Mechanical Refactor Verify
sgl-project/sglang
Make mechanical refactoring (file splits, function moves, module extractions, renames) machine-checkable instead of eyeballed.
针对用户提供的现象，用「看反常—追过程—分解释—带条件迁移」生成机制猜想，并联网核对现象、检验关键因果与竞争解释，交付证据最能支撑的机制及其边界。USE WHEN 用户调用 ljg-mechanism、说「找机制」「机制研究」「用四步框架走一遍」「联网验证这个解释」，或希望研究一个现象怎样发生。NOT FOR 纯概念定义、普通摘要、已有唯一解的操作题或只画地图。
MITAuto-check passed
Install Ljg Mechanism
$ npx skills add lijigang/ljg-skills --skill ljg-mechanism -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lijigang/ljg-skills ljg-mechanism --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/lijigang/ljg-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ljg-mechanism .claude/skills/ljg-mechanism && 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 "ljg-mechanism" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-mechanism into .claude/skills/ljg-mechanism/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-mechanism", 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/lijigang/ljg-skills/tree/master/skills/ljg-mechanismType 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 lijigang/ljg-skills --skill ljg-mechanism -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lijigang/ljg-skills ljg-mechanism --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ljg-mechanism .agents/skills/ljg-mechanism && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ljg-mechanism" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-mechanism into .agents/skills/ljg-mechanism/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-mechanism", 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 lijigang/ljg-skills --skill ljg-mechanism -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lijigang/ljg-skills ljg-mechanism --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ljg-mechanism .cursor/skills/ljg-mechanism && 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 "ljg-mechanism" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-mechanism into .cursor/skills/ljg-mechanism/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-mechanism", 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/lijigang/ljg-skills.git --path skills/ljg-mechanism--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 lijigang/ljg-skills --skill ljg-mechanism -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lijigang/ljg-skills ljg-mechanism --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ljg-mechanism .gemini/skills/ljg-mechanism && 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 "ljg-mechanism" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-mechanism into .gemini/skills/ljg-mechanism/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-mechanism", 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 lijigang/ljg-skills ljg-mechanismInstalls 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 lijigang/ljg-skills --skill ljg-mechanism -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ljg-mechanism .github/skills/ljg-mechanism && 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 "ljg-mechanism" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-mechanism into .github/skills/ljg-mechanism/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-mechanism", 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 lijigang/ljg-skills --skill ljg-mechanism -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lijigang/ljg-skills ljg-mechanism --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ljg-mechanism .opencode/skills/ljg-mechanism && 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 "ljg-mechanism" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-mechanism into .opencode/skills/ljg-mechanism/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-mechanism", 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
ljg-mechanism- GitHub stars
- 7.5k
- Token cost
- ~498 tokens
- SKILL.md length
- 42 words
- Files
- 3
- Skills in repo
- 26
- Repo updated
- First seen
- Licence
- MIT
At a glance
针对用户提供的现象，用「看反常—追过程—分解释—带条件迁移」生成机制猜想，并联网核对现象、检验关键因果与竞争解释，交付证据最能支撑的机制及其边界。USE WHEN 用户调用 ljg-mechanism、说「找机制」「机制研究」「用四步框架走一遍」「联网验证这个解释」，或希望研究一个现象怎样发生。NOT FOR 纯概念定义、普通摘要、已有唯一解的操作题或只画地图。
- 用户调用 ljg-mechanism、说「找机制」「机制研究」「用四步框架走一遍」「联网验证这个解释」，或希望研究一个现象怎样发生。NOT FOR 纯概念定义、普通摘要、已有唯一解的操作题或只画地图
- SKILL.md covers Workflow Routing, 研究约定, 成品 and Gotchas, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Ljg Mechanism is an agent skill from lijigang/ljg-skills. 针对用户提供的现象，用「看反常—追过程—分解释—带条件迁移」生成机制猜想，并联网核对现象、检验关键因果与竞争解释，交付证据最能支撑的机制及其边界。USE WHEN 用户调用 ljg-mechanism、说「找机制」「机制研究」「用四步框架走一遍」「联网验证这个解释」，或希望研究一个现象怎样发生。NOT FOR 纯概念定义、普通摘要、已有唯一解的操作题或只画地图。
Its SKILL.md is about 500 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `Workflows/DiscoverMechanism.md` and `agents/openai.yaml`).
