Token导航 LogoToken导航TokenDH.com
开发需要联网github未标认证来源可访问许可证需确认审计异常

simplify简化

Agent Skill

simplify 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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。

总安装

698

周安装

30

GitHub Stars

公开资料未说明

下载量

245
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:simplify(简化)
来源仓库:https://github.com/eljun/workflow-skills
仓库路径:skills/simplify
安装命令:
npx skills add https://github.com/eljun/workflow-skills --skill simplify
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/eljun/workflow-skills --skill simplify

简介

用于代码质量门禁检查。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。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中拦截缺陷流入。
  • 对照开发规范和验收标准进行逐项核对。
  • 输出 PASS/FAIL 信号并记录 Implementation Notes。
  • simplify 属于开发类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

/simplify - Quality Gate Agent

Workflow

/simplify {ID}
       ↓
1. Resolve task ID → read task document
2. Identify changed files (Implementation Notes or git diff)
3. Read changed files
4. Run coding standards checklist
5. Check methodology compliance (if specified in task doc)
6. Classify deviations from the plan
7. Write Implementation Notes to task document
       ↓
┌─── Result ───────────────┐
│                          │
▼ PASS                     ▼ FAIL
Output SIGNAL, exit        Report issues, output SIGNAL, exit

Step 1: Read Context

  • Resolve task ID → read docs/task/{ID}-{task-name}.md
  • Focus on: ## Development Approach, ## Acceptance Criteria, ## File Changes
  • Identify actually changed files: git diff --name-only main...HEAD
  • Read only the changed files — not the entire codebase

Step 2: Coding Standards

Review each changed file:

TypeScript / JavaScript

  • No any types — use proper types, generics, or unknown
  • No unused variables or imports
  • Named constants for magic strings/numbers
  • Early returns / guard clauses — avoid nesting deeper than 3 levels
  • Functions do one thing (single responsibility)
  • Functions fit in ~30 lines (soft limit)
  • Descriptive names — functions read as sentences (getUserByEmail, not getUser)
  • No commented-out code
  • No console.log in production paths

React / UI (if applicable)

  • Components have explicit Props types
  • Hooks called before any early returns
  • Loading, error, and empty states handled
  • No unnecessary re-render triggers (inline anonymous functions in JSX)

General

  • No deep nesting — prefer flat logic and early exits
  • No duplicate logic — if same pattern appears 3+ times, extract it
  • Immutable patterns where possible

Step 3: Methodology Compliance

If task doc has ## Development Approach, validate against it:

  • TDD: Does implementation satisfy each acceptance criterion? Test files included if TDD specified?
  • CDD: Atomic components built before composites? Components independently usable?
  • SOLID: Single Responsibility — files/functions have one clear job? Dependency Inversion — dependencies injected, not hardcoded?

If no methodology specified, skip this step.


Step 4: Deviation Classification

Compare implementation against ## Acceptance Criteria and ## File Changes:

SeverityDefinitionAction
MinorDifferent approach, same outcome; extra helper extractedDocument in Implementation Notes, PASS
MediumPlan assumption wrong (API shape differs, component didn't exist); scope slightly off but requirements metDocument clearly, flag in summary, still PASS
MajorCore approach unworkable; requirements misunderstood; blocking dependency missingSTOP — write deviation summary, do NOT chain to /test

Step 5: Write Implementation Notes

Write (or update) this section in the task document:

## Implementation Notes

> **Simplify Review:** PASS | FAIL
> **Reviewed:** {Date}

### What was built
{Concrete description of behavior — what the user/system can now do}

### How to access for testing
- URL: {if applicable}
- Entry point: {button, page, API endpoint}
- Test credentials: {if auth involved}
- Setup required: {seed data, env vars, migrations}

### Deviations from plan
{None | Description of minor/medium deviations found}

### Standards check
{Pass | List any issues found and how they were resolved}

Step 6: Result

PASS

Auto mode — output SIGNAL and exit:

≡ SIGNAL
STAGE: simplify
STATUS: PASS
TASK: {ID}
SUMMARY: {deviations summary | "No deviations"}
REFERENCE: docs/task/{ID}-{task-name}.md ## Implementation Notes
≡ END

Manual mode: Run /clear before invoking /test {ID}.

FAIL — Standards Issues

Issues written to task doc ## Implementation Notes.

Auto mode — output SIGNAL and exit:

≡ SIGNAL
STAGE: simplify
STATUS: FAIL
TASK: {ID}
SUMMARY: {N} standards issues found
REFERENCE: docs/task/{ID}-{task-name}.md ## Implementation Notes
≡ END

Manual mode: Fix with /implement {ID}, then re-run /simplify {ID}.

FAIL — Major Deviation

Auto mode — output SIGNAL and exit:

≡ SIGNAL
STAGE: simplify
STATUS: BLOCKED
TASK: {ID}
SUMMARY: Major deviation — {one sentence}
REFERENCE: docs/task/{ID}-{task-name}.md ## Implementation Notes
≡ END

Manual mode: Present options — re-plan via /task, continue with documented deviation, or mark blocked in TASKS.md.


Auto Mode Behavior

When task document has Automation: auto, this skill is a worker — it does not chain to the next stage. The orchestrator (/implement auto) drives all routing.

  • PASS → output SIGNAL, exit
  • FAIL (standards) → write issues to task doc, output SIGNAL, exit
  • FAIL (major deviation) → output BLOCKED SIGNAL, exit

Retry Context

When invoked as part of a retry cycle, read the previous test report: docs/testing/{ID}-{task-name}.md

Verify the fix actually addresses the specific failure before proceeding:

### Retry context (attempt {N})
- Previous failure: {summary of what /test reported}
- Fix applied: {what /implement changed}
- Fix verified: Yes | Partial | No

If the fix does not address the previous failure, FAIL immediately.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.65%
按下载量换算90

Claude

30.31%
按下载量换算74

Cursor

17.63%
按下载量换算43

Gemini CLI

8.87%
按下载量换算22

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills