Minimizing Ty Ecosystem Changes
astral-sh/ruff
A skill your agent uses when a user says "minimize this ty ecosystem change", "reproduce this ecosystem result", "investigate a primer difference", "investigate a mypyprimer difference"…
Skill 创建预检、可靠性验收与格式审查工具。本技能应在用户创建、重大改造或审查Skill,需要识别旧版 Skill 的指令遵循不稳定、产出漂移、验证模态错配、约束漏检,或检查 Harness 契约、候选绑定证据、故障注入、目录结构、业务流和安全风险时使用。不要用于:代替业务领域验证器、代码审查、应用功能测试、通用编程任务。
$ npx skills add cat-xierluo/legal-skills --skill skill-lint -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cat-xierluo/legal-skills skill-lint --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/cat-xierluo/legal-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-lint .claude/skills/skill-lint && 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 "skill-lint" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/skill-lint into .claude/skills/skill-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lint", 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/cat-xierluo/legal-skills/tree/main/skills/skill-lintType 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 cat-xierluo/legal-skills --skill skill-lint -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cat-xierluo/legal-skills skill-lint --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skill-lint .agents/skills/skill-lint && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-lint" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/skill-lint into .agents/skills/skill-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lint", 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 cat-xierluo/legal-skills --skill skill-lint -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cat-xierluo/legal-skills skill-lint --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skill-lint .cursor/skills/skill-lint && 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 "skill-lint" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/skill-lint into .cursor/skills/skill-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lint", 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/cat-xierluo/legal-skills.git --path skills/skill-lint--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 cat-xierluo/legal-skills --skill skill-lint -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cat-xierluo/legal-skills skill-lint --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skill-lint .gemini/skills/skill-lint && 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 "skill-lint" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/skill-lint into .gemini/skills/skill-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lint", 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 cat-xierluo/legal-skills skill-lintInstalls 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 cat-xierluo/legal-skills --skill skill-lint -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skill-lint .github/skills/skill-lint && 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 "skill-lint" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/skill-lint into .github/skills/skill-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lint", 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 cat-xierluo/legal-skills --skill skill-lint -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cat-xierluo/legal-skills skill-lint --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skill-lint .opencode/skills/skill-lint && 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 "skill-lint" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/skill-lint into .opencode/skills/skill-lint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lint", 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.
skill-lintSkill 创建预检、可靠性验收与格式审查工具。本技能应在用户创建、重大改造或审查Skill,需要识别旧版 Skill 的指令遵循不稳定、产出漂移、验证模态错配、约束漏检,或检查 Harness 契约、候选绑定证据、故障注入、目录结构、业务流和安全风险时使用。不要用于:代替业务领域验证器、代码审查、应用功能测试、通用编程任务。
Skill Lint is an agent skill from cat-xierluo/legal-skills. Skill 创建预检、可靠性验收与格式审查工具。本技能应在用户创建、重大改造或审查Skill,需要识别旧版 Skill 的指令遵循不稳定、产出漂移、验证模态错配、约束漏检,或检查 Harness 契约、候选绑定证据、故障注入、目录结构、业务流和安全风险时使用。不要用于:代替业务领域验证器、代码审查、应用功能测试、通用编程任务。
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 38 other files, including scripts and reference files (for example `CHANGELOG.md`, `config/instruction-stability-contract.example.json` and `config/instruction-stability-held-out-cases.example.json`).
It sits in Development, covering Linting and formatting. The licence is MIT.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit db2c58c. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Skill Lint loads about 2.9k tokens when it runs, and up to ~39k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 553 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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
如果在 Skill 单元内出现 `.env`、真实密钥、`__pycache__/`、`docs/`、`test/` 等发布版不应包含的内容,按严重程度记录。仓库根目录的 README、docs、LICENSE、CHANGELOG 可以是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.
The full file from cat-xierluo/legal-skills at commit db2c58c, republished under its MIT licence (© cat-xierluo). 553 words, ~2,930 tokens.
.claude/skills/skill-lint/SKILL.md (or your agent's skills folder). This skill also uses 35 other files; get the full folder from GitHub.本技能负责 Skill 创建前设计预检和创建后质量验收:审查一个 Skill 是否结构合规、文档一致、可发布、可评估、安全风险可控,判断它是否真实承载业务流程,并检查“完成”结论是否由候选绑定证据和多轮真实产物支撑。
本技能不代替主要创建者或领域验证器。创建或大改 Skill 时,用它先审查 Harness 设计,再由创建工具实现,完成后回到本技能做候选绑定验收。
审查时至少需要:
可选输入:
config/review-profile.local.yaml如需配置个人或项目的发布元数据策略,先复制 config/review-profile.example.yaml 为 config/review-profile.local.yaml,再填入本地值。个人偏好只作为本地上下文使用,不写入公开文件,不复制到审查报告中,除非用户明确要求公开。
references/harness-reliability-standards.md,产出七层 Harness 设计、Hard Fail 和至少一个逃逸反例;不要直接扩大提示词。NOT_VERIFIED,不得称功能已验收。references/instruction-stability-standards.md 并运行静态 assess;缺少约束追踪合同或多轮证据时标记 NOT_VERIFIED,不得用一次成功执行推断稳定。NOT_VERIFIED,除非用户明确授权并使用隔离环境。创建预检完成后,由用户指定的创建工具或实现者落地;本技能在实现完成后重新进入正式验收。这样既把可靠性理念前移,又不让审查器与生产器混成同一责任。
先读取 references/repository-skill-discovery-standards.md,判断输入目标是哪一类:
SKILL.mdSKILL.md 单元,但存在带 name / description frontmatter 的 Markdown 或 README 索引不要只因为仓库根目录缺少 SKILL.md 就判定整个仓库不合格。根目录缺少 SKILL.md 只有在用户明确指定根目录就是单个 Skill,或仓库声明自己是一个可加载 Skill 根目录时,才按严重问题处理。
发现候选单元后,先列出:
SKILL.mdname / description frontmatter,或 README 明确称为 skill如果候选单元很多,先按用户指定范围审查;用户未指定时,优先审查已确认 Skill 单元,并抽样检查 Skill-like 文档,报告中说明抽样范围。
对每个已确认或被选中的候选单元列出文件,并重点检查:
SKILL.mdCHANGELOG.mdLICENSE.txtconfig/*.example.*references/*.mdscripts/*assets/*templates/*archive/.gitkeep如果在 Skill 单元内出现 .env、真实密钥、__pycache__/、docs/、test/ 等发布版不应包含的内容,按严重程度记录。仓库根目录的 README、docs、LICENSE、CHANGELOG 可以是 monorepo 治理文件,不按单个 Skill 目录结构误判。
先读取 references/skill-standards.md 作为审查索引,再按问题类型读取对应模块。不要一次性把所有细则混在一份报告逻辑中。
默认模块:
repository-skill-discovery-standards.md:仓库类型、monorepo、最小 Skill 单元和候选文档发现structure-standards.md:目录结构、文件可达性、references 命名frontmatter-metadata-policy.md:通用字段与发布字段分层trigger-description-standards.md:name 与 description 触发边界configuration-privacy-standards.md:配置模板、本地配置隔离、公开内容去具体化security-assessment-standards.md:危险执行、敏感访问、数据外传、凭证、依赖、MCP 和提示词安全publishing-standards.md:LICENSE、CHANGELOG、version、README / marketplace 同步workflow-output-standards.md:SKILL.md 正文、依赖、脚本、输出和可编排性business-flow-rubric.md:业务流深度、Hard Fail 和可评估性基础harness-reliability-standards.md:七层 Harness、独立验证、候选绑定证据、故障注入和闭环instruction-stability-standards.md:约束追踪、验证模态、产物阶段、多轮覆盖和漂移判定reporting-standards.md:问题分级和报告结构LICENSE.txt、version、README 和 Marketplace 属于发布治理,不属于普通目录结构硬要求。审查私人或第三方普通 Skill 时,只有在用户给出发布目标或项目规则时才按发布模块判定。
读取 references/security-assessment-standards.md,对纳入审查的 Skill 单元做安全风险评估。
先运行确定性静态安全扫描(对应 NVIDIA SkillSpector 的漏洞模式):
# 单个 Skill
python3 scripts/security_scan.py audit --candidate-root /path/to/skill
# Skill 集合 / monorepo(递归发现所有含 SKILL.md 的最小单元)
python3 scripts/security_scan.py batch --root /path/to/skills
# 联网查询 OSV 已知漏洞(默认离线只做版本 pin 检查)
python3 scripts/security_scan.py audit --candidate-root /path/to/skill --online扫描器输出含文件、行号、能力信号、严重级、置信度与修正建议的结构化 JSON;存在 critical/high finding 时退出码 1(FAIL),未发现 SKILL.md 时退出码 2。覆盖:危险执行(subprocess/os.system/eval/exec/动态导入)、网络外传、环境变量/敏感文件访问、运行时自动安装、未固定依赖与已知 CVE、硬编码凭证、提示注入、污点流(env/argv/input → subprocess)、文件系统枚举、隐藏 Unicode 字符、MCP 通配权限,以及"能力存在但文档未披露/未声明权限"(Missing User Warnings / MCP Least Privilege / Context-Inappropriate Capability)与文档级 scope creep(commit 技能引导发布/改 allowlist 等未披露的高风险动作)。
重点检查:
SKILL.md 和 references 是否含提示注入、绕过安全限制、隐藏执行、敏感数据收集或欺骗性描述安全评估不等同于完整渗透测试。对扫描器命中项要结合上下文判断误报;但涉及凭证泄露、下载并执行、权限提升、持久化、无确认数据外传、隐藏提示词指令等问题时,默认按严重问题处理。
使用 references/business-flow-rubric.md 检查:
默认采用中等严格度:Hard Fail 是硬指标,五层评估对象是软指标。
创建预检、重大改造和正式验收必须读取 references/harness-reliability-standards.md,逐层检查 Contract / Producer / Verifier / Evidence Binding / Fault Injection / Closure / Composition。旧版、多维审阅、视觉生产或用户反馈“反复漏项/产出漂移”时还必须读取 references/instruction-stability-standards.md。
先运行不执行候选代码的具体失效审查。单 Skill:
python3 scripts/harness_failure_audit.py audit \
--candidate-root /path/to/skillSkill 集合或 monorepo:
python3 scripts/harness_failure_audit.py batch \
--root /path/to/skills该审查器递归发现包含 SKILL.md 的最小单元,输出带文件、行号、证据、影响和修正建议的稳定 JSON;hard finding 返回 1,范围错误或集合中零 Skill 返回 2。规则 ID 与边界见 references/harness-reliability-standards.md。默认只做静态审查,不执行、安装或联网。
旧版结构性稳定性审查:
python3 scripts/instruction_stability_gate.py assess \
--candidate-root /path/to/skill缺少 config/instruction-stability-contract.json 时,assess 返回退出码 2 和 INSTRUCTION_STABILITY_NOT_VERIFIED,同时给出 ISG 结构性 finding 与 HFA/HRA 具体实现 finding。视觉/几何语义只从 SKILL.md 和 references/**/*.md 的规范性上下文识别,TASKS/DECISIONS/CHANGELOG 的历史讨论不触发视觉模态。此模式不执行候选代码,适合旧版和未知第三方 Skill。
ISG-002 会列出触发视觉/几何要求的规范来源和行号,但它只证明候选缺少合适模态的领域验证证据。不要据此声称已经检测出重叠、裁切或其他具体业务错误;应让目标 Skill 提供自己的 checker、最小违规反例与合法近似正例,再由正式门禁复算。
