Token导航 LogoToken导航

Agent Skill · 研究检索

quality-gate(质量门)

quality-gate 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。

quality-gate 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 47,393。

总安装 734周安装 30GitHub Stars 6下载 235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:quality-gate(质量门)
来源仓库:https://github.com/duc01226/easyplatform
仓库路径:skills/quality-gate
安装命令:
npx skills add https://github.com/duc01226/easyplatform --skill quality-gate
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/duc01226/easyplatform --skill quality-gate

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。

quality-gate 用于查找、检索和筛选相关信息,适合根据关键词或任务线索快速定位候选结果。适用于研究、调研或信息收集类场景,可提升外部资源发现效率。通过指定查询条件调用搜索接口,返回结构化候选列表供进一步处理。使用前建议确认是否允许联网及数据抓取边界,避免违反平台策略。

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/quality-gate

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/duc01226/easyplatform --skill quality-gate;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

quality-gate 怎么安装?

在终端执行 npx skills add https://github.com/duc01226/easyplatform --skill quality-gate。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

quality-gate 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。

quality-gate 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。

quality-gate 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。

quality-gate 用的人多吗?

公开数据是累计安装 734 次,近一周安装 30 次,下载 235 次,GitHub 6 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。

quality-gate 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
quality-gate

质量门 · 本页

7346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

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.
Understand Code First — HARD-GATE: Do NOT write, plan, or fix until you READ existing code. 1. Search 3+ similar patterns (grep/glob) — cite file:line evidence 2. Read existing files in target area — understand structure, base classes, conventions 3. Run python.claude/scripts/code_graph trace <file> --direction both --json when .code-graph/graph.db exists 4. Map dependencies via connections or callers_of — know what depends on your target 5. Write investigation to .ai/workspace/analysis/ for non-trivial tasks (3+ files) 6. Re-read analysis file before implementing — never work from memory alone 7. NEVER invent new patterns when existing ones work — match exactly or document deviation BLOCKED until: - [] Read target files - [] Grep 3+ patterns - [] Graph trace (if graph.db exists) - [] Assumptions verified with evidence
  • docs/project-reference/domain-entities-reference.md — Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models) (content auto-injected by hook — check for [Injected:...] header before reading)
Graph Impact Analysis — When .code-graph/graph.db exists, run blast-radius --json to detect ALL files affected by changes (7 edge types: CALLS, MESSAGE_BUS, API_ENDPOINT, TRIGGERS_EVENT, PRODUCES_EVENT, TRIGGERS_COMMAND_EVENT, INHERITS). Compute gap: impacted_files - changed_files = potentially stale files. Risk: <5 Low, 5-20 Medium, >20 High. Use trace --direction downstream for deep chains on high-impact files.

Quick Summary

Goal: Verify readiness criteria before proceeding to next phase.

Workflow:

  1. Identify — Determine gate type (pre-dev, pre-QA, pre-release)
  2. Check — Run gate-specific checklist items
  3. Report — PASS/FAIL with evidence per criterion

Key Rules:

  • Output must be PASS or FAIL with specific evidence
  • Never skip checklist items — mark as N/A if not applicable
  • Block progression on FAIL — list blocking items

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Frontend/UI Context (if applicable)

When this task involves frontend or UI changes,
UI System Context — For ANY task touching .ts, .html, .scss, or .css files: MUST ATTENTION READ before implementing: 1. docs/project-reference/frontend-patterns-reference.md — component base classes, stores, forms 2. docs/project-reference/scss-styling-guide.md — BEM methodology, SCSS variables, mixins, responsive 3. docs/project-reference/design-system/README.md — design tokens, component inventory, icons Reference docs/project-config.json for project-specific paths.
  • Component patterns: docs/project-reference/frontend-patterns-reference.md
  • Styling/BEM guide: docs/project-reference/scss-styling-guide.md
  • Design system tokens: docs/project-reference/design-system/README.md

Gate Types & Checklists

Pre-Development Gate

  • Acceptance criteria defined and clear
  • Dependencies identified and available
  • Design specs available (if UI work)
  • No blocking questions unresolved
  • Story points assigned (Fibonacci 1-21: 1=trivial, 2=small, 3=medium, 5=large, 8=very large, 13=epic SHOULD split, 21=MUST ATTENTION split)

Pre-QA Gate

  • All acceptance criteria implemented
  • Unit tests passing
  • Code review complete
  • No known critical bugs
  • Test data prepared

Pre-Release Gate

  • All tests passing (unit + integration)
  • Code review complete
  • CHANGELOG.md up-to-date
  • No critical/major open bugs
  • Documentation up-to-date
  • Rollback strategy defined

Database Performance Gate (ALL gate types)

[IMPORTANT] Database Performance Protocol (MANDATORY): 1. Paging Required — ALL list/collection queries MUST ATTENTION use pagination. NEVER load all records into memory. Verify: no unbounded GetAll(), ToList(), or Find() without Skip/Take or cursor-based paging. 2. Index Required — ALL query filter fields, foreign keys, and sort columns MUST ATTENTION have database indexes configured. Verify: entity expressions match index field order, database collections have index management methods, migrations include indexes for WHERE/JOIN/ORDER BY columns.
  • All list queries use pagination (no unbounded GetAll/ToList)
  • Query filter fields have matching database indexes
  • Foreign keys have database indexes configured
  • Sort columns have database indexes configured

Output Format

## Quality Gate Result

**Gate Type:** [Pre-Dev | Pre-QA | Pre-Release]
**Verdict:** PASS | FAIL
**Date:** {date}

### Checklist

- [pass] [Item] — [evidence]
- [fail] [Item] — [reason for failure]
- N/A [Item] — [why not applicable]

### Blocking Items (if FAIL)
1. [Specific item that must be resolved]

IMPORTANT Task Planning Notes (MUST ATTENTION FOLLOW)

  • Always plan and break work into many small todo tasks using TaskCreate
  • Always add a final review todo task to verify work quality and identify fixes/enhancements

Workflow Recommendation

MANDATORY IMPORTANT MUST ATTENTION — NO EXCEPTIONS: If you are NOT already in a workflow, you MUST ATTENTION use AskUserQuestion to ask the user. Do NOT judge task complexity or decide this is "simple enough to skip" — the user decides whether to use a workflow, not you: 1. Activate pre-development workflow (Recommended) — quality-gate → plan → plan-review → plan-validate 2. Execute /quality-gate directly — run this skill standalone

Closing Reminders

  • IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
  • IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
  • IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
  • IMPORTANT MUST ATTENTION add a final review todo task to verify work quality MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting:
  • IMPORTANT MUST ATTENTION search 3+ existing patterns and read code BEFORE any modification. Run graph trace when graph.db exists.
  • IMPORTANT MUST ATTENTION run graph impact analysis on changed files. Compute gap: impacted minus changed = potentially stale.
  • IMPORTANT MUST ATTENTION read frontend-patterns-reference, scss-styling-guide, and design-system/README before any UI work.

平台分布

Claude Code

29.89%
按下载量换算70

windsurf

21.93%
按下载量换算52

OpenCode

18.88%
按下载量换算44

Codex

13.36%
按下载量换算31

Antigravity

8.26%
按下载量换算19

Gemini CLI

3.34%
按下载量换算8

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