Token导航 LogoToken导航

Agent Skill · 待分类

core-workflow(核心工作流程)

core-workflow 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。

core-workflow 是待分类类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为权限未标注;许可证信息还不明确,第三方扫描已通过,按安装量在待分类类的 11,209 个 Skill 里排第 2,634。

总安装 1,469周安装 60GitHub Stars 48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
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:core-workflow(核心工作流程)
来源仓库:https://github.com/travisjneuman/.claude
仓库路径:skills/core-workflow
安装命令:
npx skills add https://github.com/travisjneuman/.claude --skill core-workflow
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/travisjneuman/.claude --skill core-workflow

这个 Skill 是做什么的

这个 Skill 的分类还没最终确定,用法以来源仓库的说明为准。

core-workflow 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。它作为中央资源枢纽,加载章节模板、输出脚手架和脚本工具以支持 ISD 生成流程。

使用时需结合来源仓库路径和原始 README 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。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/core-workflow

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/travisjneuman/.claude --skill core-workflow;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

    权限没有明确标注,第一次使用时只给一个无关紧要的任务,观察它到底读了哪些文件和网络。

常见问题

6 条

core-workflow 怎么安装?

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

core-workflow 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。

core-workflow 需要什么权限?

权限级别没有明确标注。第一次使用时建议只给无关紧要的任务,观察它实际读写了哪些内容。

core-workflow 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。

core-workflow 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 48 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。

core-workflow 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。
  • 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

  • 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。
  • 需要处理待分类类任务、又不想每次都手写提示词的人。

不太适合

  • 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。

待分类类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
infsh-cli

infsh CLI · Codex、Claude

4,374,576382权限未标注未明确未收录
ai-video-generation

AI 视频生成 · Codex、Claude

4,313,376382调用外部服务未明确有提醒
lark-openapi-explorer

云雀 OpenAPI 浏览器 · Codex、Claude

2,064,1209,011需要联网未明确有提醒
lark-workflow-standup-report

Lark 工作流程站立报告 · Codex、Claude

2,041,6328,978需要联网未明确通过
use-my-browser

使用我的浏览器 · Codex、Claude

1,848,49140操作浏览器未明确未通过
core-workflow

核心工作流程 · 本页

1,46948权限未标注未明确通过

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

name
core-workflow
description
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, testing strategy, and communication standards.

Core Workflow Patterns

Comprehensive development workflow reference. This loads on-demand for detailed patterns.

Quick links to rules: ~/.claude/rules/ for stack-specific and task-type checklists.


Session Protocol

Start Checklist

# 1. Sync with remote (ALWAYS FIRST)
git fetch origin main && git merge origin/main --no-edit
# or: git fetch origin master && git merge origin/master --no-edit

# 2. Get context
git log -3

# 3. Check for existing work
ls tasks/*.md 2>/dev/null || echo "No active tasks"

CRITICAL: Check <env> section for today's date. NEVER guess dates.

End Checklist

# 1. Verify
npm run test && npm run type-check  # or project equivalent

# 2. Archive completed work
mv tasks/<completed-task>.md .archive/completed-tasks/

# 3. Commit with comprehensive message
git add .
git commit  # See Git Conventions below
git push origin main

Stop dev server after testing: lsof -ti:PORT | xargs kill (or Windows equivalent)


GSD (Get Shit Done) - Multi-Phase Projects

For complex features spanning days/weeks, use GSD.

When to Use GSD

ComplexityUse GSD?Workflow
Simple fix (<30 min)NoDirect execution
Single feature (30min-2hr)NoTask file + TodoWrite
Multi-phase feature (days)YesGSD workflow
New project/appYesGSD from start

GSD Quick Start

/gsd:new-project       # Initialize with brief + config
/gsd:create-roadmap    # Create phases and state tracking
/gsd:plan-phase 1      # Create detailed plan for phase
/gsd:execute-plan <path>  # Execute the plan

GSD Commands Reference

CommandPurpose
/gsd:progressCheck status, route to next action
/gsd:resume-workResume from previous session
/gsd:pause-workCreate handoff when pausing
/gsd:plan-phase <n>Create detailed phase plan
/gsd:execute-plan <path>Execute a PLAN.md
/gsd:add-phase <desc>Add phase to roadmap
/gsd:insert-phase <after> <desc>Insert urgent work
/gsd:complete-milestone <ver>Archive and tag release
/gsd:helpFull command reference

