Token导航 LogoToken导航

Agent Skill · 研究检索

bash-script-validator(bash 脚本验证器)

bash-script-validator 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 Codex、Claude、Cursor、Gemini CLI 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

bash-script-validator 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 27,345。

总安装 3,408周安装 142GitHub Stars 197下载 1,136核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:bash-script-validator(bash 脚本验证器)
来源仓库:https://github.com/akin-ozer/cc-devops-skills
仓库路径:skills/bash-script-validator
安装命令:
npx skills add https://github.com/akin-ozer/cc-devops-skills --skill bash-script-validator
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/akin-ozer/cc-devops-skills --skill bash-script-validator

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于 Bash 脚本的语法检查与自定义规则验证,支持 ShellCheck 集成。适合在 Codex、Claude、Cursor、Gemini CLI 中提升脚本质量与 CI 门禁。

通过 npx skills add https://github.com/akin-ozer/cc-devops-skills --skill bash-script-validator 安装。使用前请确认系统是否具备 shellcheck 二进制文件,受限环境可能跳过部分检查。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/bash-script-validator

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/akin-ozer/cc-devops-skills --skill bash-script…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

bash-script-validator 怎么安装?

在终端执行 npx skills add https://github.com/akin-ozer/cc-devops-skills --skill bash-script-validator。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

bash-script-validator 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

bash-script-validator 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/akin-ozer/cc-devops-skills --skill bash-script-validator 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

bash-script-validator 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

bash-script-validator 用的人多吗?

公开数据是累计安装 3,408 次,近一周安装 142 次,下载 1,136 次,GitHub 197 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

bash-script-validator 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
bash-script-validator

bash 脚本验证器 · 本页

3,408197执行命令未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Bash Script Validator

Overview

This skill validates Bash and POSIX shell scripts with layered checks:

  1. Syntax validation (bash -n or sh -n)
  2. ShellCheck static analysis (system binary or wrapper fallback)
  3. Custom security, portability, and optimization checks

Use the default flow below, then branch to fallbacks only when the environment is constrained.

Trigger Guidance

Use this skill when the request includes script quality, linting, syntax checking, or shell portability work.

Trigger Phrases

  • "Validate this bash script"
  • "Lint this .sh file"
  • "Find security issues in this shell script"
  • "Why does this script fail ShellCheck?"
  • "Make this script POSIX compliant"
  • "Review this shell script before CI"

Non-Trigger Examples

  • General Linux command questions with no script file
  • Kubernetes, Terraform, or pipeline validation tasks that do not involve shell scripts
  • Pure prose editing tasks

Deterministic Execution Model

Run commands from this skill directory:

cd devops-skills-plugin/skills/bash-script-validator

Step 1: Preflight

  1. Confirm target path exists and is readable.
  2. Confirm bash is available.
  3. Determine whether fixes can be applied directly (write access) or only suggested (read-only).

Step 2: Run Baseline Validation (Default Path)

bash scripts/validate.sh <script-path>

For deterministic stage behavior, set the ShellCheck provider explicitly:

# Modes: auto (default), system, wrapper, disabled
VALIDATOR_SHELLCHECK_MODE=system bash scripts/validate.sh <script-path>

Record:

  • Detected shell type
  • Exit code (0 clean, 1 warnings, 2 errors)
  • All reported issue lines and ShellCheck codes (SC####) when present

Step 3: Load Only Needed References

Progressive disclosure by issue type:

  • ShellCheck code explanations: docs/shellcheck-reference.md
  • General fix patterns and security mistakes: docs/common-mistakes.md
  • Bash-only behavior: docs/bash-reference.md
  • POSIX portability or bashism fixes: docs/shell-reference.md
  • Text-processing optimization issues: docs/grep-reference.md, docs/awk-reference.md, docs/sed-reference.md, docs/regex-reference.md (only when directly relevant)

Step 4: Provide or Apply Fixes

For each issue, include:

  1. Exact location from validator output (line number and snippet)
  2. Root cause
  3. Corrected code
  4. Why the change is safer or more portable
  5. Subsection-level citation (format below)

If the request includes patching files and write access is available, apply fixes in small batches grouped by issue type.

Step 5: Rerun Policy (Mandatory After Changes)

After each batch of edits, rerun the validator:

bash scripts/validate.sh <script-path>

Rerun loop rules:

  1. Continue until no new errors are introduced.
  2. If warnings remain by design, document why they are intentionally accepted.
  3. If constraints prevent full resolution, report unresolved items with a clear next action.
  4. Always report the latest rerun exit code and remaining issue count.

