code-quality
Generic code-authoring standards for dev agents: correctness over convenience, no fail-open branches, comment rules, over-engineering limits, prove-your-guards. Load before writing or modifying code.
供给资产档案
编程与开发 Agent
代码审查、仓库分析、测试、CI、GitHub、DevOps 与开发工作流 Skill。
场景
GitHub automation
I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.
适配 Agent
Claude Code + CLI + Codex
适用于 Codex、Claude Code、Cursor、CLI 或自定义 Agent。
安装
就绪
npx skills add vanillagreencom/kendex --skill code-quality
维护状态
新鲜
今天有推送
风险
需审查
Permission surface may require sandboxing
GitHub 质量
63
65/100 质量 · 75/100 信任
覆盖标签
审查说明
Permission surface may require sandboxing · Quality score needs review
Agent 采用评分卡
一眼查看信任、审计与安装准备度
这些分数综合公开仓库元数据、OpenAgentSkill 审查信号、维护新鲜度与安装准备度。它用于候选筛选,不替代人工审查。
质量
有潜力有用的候选项,但采用前应与替代方案比较。
信任
仅限沙盒有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。
审计
需审查对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。
OpenAgentSkill 信任评分 v5
安装前需人工审查
仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。
Stars
63 个 GitHub Stars
仓库活跃度
63 个 Star,23 个 Fork
维护状态
今天有推送
许可证
MIT
安装
npx skills add vanillagreencom/kendex --skill code-quality
安装安全性
标准软件包或运行时安装路径
权限范围
shell or command execution, filesystem or document access
Agent 结果
暂未有 Agent 结果数据
文档
README/SKILL.md 上下文充分
风险摘要
生产前审查
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access
- GitHub adoption: 63 GitHub stars
- Stars/forks activity: 63 stars, 23 forks; issue activity unavailable in current metadata
安装准备度
安装路径可用
- 安装路径可用
- 仓库证据可用
- 已声明许可证
- 暂无 Agent 验证结果证据
Agent 可读元数据
这个 Skill 的机器可读决策数据。
使用此区块或内嵌 JSON 判断 Agent 是否应安装该 Skill、选择替代方案,或先请求人工审查。
适用任务
- GitHub automation 工作流
- Claude Code 团队
- builders willing to evaluate younger projects
- Inspect repository metadata
适用 Agent
安装决策
- 命令
- npx skills add vanillagreencom/kendex --skill code-quality
- 策略
- 审查
- 人工审查
- 是
信任与风险
- 信任
- 67/100
- 审计
- 79/100
- 风险级别
- 需审查
结果闭环
- 端点
- /api/agent/outcome
- 事件 ID
- resolve
- 结果
- 5
不适用场景
- 需要厂商支持 SLA 的团队
- 没有内部安全审查的高合规环境
- 当前元数据中未发现重大风险信号
- 高风险权限提示:Shell 或命令执行
- Permission surface may require sandboxing
替代 Skill
Code Review
168.6K Stars
npx skills add mattpocock/skills --skill code-review
替代 Skill
Grill With Docs
164.7K Stars
npx skills add mattpocock/skills --skill grill-with-docs
替代 Skill
To Spec
164.7K Stars
npx skills add mattpocock/skills --skill to-spec
替代 Skill
To Tickets
176.7K Stars
npx skills add mattpocock/skills --skill to-tickets
Agent 安全 v2
51/100 · 避免自动安装
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
高
Shell 或命令执行
Skill 元数据引用了终端、CLI、Shell、子进程或命令执行工作流。
中
网络访问
Skill 可能访问远程页面、API、仓库或外部服务。
中
文件系统访问
Skill 可能读取或写入项目文件、文档、生成产物或本地工作区状态。
- 高风险权限提示:Shell 或命令执行
- Permission surface may require sandboxing
安装目标
在你的 Agent 工作流中安装此 Skill
通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。
OpenAgentSkill CLI
Resolve policy, run the source installer safely, and report a verified install receipt.
$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install vanillagreencom-code-qualityAgent 解析计划
让 Agent 在安装前验证匹配度。
Resolve API 返回首选 Skill、替代方案、安全策略、审计说明、安装目标和可直接执行的提示词,无需抓取此页面。
打开 JSON
/api/agent/resolve?task=Use%20code-quality%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve 文本
/api/agent/resolve?task=Use%20code-quality%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
安装交接
/api/skills/vanillagreencom-code-quality/install
Agent 应检查
- 从 Resolve API 检查任务匹配与替代方案。
- 检查审计评分、信任评分和安全策略警告。
- 检查 Codex、Claude Code、Cursor 或 CLI 的安装目标兼容性。
复制提示词
Task: Use code-quality in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20code-quality%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/vanillagreencom-code-quality/install
Install command: npx skills add vanillagreencom/kendex --skill code-quality
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent 交接
把安装路径交给 Agent,而不是再给一个目录页。
通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。
安装交接
/api/skills/vanillagreencom-code-quality/install
LLM 文本格式
/api/skills/vanillagreencom-code-quality/install?format=text
寻找替代方案
/api/skills/search?q=code-quality&limit=3
Agent 提示词
Use code-quality for this task. Review https://www.openagentskill.com/api/skills/vanillagreencom-code-quality/install, then install with: npx skills add vanillagreencom/kendex --skill code-qualityRegistry 元数据
用于自动选择 Skill 的 Agent 可读档案。
本页通过 Registry API 提供相同的决策、信任、审计、场景和安装信号,让 Agent 无需抓取界面即可排序。
Agent 决策面板
Fallback candidate for GitHub automation
先用此 Skill 做原型验证,并保留备选方案。
栈中角色
备选候选
主要匹配
GitHub automation
信任标签
先做原型验证
安装路径
命令已就绪
适用场景
- GitHub automation 工作流
- Claude Code 团队
- builders willing to evaluate younger projects
证据
- 仓库近期活跃
- 已提供安装命令或 GitHub 仓库
- 65/100 质量档案
- 1 个 OpenAgentSkill 交互事件
先审查
- 当前元数据中未发现重大风险信号
实施路径
- 1在沙盒 Agent 中安装它,并端到端完成一次GitHub automation任务。
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.
信任档案
仅限沙盒
有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。
GitHub 采用度
检查63 个 GitHub Stars
Star/Fork 活跃度
检查63 个 Star,23 个 Fork; 当前元数据中没有议题活跃度信息
近期维护
通过今天有推送
许可证清晰度
通过MIT
积极信号
- AI 审查已通过
- 安装路径可用
- 仓库证据可用
- 近期维护的仓库
- 安装命令未发现明显高风险模式
- 结果闭环已就绪,但需要首次真实 Agent 运行
安装前审查
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access
- GitHub adoption: 63 GitHub stars
- Stars/forks activity: 63 stars, 23 forks; issue activity unavailable in current metadata
- Permission surface: shell or command execution, filesystem or document access
- 暂未有真实 Agent 结果报告
- 无人值守安装前需要人工审查
建议操作
仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。
质量档案
有潜力 适用于 Agent 工作流的候选
有用的候选项,但采用前应与替代方案比较。
工作流匹配
在这些场景使用此 Skill
Manage repositories
GitHub automation
I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.
Build and ship code
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Operate local tools
Local desktop
I need my agent to operate local files and desktop apps in a repeatable workflow.
工作流匹配
加入完整工作流
Inspect, patch, and verify code
Coding review agent
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Find, compare, and synthesize
Research report agent
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Operate and verify web apps
Browser QA agent
A workflow for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
替代方案短名单
安装前对比
可能适合该任务的相近 Skill。
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
Grill With Docs
A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
To Spec
Turn the current conversation and codebase context into a structured implementation spec, then publish it to the configured project issue tracker.
To Tickets
Break a plan, spec, or conversation into independently actionable tracer-bullet tickets with explicit blocking relationships.
概览
--- name: code-quality description: "Generic code-authoring standards for dev agents: correctness over convenience, no fail-open branches, comment rules, over-engineering limits, prove-your-guards. Load before writing or modifying code." license: MIT user-invocable: true metadata: author: vanillagreen source: kendex repository: "https://github.com/vanillagreencom/kendex" bugs: "https://github.com/vanillagreencom/kendex/issues" version: "1.0.0" tags: [review] ---
# Code Quality
> **Problem with this skill?** Run `kendex report` — it files to the owning repo automatically. Do not hand-file.
Generic authoring rules, one copy upstream. Repo-specific standards (safety-critical invariants, domain rules, CI-pinned policies) ride each repo's `## Project Instructions` section below and override nothing here — they add to it.
## Core Principle
A loud failure beats a silent wrong answer. Handle every error, check invariants, and never continue in a state the code does not understand.
## Correctness
- No workarounds or quick hacks. If the correct fix is larger than expected, say so — do not ship the shortcut. - **Never fail open.** A dependency failure (command, file, network, parse) must not leave the caller in a passing or default state — e.g. a validator that degrades to "no findings", a probe failure read as "not applicable", an unchecked `$(mktemp)` running on with an empty variable. - A branch that "shouldn't happen" is never an empty or silently-ignored `else`: assert it, return an explicit internal error, or mark it unreachable — with a message naming the violated invariant. Use plain conditionals only when both branches are expected paths. - When an error path fires, it must blame the actual cause. A loud failure naming the wrong dependency misdirects the operator as badly as silence. - Edge cases are not optional: on a long enough timeline every possible input arrives. Empty input, boundary values, junk prefixes/suffixes, and interrupted-then-retried flows are the standard escapes.
## Prove Your Guards
A new or modified check, guard, assertion, or test ships with a must-fail control: plant the defect it exists to catch (a red-first run or a temporary mutation) and see it go red before its green counts as evidence. A guard that pattern-matches source text also gets controls for the shapes that satisfy the match without the property — comments, string and template-literal interiors, nested occurrences, alternate quoting, a braceless statement. Assertions loose enough to match a skip note, fixtures that never reach the guarded bound, and harness code that keeps alive what the implementation should, ship real bugs behind green suites.