The licence is MIT.
When your agent uses it
- 用户调用 ljg-mechanism、说「找机制」「机制研究」「用四步框架走一遍」「联网验证这个解释」，或希望研究一个现象怎样发生。NOT FOR 纯概念定义、普通摘要、已有唯一解的操作题或只画地图
Example prompts
- “/ljg-mechanism”
What it can do on your machine
Read from SKILL.md and the folder at commit 9e75497. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Ljg Mechanism loads about 498 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 42 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from lijigang/ljg-skills at commit 9e75497, republished under its MIT licence (© lijigang). 42 words, ~498 tokens.
Download SKILL.mdSave it as
.claude/skills/ljg-mechanism/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- ljg-mechanism
- description
- 针对用户提供的现象，用「看反常—追过程—分解释—带条件迁移」生成机制猜想，并联网核对现象、检验关键因果与竞争解释，交付证据最能支撑的机制及其边界。USE WHEN 用户调用 ljg-mechanism、说「找机制」「机制研究」「用四步框架走一遍」「联网验证这个解释」，或希望研究一个现象怎样发生。NOT FOR 纯概念定义、普通摘要、已有唯一解的操作题或只画地图。
- metadata.version
- 1.0.0
ljg-mechanism · 机制研究
从眼前的现象中找出真正起作用的关系。生成解释后，让它与竞争解释一起接受现实检验；根据证据修正对象、关系或成立条件，给出当前最扎实的机制判断。
「solid」指关键关系有可检查的依据、能够区分竞争解释、能推出新观察，并留下修改自己的入口。完整、流畅或引用很多，均不足以达到这个标准；公开证据不足时，交付领先猜想和具体缺口。
Workflow Routing
| 请求 | 执行 |
|---|---|
| 提供现象，希望解释其生成过程并验证 | 阅读 Workflows/DiscoverMechanism.md |
| 希望示范、学习或「走一遍」 | 使用同一研究框架，在成品中展开四个环节与判断变化 |
| 补充新事实、反例或改变范围 | 回到受影响的观察或因果关系，更新判断，不从头重复无关部分 |
研究约定
- 原始现象也需要核对。保留有价值的观察，明确对象、指标、比较基准和时段；「大家」「越来越」「没有效果」等概括不能直接当全称事实。
- 机制说清「谁或什么，在什么条件下，通过哪些中间变化，生成什么结果」。「供求」「激励」「文化」「系统」等名称须展开到可观察的过程。
- 保留能争夺同一解释对象的竞争解释，写出它们会产生的不同观察。方向不同、时间不同、影响的人不同，也可以形成区别性预测。
- 默认使用当前可用的联网搜索与正文获取能力，检验现象和机制。来源支持的范围，与自己的推断、教学设例和未知分开。
- 新材料可以推翻、重写或收窄机制。声明后的反例不能靠不断追加例外消解；需要说明原预测为何失败、新关系会推出什么不同结果。
成品
默认中文，直接在对话中交付。先给机制判断与证据强度，再以具体对象讲清过程，展示最能改变判断的竞争解释、证据与边界。四步是研究框架，不要求把全部检索过程或思考过程打印出来。
涉及关键因果时，把来源链接放在对应判断旁边；说明来源实际支持的是现象、机制环节还是因果关系。正文应让读者看见：当前相信什么、为什么、什么观察会使它改口，以及换个现场时必须保留哪些条件。
用户要求完整示范时，按「看反常 / 追过程 / 分解释 / 带条件迁移」展开。比较确有帮助时用短表，承重关系难以看清时用简图；不给每个简单问题硬加图、公式或固定数量的假说。
研究默认只读，不自动创建笔记、报告文件、日志、规则或记忆。用户另行要求保存时，遵循指定位置与格式。联网不可用或用户要求离线时，说明只完成了推演，不能声称已联网验证。
Gotchas
- 反常既包括「预期条件缺失，结果却出现」，也包括「条件已出现，预期结果没有出现」。普通现象也可以通过重新追问其生成过程成为研究对象。
- 产能、产出、合格交付、成交、收入、利润与单位时间回报是不同指标；平均变化、个体变化和群体构成变化也要分开。
- 一个来源证明现象发生，不自动证明候选机制成立。把同一论文的多次转述计作多个独立证据，会夸大支持。
- 没找到反例不等于通过验证；未显著不等于无效；缺少区分证据时可以同时保留多条解释。
- 跨域类比可生成猜想，不能代替当前领域的证据。迁移时既要保留关系，也要检查关键条件与失配处。
- 一个反例是否改变总体判断，取决于原来的命题口径。不能用一个赢家否定平均停滞，也不能用平均停滞否定个体获益。
Examples
/ljg-mechanism AI 让创作容易了，为什么收入没有同步增长？：拆开产能、交付、成交、价格与净收益，比较需求瓶颈、竞争替代和中间环节提速等候选解释，再检索能区分它们的材料；不预设所有领域都由同一机制主导。没人统一指挥，为什么群里的问题仍能找到回答者？走一遍这个框架。：对照成员自行认领与少数人集中撮合，找出关键参与者缺席时的不同预测；缺少该群的过程证据时，保留为待检验解释。网上都说某项技术没有实际效果，帮我找机制并验证。：先核对「效果」的指标、时期和适用群体；原始概括不成立时，改写研究问题，再解释哪些环节改善、哪些环节仍然卡住。
© lijigang, MIT. 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 2 other files in skills/ljg-mechanism of lijigang/ljg-skills.
