Skill 与 AgentSKILLS & AGENTS· CLAUDE-SKILL
unclebob/ub-mode
让AI助手按Bob大叔的编程原则写代码,先跑通再改好。A skill that enforces disciplined coding principles — make it work, then make it right — for AI agents.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
把每个函数的复杂度控制在10以下
消除相似度超过0.8的重复代码
发现测试覆盖不到的代码和存活变异体
让每次提交都是小而有序的
Write code that works first, then refactor it to be right.
Keep cyclomatic complexity below a defined threshold.
Eliminate duplicate code blocks automatically.
Run mutation testing to catch untested code paths.
Visualize component structure and quality metrics.
上手GET STARTED
Copy `SKILL.md` into your agent's skills directory as `ub-mode/SKILL.md` (for example `~/.grok/skills/ub-mode/SKILL.md`, `~/.claude/skills/ub-mode/SKILL.md`, or `~/.cursor/skills/ub-mode/SKILL.md`), then invoke `/ub-mode`.选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.
The static scan found no obvious risk patterns in the documentation, but that does not prove the skill is safe to run.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
15 NOV 202615 NOV 2026
增长GROWTH
+3.6%+3.6%
8.0k → 8.3k stars · 6 个快照8.0k → 8.3k stars · 6 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
1 条外部提及1 external mentions
状态STATUS
持续活跃Active
质量 A-Quality A-
这个技能能帮你强制代码先跑通再改对,避免写出又乱又难测的代码。Created by Uncle Bob (Robert C. Martin), a well-known figure in software craftsmanship.
HN_STORY · 3 points · 0 comments
{
"agents": [],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 0,
"dev-tools": 1,
"indie-web": 0,
"skill-agent": 2,
"productivity": 1
},
"primary": "skill-agent",
"secondary": "claude-skill"
},
"localRuntime": null,
"skillMdTotal": 1,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 2,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "1 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
}
],
"scannedSources": [
"readme",
"SKILL.md"
],
"skillMdFetched": 1
}