## Language Discipline
- **Rust**: make illegal states unrepresentable; exhaustive matches (no `_ =>` over enums you own); enums over strings/sentinels/booleans-with-meaning. - **Bash**: `set -euo pipefail` in every new script; check the result of every effectful substitution; `--` before variable path arguments whose value can come from configuration, argv, or the environment — not before a path the script built itself (`mktemp -d`, its own fixture directory); no `[A-Za-z]`-class assumptions under arbitrary locales. - **TypeScript/JS**: distinguish missing from present-but-falsy (`""`, `0`) at every guard; no `any` at module boundaries.
## Comments and Prose
Do:
- Document WHY — the constraint or invariant the code cannot show — not what the line does. - Document public functions, structs, enums, and variants.
Don't:
- Comments that repeat the code. - Temporal markers ("added", "new", "existing code", "Phase 1") or revision narration — history lives in git. - References to AI conversations, review rounds, or issue archaeology. - Claims broader than what the adjacent code or assertion actually enforces.
The same rules govern docs, READMEs, and skill/agent files: state the rule or behavior, never its provenance, justification essay, or the analysis that produced it.
## Over-Engineering
Build only what was asked. No speculative abstractions, no error handling for impossible scenarios, no generalization before a third caller exists — three similar lines beat a premature abstraction. A wrapper that only forwards is a deletion candidate, not a pattern.
## Cleanup
Remove unused code completely: no backwards-compatibility shims, no renamed `_vars`, no commented-out blocks, no `// removed` markers, no re-exports for callers that no longer exist. Breaking removals get a CHANGELOG note, not a compat layer.
技术详情
- 版本
- 1.0.0
- 许可证
- MIT
- 最近更新
- 2026年8月23日
- 发布时间
- 2026年8月23日
决策摘要
备选候选
仓库近期活跃
Agent 验证证据
Agent 验证证据
来自解析、审查、安装和一次小范围运行后的结果报告。
- 成功率
- —
- 近期失败
- —
- 结果
- 0
- 输出质量
- —
- 失败
- 0
- 不相关
- 0
- 安装次数
- 0
- 风险拦截
- 0
- 需要配置
- 0
- 生产环境
- 0
暂时没有 Agent 结果数据。首次 Agent 执行可以通过 /api/agent/outcome 报告成功、需要设置、风险拦截、失败或不相关。
增长闭环
分享工具包
为 code-quality 准备的场景化草稿,可手动发布到 X。
code-quality: Generic code-authoring standards for dev agents: correctness over convenience, no fail-open b... 63 stars https://www.openagentskill.com/skills/vanillagreencom-code-quality?ref=x
可选:带安装命令的回复
Listing + install path for code-quality: https://www.openagentskill.com/skills/vanillagreencom-code-quality?ref=x Install: npx skills add vanillagreencom/kendex --skill code-quality
收录来源
Registry 收录
此列表来自公开来源,维护者认领获批前不会标记为官方。
- 收录方
- OpenAgentSkill 社区索引
归属链接指向公开仓库或创作者主页。创作者可认领列表以更新所有权信号。
认领此 Skill所有者认领
认领此 Skill 页面
这条 Registry 收录 列表归属于 vanillagreencom,但尚未标记为官方。认领后可增加已验证所有者信号,使后续发布、安装和审计更新更值得信赖。
创作者外链工具包
将证据徽章加入你的 README
在开发者评估仓库的位置展示规范页面、当前信任与审计信号,以及真实的 Agent 验证证据。
[](https://www.openagentskill.com/skills/vanillagreencom-code-quality)
[](https://www.openagentskill.com/skills/vanillagreencom-code-quality)
[](https://www.openagentskill.com/skills/vanillagreencom-code-quality/audit)
[](https://www.openagentskill.com/skills/vanillagreencom-code-quality)作者
vanillagreencom
@vanillagreencom
平台适配
健康信号
- GitHub Stars
- 63
- 质量评分
- 36/100
- 最近 GitHub 推送
- 2026年8月23日
- 框架提示
- 未知
- OpenAgentSkill 浏览量
- 1
- 复制安装命令
- 0
- 跳转点击
- 0
社区信号
告诉我们这个 Skill 是否对你的 Agent 工作流有帮助。汇总反馈会持续改善排序。
信任与安全
仅限沙盒
- GitHub 采用度63 个 GitHub Stars检查
- Star/Fork 活跃度63 个 Star,23 个 Fork; 当前元数据中没有议题活跃度信息检查
- 近期维护今天有推送通过
- 许可证清晰度MIT通过
- README/SKILL.md 完整度元数据包含足够的用法与工作流上下文通过
- 依赖与运行时风险命令执行范围信息
相关 Skill
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
168.6K StarsGrill With Docs
A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
164.7K StarsTo Spec
Turn the current conversation and codebase context into a structured implementation spec, then publish it to the configured project issue tracker.
164.7K StarsTo Tickets
Break a plan, spec, or conversation into independently actionable tracer-bullet tickets with explicit blocking relationships.
176.7K Stars