needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Mechanical Refactor Verify access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Mechanical Refactor Verify safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Mechanical Refactor Verify use?
Mechanical Refactor Verify is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Mechanical Refactor Verify use?
About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Mechanical Refactor Verify?
Skills that share tags, products or a category with Mechanical Refactor Verify: Guidelines (akash-network/node, 1.1k stars), Component Refactoring (langflow-ai/langflow, 156k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars) and Systematic Code Refactoring (luongnv89/claude-howto, 42k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mechanical Refactor Verify?
sgl-project (a GitHub organization) maintains it in sgl-project/sglang, which has 36,851 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 8, 2026.
Source: sgl-project/sglang on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.