声称“指令遵循稳定”“多轮不漏项”前,目标 Skill 必须提供约束追踪合同。每条 hard constraint 在权威来源中使用唯一 <!-- skill-lint:constraint CONSTRAINT-ID --> 锚点;候选外 evaluator-signed 基线必须与全部锚点、规范行、合同和当前候选哈希一致。先取得当前候选可复算的 Harness 审查证据,再用相同输入/配置至少独立执行三轮;每轮保留唯一 execution nonce、evaluator-signed producer log 和独立目录内的真实产物。每条硬约束还必须有候选外 evaluator-signed held-out 正反例。完成静态安全审查、披露 checker 且用户确认候选为自有/可信代码后,运行:
python3 scripts/instruction_stability_gate.py verify \
--candidate-root /path/to/skill \
--evaluator-public-key /path/to/review/evaluator-public.pem \
--requirements-baseline /path/to/review/requirements-baseline.json \
--harness-evidence /path/to/review/harness-review.json \
--held-out-cases /path/to/review/held-out-cases.json \
--held-out-root /path/to/review/held-out \
--run-evidence /path/to/review/runs.json \
--runs-root /path/to/review/runs \
--receipt /path/to/review/instruction-stability-receipt-draft.json \
--confirm-trusted-candidate该门禁固定使用当前受信 skill-lint 复算 HARNESS_REVIEW_VERIFIED,再逐轮重跑 active checker。它要求每条硬约束精确映射到显式来源锚点、自动发现并签名枚举的 requirements sources/exclusions、checker、正确验证模态、正确产物阶段、带类型/条件/阈值的 measurement、签名 hidden 正反例和已知历史回归;合同漏列规范行、签名无效、三轮复用路径、旧候选/旧 producer 日志重放、负向用例因其他约束失败、少报一个 constraint id、checker 修改产物或关键 observable 漂移都会阻塞。公开、隐藏和真实运行产物统一使用同类随机暂存路径,避免 checker 按样本类别分支。
verify 只生成 INSTRUCTION_STABILITY_EVIDENCE_READY 草稿。evaluator 必须在不执行候选代码的隔离环境用 Ed25519 私钥运行 sign-evidence --private-key ...,再用只持有候选外公钥的 verify-receipt 复验全部绑定;只有后一步输出 INSTRUCTION_STABILITY_VERIFIED 才能声明稳定。私钥不得出现在 producer/checker 的进程树、环境或可读工作区,完整命令见 references/instruction-stability-standards.md。
客观 Hard Fail 一律阻塞。正式验收应先用 scripts/harness_evidence_gate.py snapshot 固化候选与规则读集,填写候选内 checker、参数、超时和故障用例的预期失败码。完成静态安全审查并取得用户对自有/可信候选的确认后,再用 verify --confirm-trusted-candidate 亲自重跑。JSON 中不得填写或采信自报退出码、PASS 和日志。只有退出码为 0 且出现 HARNESS_REVIEW_VERIFIED,才能说“当前候选的 Harness 审查证据已验证”。该标记不替代目标 Skill 自己的 DOMAIN_VERIFIED,门禁也不是第三方代码沙箱。
完成标记不可互相替代:
HARNESS_REVIEW_VERIFIED:当前候选、规则、checker 和故障用例证据有效。INSTRUCTION_STABILITY_EVIDENCE_READY:动态复算已完成,但草稿尚未离线签名与验签,不能作为完成标记。INSTRUCTION_STABILITY_VERIFIED:evaluator Ed25519 签名回执已复验,外部硬约束基线/held-out、当前 Harness evidence、候选/producer 绑定和至少三轮真实产物逐约束通过,measurement/observable 未漂移。DOMAIN_VERIFIED:领域验证器确认具体业务产物正确。只要 Skill 声称“稳定完成”,就必须同时满足前两项;若还声称业务结果正确,再加第三项。未运行的层一律写 NOT_VERIFIED。
确认 Skill 是否具备后续 eval 的基础:
缺少这些内容不一定阻塞发布,但应作为质量风险记录。
审查报告应优先列出问题,再给摘要。严重问题必须具体到文件和位置。
如用户需要最终交付件、发布前意见或正式质量结论,使用 templates/skill-quality-opinion-report.md 生成“Skill 质量意见报告”,报告中必须写明问题、影响、修正方式和复查标准。
对承载设计原理的结构性建议(拆解披露、触发边界、上下文聚焦、自由度匹配、可机判验收等),在 finding 的「设计理念」字段一句话讲清背后写作原理,可回查对应 standards 文件的「设计理念」小节,使报告同时具备 skill 写作教学价值;纯事实问题(文件缺失、引用断裂、命名大小写)可省。稳定性 finding 必须具体指出漏的是哪条 constraint、验证模态、产物阶段、case 或 run,不使用“遵循不稳定”这类无法复查的泛称。
生成正式质量意见报告后,按 references/archive-standards.md 判断是否归档。需要归档时,在本技能 archive/YYYYMMDD_HHMMSS_<target-slug>/ 下保存报告、元数据和证据索引;真实归档内容不提交到 Git。
| 级别 | 说明 | 处理 |
|---|---|---|
| ❌ 严重 | 阻塞加载、发布、使用安全或质量验收 | 必须修复 |
| ⚠️ 警告 | 影响维护、复用、审查可信度或可评估性 | 建议修复 |
| ℹ️ 信息 | 风格、清晰度或后续改进建议 | 可选处理 |
Hard Fail 一律按严重问题处理。
正式质量意见报告模板见 templates/skill-quality-opinion-report.md。报告除原有结构、安全、业务流和可评估性外,必须单列 Harness 七层结论、证据等级和完成标记。
模板的设计理念要点(结构性建议必填「设计理念」字段,纯事实问题可省):
references/skill-standards.md:审查索引和模块路由references/repository-skill-discovery-standards.md:仓库类型识别、monorepo 单元发现和候选文档分级references/structure-standards.md:目录结构、文件可达性和 references 命名references/frontmatter-metadata-policy.md:Frontmatter 通用字段与项目发布字段分层策略references/trigger-description-standards.md:name 与 description 触发边界references/configuration-privacy-standards.md:配置模板、本地配置隔离和公开内容去具体化references/security-assessment-standards.md:危险执行、敏感访问、数据外传、凭证、依赖、MCP 和提示词安全references/publishing-standards.md:LICENSE、CHANGELOG、version 与发布索引references/workflow-output-standards.md:正文工作流、依赖、脚本、输出和可编排性references/business-flow-rubric.md:业务流深度和可评估性判则references/harness-reliability-standards.md:Harness 七层可靠性、Hard Fail、创建预检和候选绑定证据门禁references/instruction-stability-standards.md:旧版识别、约束追踪、模态/阶段匹配、多轮执行和产出漂移门禁references/reporting-standards.md:问题分级和审查报告模板references/archive-standards.md:正式审查报告的内部归档机制references/skill-dev-guide.md:Skill 开发规范参考references/skill-orchestration-guide.md:复杂编排规范参考config/review-profile.example.yaml:个人/项目审查配置模板config/instruction-stability-contract.example.json:目标 Skill 的约束追踪合同示例config/instruction-stability-requirements-baseline.example.json:候选外独立硬约束基线格式示例config/instruction-stability-held-out-cases.example.json:evaluator-signed 候选外隐藏正反例清单格式scripts/harness_evidence_gate.py:生成和复算候选绑定的 Harness 审查证据scripts/harness_failure_audit.py:单 Skill / Skill 集合的具体 Harness 失效模式静态审查scripts/instruction_stability_gate.py:静态识别旧版结构风险,并验证多轮真实产物的逐约束覆盖稳定性templates/skill-quality-opinion-report.md:最终 Skill 质量意见报告模板© cat-xierluo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 35 other files (scripts, references) in skills/skill-lint of cat-xierluo/legal-skills.
