Token导航 LogoToken导航

Agent Skill · 研究检索

skill-linter(技能检查)

skill-linter 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

skill-linter 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,权限为需要联网;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 39,065。

总安装 1,469周安装 60GitHub Stars 37下载 470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
MIT

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:skill-linter(技能检查)
来源仓库:https://github.com/majesticlabs-dev/majestic-marketplace
仓库路径:skills/skill-linter
安装命令:
npx skills add https://github.com/majesticlabs-dev/majestic-marketplace --skill skill-linter
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/majesticlabs-dev/majestic-marketplace --skill skill-linter

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。

skill-linter 用于查找、检索和筛选相关信息,适合在代码审查或规范检查中快速定位问题模式。支持基于关键词、规则集或错误类型筛选相关内容,提升 linting 效率。通过 npx skills add 命令从指定仓库安装,需确认来源仓库的有效性与访问权限。

使用前建议核实维护状态,避免使用废弃或存在兼容性问题功能。注意是否涉及文件读写或外部工具调用,确保符合本地安全策略。

来源仓库内路径:skills/skill-linter

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/majesticlabs-dev/majestic-marketplace --skill…;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

    它需要需要联网,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

skill-linter 怎么安装?

在终端执行 npx skills add https://github.com/majesticlabs-dev/majestic-marketplace --skill skill-lint…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

skill-linter 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。

skill-linter 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

skill-linter 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

skill-linter 用的人多吗?

公开数据是累计安装 1,469 次,近一周安装 60 次,下载 470 次,GitHub 37 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。

skill-linter 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
skill-linter

技能检查 · 本页

1,46937需要联网MIT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

Skill Linter

When to Use

  • Adding new skills to the marketplace
  • Reviewing skill PRs
  • Running quality gates before merge
  • Checking existing skills for compliance

Validation Rules

Required Frontmatter

FieldConstraints
name1-64 chars, lowercase alphanumeric + hyphens, no leading/trailing/consecutive hyphens, must match parent directory name. Cannot contain "claude" or "anthropic" (reserved).
description1-1024 chars, non-empty, should include keywords for discoverability. No XML angle brackets (< >).

Optional Frontmatter

FieldConstraints
compatibility1-500 chars, environment requirements
metadataKey-value pairs (string values only)
allowed-toolsSpace-delimited tool list (FAIL on commas or array syntax)

Structure Requirements

RuleRequirement
Directory nameMust match name field exactly
SKILL.mdRequired, must exist
README.mdMust NOT exist inside skill folder (docs go in SKILL.md or references/)
Line limitMax 500 lines in SKILL.md
SubdirectoriesOnly scripts/, references/, assets/ allowed

Content Quality Rules

RuleRequirement
No ASCII artBox-drawing characters (─│┌┐└┘├┤┬┴┼), arrows (↑↓←→↔), and decorative diagrams waste tokens. LLMs tokenize character-by-character, not visually. Use plain lists or tables instead.
No decorative quotesInspirational quotes or attributions ("As X said...") have no functional value for LLM execution.
No persona statements"You are an expert..." wastes tokens. Use Audience: / Goal: framing instead.
Functional content onlyEvery line should improve LLM behavior. Ask: "Does this help Claude execute better?"

Audience/Goal Framing (Required)

Replace persona roleplay with audience-focused framing:

❌ Bad (persona):

You are an expert software engineer with deep expertise in testing.
Your role is to analyze code and generate thorough test coverage.

✅ Good (audience/goal):

**Audience:** Developers needing test coverage for new or changed code.

**Goal:** Generate comprehensive tests based on specified test type and framework.

Rationale: "Explain X for audience Y" yields better-tailored outputs than "Act as persona Z".

ASCII Art Detection Pattern:

[─│┌┐└┘├┤┬┴┼╭╮╯╰═║╔╗╚╝╠╣╦╩╬↑↓←→↔⇒⇐⇔▲▼◄►]{3,}

Files matching this pattern should be flagged for review.

Description Routing Quality (WARN)

Skill descriptions are routing logic, not documentation. They answer:

  • When to use this skill (trigger conditions)
  • When NOT to use (negative routing)
  • What outputs to expect (success criteria)
Quality LevelExample
Good"Use when implementing Stimulus controllers. Not for React components. Outputs controller with targets and actions."
Adequate"Use when working with Stimulus controllers in Rails applications."
Poor"Stimulus controller development skill."
Anti-pattern"Comprehensive, powerful toolkit for building cutting-edge Stimulus controllers."