Fallback Behavior

Use these branches only when the default flow cannot run as-is.

ConstraintFallback actionReporting requirement
shellcheck missing, wrapper availableLet scripts/validate.sh use scripts/shellcheck_wrapper.sh --cache automaticallyState that wrapper mode was used
shellcheck and wrapper unavailableRun syntax + custom checks only (validator does this)Explicitly call out reduced coverage and missing ShellCheck analysis
Python unavailable for wrapperSkip wrapper path, keep syntax + custom checksState why ShellCheck could not run
Target file is read-onlyProvide precise patch suggestions without editingMark response as "advisory only"
Target file missing or unreadableStop and request a valid file pathDo not fabricate results
Binary/non-text inputStop validationReport unsupported input type

Citation Guidance for Fixes

Use subsection-level citations for every non-trivial fix.

Required citation format:

Reference: docs/<file>.md -> <Section> -> <Subsection>

Examples:

  • Reference: docs/common-mistakes.md -> 1. Unquoted Variables -> Solution
  • Reference: docs/shellcheck-reference.md -> SC2164: Use || exit After cd
  • Reference: docs/shell-reference.md -> POSIX Best Practices -> 5. Avoid Bashisms

Citation rules:

  1. Cite the most specific section that justifies the fix.
  2. For ShellCheck findings, include both the SC#### code and the matching section.
  3. If no exact subsection exists, cite the closest section and state that the fix is inferred from that guidance.

Response Template

Use this structure for deterministic output:

  • Validation Results
  • Command: bash scripts/validate.sh <script-path>
  • Detected shell: <shell>
  • Exit code: <code>
  • Summary: <errors> errors, <warnings> warnings, <info> info
  • Issue: <short label> (Line <n>)
  • Problem: <problematic snippet>
  • Fix: <corrected snippet>
  • Why: <short explanation>
  • Reference: docs/<file>.md -> <Section> -> <Subsection>
  • Rerun command: bash scripts/validate.sh <script-path>
  • Exit code after fixes: <code>
  • Remaining issues: <count or none>

Example Flows

Fully Automated Environment

# 1) Baseline validation
bash scripts/validate.sh examples/bad-bash.sh

# 2) Apply fixes to target script
# 3) Rerun validation
bash scripts/validate.sh examples/bad-bash.sh

Expected behavior: full syntax + ShellCheck + custom-check coverage, with iterative reruns until stable.

Deterministic CI Gate

# Requires a system shellcheck binary.
bash scripts/run_ci_checks.sh

This runner enforces VALIDATOR_REQUIRE_SHELLCHECK=1 and VALIDATOR_SHELLCHECK_MODE=system so CI fails if the ShellCheck stage is skipped or unavailable.

Constrained Environment (No ShellCheck Runtime)

# shellcheck unavailable and wrapper cannot run
bash scripts/validate.sh examples/bad-shell.sh

Expected behavior: syntax + custom checks still run. Report reduced coverage and list what must be revalidated once ShellCheck is available.

Validator Script Details

Scripts

  • scripts/validate.sh: primary validator entrypoint
  • scripts/shellcheck_wrapper.sh: optional ShellCheck fallback using a cached Python virtual environment

Detection and Ordering

Validation order in scripts/validate.sh:

  1. File checks (exists/readable/text)
  2. Shebang-based shell detection
  3. Syntax check
  4. ShellCheck (or fallback/skip behavior)
  5. Custom checks
  6. Summary with exit code

Exit Codes

  • 0: no issues found
  • 1: warnings found
  • 2: errors found

References

Load only what is needed:

  • docs/bash-reference.md
  • docs/shell-reference.md
  • docs/shellcheck-reference.md
  • docs/common-mistakes.md
  • docs/grep-reference.md
  • docs/awk-reference.md
  • docs/sed-reference.md
  • docs/regex-reference.md

Done Criteria

This skill update is complete when all are true:

  1. Trigger guidance is explicit (positive and non-trigger examples).
  2. Default workflow is deterministic and ordered.
  3. Fallback behavior is explicit for missing tooling and constrained environments.
  4. Fix explanations include subsection-level citations.
  5. Post-fix rerun policy is mandatory and reported with exit codes.
  6. Documentation supports both fully automated and constrained execution paths.

平台分布

Codex

36.39%
按下载量换算413

Claude

30.78%
按下载量换算350

Cursor

20.11%
按下载量换算228

Gemini CLI

10.39%
按下载量换算118

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/akin-ozer/cc-devops-skills --skill bash-script-validator 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills