skills/clig-eval-prompt/SKILL.md
Generate a concise Chinese evaluation prompt for DevOps CLI / command-line tool projects based on clig.onev.dev guidelines, with weights, thresholds, and hard gates. Use when a user asks to create or store a reusable CLI review prompt, a scoring rubric, an evaluation checklist, or wants to evaluate a command-line interface, terminal tool, or CLI best practices against design guidelines.
npx skillsauth add samzong/samzong clig-eval-promptInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Output the canonical evaluation prompt for reviewing DevOps CLI tools against clig.onev.dev. Keep output Chinese, short, and copy-paste ready.
你是严格的 CLI 评审员。基于《命令行界面设计指南》,评估 DevOps 类 CLI 项目 {project_name}。输出中文、尽量简短。
评分:0-100,总分=Σ(维度分×权重)。每维度 0-5 分。
权重:
A 基础契约与可组合性 18
B 输出与机器可读 12
C 错误与诊断 10
D 交互与危险操作 10
E 参数/标志一致性 8
F 帮助与文档 8
G 健壮性与长任务体验 10
H 配置/环境变量/安全 10
I 子命令结构 5
J 面向未来/兼容性 5
K 信号与 Ctrl-C 2
L 分发与卸载 1
M 分析与隐私 1
阈值:
- ≥85 生产级
- 70-84 可用但需改进
- 55-69 不推荐投入生产
- <55 不合格
硬性门槛(触发则结论最多"可用但需改进",且总分上限 69):
- 退出码或 stdout/stderr 规范明显错误
- 非交互场景仍强制提示/无法脚本化
- 破坏性操作无确认/无预演/无 --force 或等价机制
- 明显泄露密钥(flag/env 中传递或输出)
评审维度要点(每项:结论+证据+建议,1-2 句):
A 退出码;stdout 主输出/机器可读;stderr 日志错误
B TTY 感知;人类优先;提供 --json/--plain;颜色/动画/分页在非 TTY 或 NO_COLOR 下禁用
C 错误可理解可操作;高信噪比;给出调试/报错路径
D 仅 TTY 提示;--no-input;密码不回显;危险操作确认/可预演
E 优先 flags;长短版本;通用命名;顺序尽量无关;支持 '-' 读写
F -h/--help;无参简洁帮助+示例;终端文档/网页文档/可查 man
G 输入校验;快速反馈;进度/超时;可恢复;并发输出不乱
H 配置类型匹配 flags/env/config;遵循 XDG;环境变量命名规范;敏感信息不放 env;支持常见代理变量
I 一致命名;noun-verb 或 verb-noun;避免歧义
J 有弃用期;避免隐式子命令/任意缩写;稳定机器输出
K Ctrl-C 及时响应;可强制退出;清理有超时
L 尽量单文件或原生包;易卸载
M 默认不收集;明确告知/易关闭/优先选择加入
输出格式:
1) 一句话总评
2) 得分与结论
3) 严重问题清单(阻断/高/中/低)
4) 维度评分(A-M,短句)
5) 最小改动清单(优先级 1-5)
证据不足请标"未知",并写出需要的证据(命令输出/文档/源码位置)。
User: "把 B 的权重改成 15,A 改成 15" → Output the full prompt with only those two weights updated; all other lines verbatim.
documentation
撰写微信公众号技术文章的结构化工作流。使用场景:用户要写一篇公众号文章、需要创建文章目录、组织素材、迭代草稿。强制遵循 blogs/wechat/README.md 的命名规范和目录结构。
tools
Cross-tool vibe coding profiler. Scans AI coding tool data on the machine (Claude Code sessions, OpenCode DB, Codex sessions), combined with git history and project memory, to build a true user portrait, discover workflow automation opportunities, and update the target tool's instruction file (CLAUDE.md or AGENTS.md) accordingly. Use when: "calibrate", "vibe-calibrate", "分析我的习惯", "profile me", "update my CLAUDE.md based on my history", "我的效率怎么提升", "analyze my patterns", "优化我的配置", or at the start of a long-term engagement with a new user.
development
Ruthless code simplifier: flatten abstractions, inline wrappers, remove unnecessary layers, delete dead code — without changing behavior. Use when: user says "simplify", "simplify this", "flatten", "inline", "too complex", "over-engineered", "remove abstraction", "unwrap", "reduce complexity", "make it simpler", "this is too complicated", or points at code that has unnecessary indirection. Does NOT change behavior, break public APIs, or remove meaningful error handling.
testing
Ship staged changes through a narrow release flow: auto-clean staged files, block unexpected non-i18n CJK additions, create or keep a branch, commit staged work, push, and open a pull request — all without confirmation. Use mainly when the user explicitly invokes `/ship` or says "ship it", "push and PR", or "commit and PR". Do not use for commit-only, push-only, PR-only, or existing-PR editing requests. All generated git and GitHub text must be in English.