Open the folder on GitHubat commit db2c58c
Skill Lint 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 |
|---|---|---|---|---|---|---|
| Skill Lint this skillcat-xierluo/legal-skills | 720 | — | ~2.9k | Automated safety check: Notes | MIT | |
| Minimizing Ty Ecosystem Changesastral-sh/ruff | 50k | — | ~4.6k | Automated safety check: Pass | MIT | |
| Install Anti-Slop Oxlint Rulesdmmulroy/anti-slop | 5.4k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Babysit PR To Pass CIsgl-project/sglang | 37k | 2 repos | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Rust Best Practicesfarm-fe/farm | 5.6k | 3 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Summarise Ecosystem Resultsastral-sh/ruff | 50k | — | ~2.2k | Automated safety check: Pass | MIT |
astral-sh/ruff
A skill your agent uses when a user says "minimize this ty ecosystem change", "reproduce this ecosystem result", "investigate a primer difference", "investigate a mypyprimer difference"…
dmmulroy/anti-slop
Installs, updates or migrates the vendored anti-slop Oxlint plugin in a repository, keeping local rule changes and the plugin's license and provenance files.
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.
farm-fe/farm
Guide for writing idiomatic Rust code based on Apollo GraphQL's best practices handbook.
astral-sh/ruff
A skill your agent uses when a user says "summarise ecosystem results", "summarize this ty ecosystem report", "what changed in this ecosystem run?", or asks to summarise or summarize ty ecosystem…
chromedp/chromedp
This skill should be used when the user is writing Go code and needs guidance on Go-specific pedantry: error wrapping with fmt.Errorf and %w, interface design (accept interfaces return structs)…
cat-xierluo/legal-skills
Converts a lawyer's ordinary complaint or a described case into the Supreme People's Court's elements-style Word template, with layout checks on the result.
cat-xierluo/legal-skills
Analyzes raw lecture transcripts for verbal tics, pacing, time use and promise follow-through, with optional slide-by-slide comparison and cross-session tracking.
cat-xierluo/legal-skills
Detects and rewrites machine-sounding patterns in the body text of Chinese articles while keeping the author's facts, headings and legal terms intact.
cat-xierluo/legal-skills
Finds GitHub projects mentioned in articles or screenshots and stars them, tracks updates to your starred repos, and builds an HTML dashboard to browse them.
cat-xierluo/legal-skills
Sets up or incrementally updates AGENTS.md and CLAUDE.md for legal professionals, with a minimal safety baseline and a check that a new session loads and follows the rules.
cat-xierluo/legal-skills
Chinese-language skill that organizes a case file into a multi-role mock trial with judge, parties and clerk, producing a transcript, issue review and a to-strengthen list.
Categories
Skill 创建预检、可靠性验收与格式审查工具。本技能应在用户创建、重大改造或审查Skill,需要识别旧版 Skill 的指令遵循不稳定、产出漂移、验证模态错配、约束漏检,或检查 Harness 契约、候选绑定证据、故障注入、目录结构、业务流和安全风险时使用。不要用于:代替业务领域验证器、代码审查、应用功能测试、通用编程任务。. Skill Lint is an agent skill from cat-xierluo/legal-skills.
Skill Lint fits situations like: tasks that involve Linting and formatting.
Run `npx skills add cat-xierluo/legal-skills --skill skill-lint -a claude-code`. Or copy the skill folder (skills/skill-lint in cat-xierluo/legal-skills) into .claude/skills/skill-lint in your project. Claude Code loads it when a task matches its description.
Run `npx skills add cat-xierluo/legal-skills --skill skill-lint -a codex`. Or copy the skill folder (skills/skill-lint in cat-xierluo/legal-skills) into .agents/skills/skill-lint in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cat-xierluo/legal-skills --skill skill-lint -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-lint, .gemini/skills/skill-lint, .github/skills/skill-lint and .opencode/skills/skill-lint in your project.
Going by SKILL.md and its folder, Skill Lint needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
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.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. 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.
Skill Lint is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 36k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Skill Lint: Minimizing Ty Ecosystem Changes (astral-sh/ruff, 50k stars), Install Anti-Slop Oxlint Rules (dmmulroy/anti-slop, 5.4k stars), Babysit PR To Pass CI (sgl-project/sglang, 37k stars) and Rust Best Practices (farm-fe/farm, 5.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
cat-xierluo (a GitHub user) maintains it in cat-xierluo/legal-skills, which has 720 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 10, 2026.
Source: cat-xierluo/legal-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.