Templates inside skills are encouraged — loaded only on trigger, essentially free tokens.

Skill Disambiguation (INFO)

When multiple skills cover similar domains, include negative routing:

Example (minitest vs rspec):

SkillDescription Routing
minitest-coder"Use when writing Minitest tests. Not for RSpec — use rspec-coder instead."
rspec-coder"Use when writing RSpec tests. Not for Minitest — use minitest-coder instead."

"Don't use when..." is as important as "Use when..." for routing accuracy.

Name Pattern

^[a-z][a-z0-9]*(-[a-z0-9]+)*$

Valid: my-skill, skill1, api-v2-handler Invalid: -skill, skill-, my--skill, MySkill, my_skill

Command/Agent Invocation Patterns

Skills should primarily provide knowledge, not orchestration. If invocations are needed:

PatternStatusUse Instead
Skill("command", args: "...")❌ Deprecated/command args
SlashCommand("command",...)❌ Deprecated/command args
Task(subagent_type="agent",...)✅ Correct(no change)

✅ Preferred command invocation:

/majestic:config tech_stack generic
/majestic-engineer:tdd-workflow
/majestic-engineer:workflows:build-task "T1"

❌ Deprecated patterns:

Skill("config-reader", args: "tech_stack generic")
SlashCommand("majestic:build-task", args: "...")

Note: Agent invocation via Task() is correct - there is no @agent syntax.

Usage

Validate Single Skill

./scripts/validate-skill.sh path/to/skill-name

Validate All Marketplace Skills

for skill in plugins/*/skills/*/; do
  ./scripts/validate-skill.sh "$skill"
done

CI Integration

Add to pre-commit hook or CI pipeline:

- name: Lint Skills
  run: |
    for skill in plugins/*/skills/*/; do
      .claude/skills/skill-linter/scripts/validate-skill.sh "$skill" || exit 1
    done

Validation Script

The linter script at scripts/validate-skill.sh performs these checks:

  1. Directory exists with SKILL.md file
  2. Frontmatter present with YAML delimiters
  3. Name field valid - pattern, length, matches directory
  4. Reserved words - name cannot contain "claude" or "anthropic" (FAIL)
  5. Description field valid - present, length constraints
  6. XML tags in frontmatter - no angle brackets < > (security, FAIL)
  7. No README.md - inside skill folder (WARN)
  8. Optional fields valid - if present, match constraints
  9. Line count - under 500 lines
  10. Subdirectory names - only allowed directories
  11. No ASCII art - box-drawing characters outside fenced code blocks (WARN)
  12. No persona statements - "You are a/an/the" outside fenced code blocks (FAIL)
  13. Description routing quality - routing keywords present (WARN)
  14. Marketing copy detection - buzzwords in description (WARN)

Error Codes

CodeMeaning
0All validations passed
1Missing SKILL.md
2Invalid frontmatter
3Name validation failed
4Description validation failed
5Optional field validation failed
6Line limit exceeded
7Invalid subdirectory
8ASCII art detected (warning)
9Persona statement detected
10Description routing quality (warning)
11Marketing copy detected (warning)

Example Output

Validating: plugins/majestic-tools/skills/brainstorming

[PASS] SKILL.md exists
[PASS] Frontmatter present
[PASS] Name 'brainstorming' valid (12 chars)
[PASS] Name matches directory
[PASS] Description valid (156 chars)
[PASS] Line count: 87/500
[PASS] Subdirectories valid
[PASS] No ASCII art outside code blocks
[PASS] No persona statements
[PASS] Description has routing keywords
[PASS] No marketing copy in description

Result: ALL CHECKS PASSED

Spec Reference

Based on agentskills.io/specification:

  • Progressive disclosure - Metadata ~100 tokens at startup, full content <5000 tokens when activated
  • Reference files - Keep one level deep from SKILL.md
  • Token budget - Main SKILL.md recommended under 500 lines

平台分布

Antigravity

27.51%
按下载量换算129

OpenCode

22.01%
按下载量换算103

Gemini CLI

16.4%
按下载量换算77

Claude Code

11.77%
按下载量换算55

trae

7.06%
按下载量换算33

windsurf

3.53%
按下载量换算17

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。

继续浏览同类 Skills