- SKILL.md
- Workflows/DiscoverMechanism.md
- agents/openai.yaml
Open the folder on GitHubat commit 9e75497
Compare with similar skills
Ljg Mechanism 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 |
|---|---|---|---|---|---|---|
| Ljg Mechanism this skilllijigang/ljg-skills | 7.5k | — | ~498 | Automated safety check: Pass | MIT | |
| Mechanical Refactor Verifysgl-project/sglang | 37k | 2 repos | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Analyzing Persistence Mechanisms In Linuxmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~801 | Automated safety check: Notes | Apache-2.0 | |
| Hunting For Persistence Mechanisms In Windowsmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Detecting T1548 Abuse Elevation Control Mechanismmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.5k | Automated safety check: Notes | Apache-2.0 | |
| Cfe Mechanismbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~681 | Automated safety check: Pass | MIT |
Similar skills
Analyzing Persistence Mechanisms In Linux
mukul975/Anthropic-Cybersecurity-Skills
Scan Linux systems for persistence mechanisms including crontab/systemd entries, LDPRELOAD injection, shell profile modifications (.bashrc, .profile), and SSH authorizedkeys backdoors, then…
Hunting For Persistence Mechanisms In Windows
mukul975/Anthropic-Cybersecurity-Skills
Systematically hunts for adversary persistence mechanisms across Windows endpoints, covering registry Run/RunOnce keys, services, startup folders, scheduled tasks, and WMI event subscriptions.
Detecting T1548 Abuse Elevation Control Mechanism
mukul975/Anthropic-Cybersecurity-Skills
Detect abuse of elevation control mechanisms (T1548), including Windows UAC bypass via auto-elevating binaries like fodhelper.exe and Linux sudo/setuid/setgid exploitation, by monitoring registry…
Cfe Mechanism
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when designing or writing mechanism analyses for a Journal-of-Finance-and-Economics (《财经研究》) empirical manuscript — mechanism tests are near-mandatory for the journal's…
Analyzing Ransomware Encryption Mechanisms
mukul975/Anthropic-Cybersecurity-Skills
Analyzes encryption algorithms, key management, and file encryption routines used by ransomware families to assess decryption feasibility, identify implementation weaknesses, and support recovery…
More from lijigang/ljg-skills
All 26 skills in this repoWhole-Book Explainer Notes
lijigang/ljg-skills
Explains a whole book to someone who has not read it, keeping its specific content and showing how its threads connect, and saves the result as an Org note.
Ljg Paper
lijigang/ljg-skills
Explain research papers to readers without a specialist background: what the paper studies, what the authors contribute, how the findings follow, and what the evidence does not establish.
Text to PNG Card Caster
lijigang/ljg-skills
Turns text, URLs or local files into tall PNG cards through HTML typography, with four modes: long reading card, full-text layout, comic and whiteboard.
Classical Chinese Text Annotator
lijigang/ljg-skills
Turns a named classical Chinese chapter, such as one from the Tao Te Ching or the Analects, into a single annotated PNG image with notes and commentary.
Constraint Engine
lijigang/ljg-skills
Finds the handful of constraints that truly define a domain, role, product or debate, grades each by hardness, and explains the behavior those constraints produce.
Offline HTML Talk Decks
lijigang/ljg-skills
Builds single-file offline HTML talk decks from Org or Markdown outlines, with faithful layout or editorial condensing and keyboard navigation.
Questions about Ljg Mechanism
What does Ljg Mechanism do?
针对用户提供的现象，用「看反常—追过程—分解释—带条件迁移」生成机制猜想，并联网核对现象、检验关键因果与竞争解释，交付证据最能支撑的机制及其边界。USE WHEN 用户调用 ljg-mechanism、说「找机制」「机制研究」「用四步框架走一遍」「联网验证这个解释」，或希望研究一个现象怎样发生。NOT FOR 纯概念定义、普通摘要、已有唯一解的操作题或只画地图。. Ljg Mechanism is an agent skill from lijigang/ljg-skills.
When should I use Ljg Mechanism?
Ljg Mechanism fits situations like: 用户调用 ljg-mechanism、说「找机制」「机制研究」「用四步框架走一遍」「联网验证这个解释」，或希望研究一个现象怎样发生。NOT FOR 纯概念定义、普通摘要、已有唯一解的操作题或只画地图.
How do I install Ljg Mechanism in Claude Code?
Run `npx skills add lijigang/ljg-skills --skill ljg-mechanism -a claude-code`. Or copy the skill folder (skills/ljg-mechanism in lijigang/ljg-skills) into .claude/skills/ljg-mechanism in your project. Claude Code loads it when a task matches its description.
How do I install Ljg Mechanism in Codex?
Run `npx skills add lijigang/ljg-skills --skill ljg-mechanism -a codex`. Or copy the skill folder (skills/ljg-mechanism in lijigang/ljg-skills) into .agents/skills/ljg-mechanism in your project. Codex loads it when a task matches its description.
Can I use Ljg Mechanism 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 lijigang/ljg-skills --skill ljg-mechanism -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ljg-mechanism, .gemini/skills/ljg-mechanism, .github/skills/ljg-mechanism and .opencode/skills/ljg-mechanism in your project.
What does Ljg Mechanism need to run?
SKILL.md names no scripts, command-line tools or credentials: Ljg Mechanism is instructions for the agent only.
Does Ljg Mechanism 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 Ljg Mechanism 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. Review the folder before installing.
What licence does Ljg Mechanism use?
Ljg Mechanism is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Ljg Mechanism use?
About 498 tokens (SKILL.md is roughly 2k 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 Ljg Mechanism?
Skills that share tags, products or a category with Ljg Mechanism: Mechanical Refactor Verify (sgl-project/sglang, 37k stars), Analyzing Persistence Mechanisms In Linux (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Hunting For Persistence Mechanisms In Windows (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Detecting T1548 Abuse Elevation Control Mechanism (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ljg Mechanism?
lijigang (a GitHub user) maintains it in lijigang/ljg-skills, which has 7,481 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 8, 2026.
Source: lijigang/ljg-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.