GSD File Structure

.planning/
├── PROJECT.md          # Vision and requirements
├── ROADMAP.md          # Phase breakdown
├── STATE.md            # Project memory (context accumulation)
├── config.json         # Workflow mode (interactive/yolo)
└── phases/
    └── 01-foundation/
        ├── 01-01-PLAN.md
        └── 01-01-SUMMARY.md

Git Conventions

Commit Types

feat | fix | refactor | perf | test | docs | chore

Commit Message Format

type: Short summary (50 chars max)

## What Changed
- File X: Added feature Y
- File Z: Updated config for A

## Why
- User requested feature Y
- Config A needed update

## Testing
- All tests passing
- Manual verification done

Auto-Commit on Task Completion

When a task or plan is complete, automatically commit without being asked.

Pre-Commit Checks
# 1. Check this is a user-owned repo (not external)
git remote get-url origin | grep -q "travisjneuman" && echo "OK: User repo"

# 2. Check push is not blocked
git remote get-url --push origin | grep -q "no_push" && echo "SKIP: External repo"
Rules
ConditionAction
User's own repoAuto-commit + push
External repo (no_push)Never commit - read-only
Submodule (external)Never commit - read-only
Uncommitted secrets detectedBlock - warn user

Security Checklist

Frontend

  • [ ] textContent not innerHTML
  • [ ] unknown type for external data
  • [ ] No exposed API keys
  • [ ] HTTPS for external requests
  • [ ] Input sanitization

Backend

  • [ ] Input validation on all endpoints
  • [ ] Auth guards on protected routes
  • [ ] Parameterized queries (no raw SQL)
  • [ ] Secrets in environment variables

Performance Targets

MetricTarget
Initial bundle<100KB gzipped
Page load<1s
Interaction latency<100ms
Lighthouse Performance95+
AccessibilityWCAG AA minimum

Accessibility (WCAG AA)

  • [ ] Semantic HTML structure
  • [ ] Alt text for meaningful images
  • [ ] Keyboard navigation (Tab, Enter, Escape)
  • [ ] Focus indicators visible
  • [ ] Color contrast >= 4.5:1
  • [ ] ARIA labels on interactive elements
  • [ ] Touch targets >= 44x44px

Testing Strategy

TypeLocationWhen
Unitsrc/**/__tests__/Every function
ComponentSameEvery component
Integrationtests/integration/Critical paths
E2Etests/e2e/Before release

Before committing: npm run test && npm run type-check


Thinking Frameworks

Use structured decision-making for complex choices:

Decision TypeFramework
Long-term implications/consider:10-10-10
Root cause analysis/consider:5-whys
Prioritization/consider:eisenhower-matrix
Innovation/consider:first-principles
Risk identification/consider:inversion
Simplification/consider:occams-razor
Focus/consider:one-thing
Tradeoffs/consider:opportunity-cost
Optimization/consider:pareto
Consequences/consider:second-order

Debugging Protocol

Standard Issues

  1. Reproduce the issue
  2. Read relevant code
  3. Identify root cause
  4. Fix + add test
  5. Verify fix

Intermittent/Complex Issues

Use debug-like-expert skill for systematic approach.


Build vs Buy Philosophy

We build features. We use utilities.

  • Build: All feature logic, business rules, UI/UX, data models
  • Use: Low-level abstractions (D3, Recharts, Lexical, Konva)
  • Criterion: We own the feature, library handles complexity

License Requirements

  • Must use: MIT, Apache 2.0, BSD
  • Never use: GPL, AGPL (blocks commercialization)

Communication Standards

Progress Updates

Give high-level updates, not spam:

✅ Added authentication middleware (3 files)
✅ Updated user store with new fields
⏳ Testing login flow...

When to Ask

Use AskUserQuestion when:

  • Requirements are ambiguous
  • Multiple valid architectures exist
  • Scope might expand
  • Design decisions need validation

Directness Protocol

  • Logic over feelings
  • Correctness over validation
  • Direct feedback over diplomacy
  • Best solution over agreement

Context Hygiene

Reduce Token Usage

  • Short, high-signal summaries over long logs
  • Don't @-embed large docs by default
  • Reference paths + when to read them
  • Use /clear after completing work units

Delegation Patterns

SituationAction
Context >100k tokensCreate prompt → delegate to fresh context
Moderate complexity/create-prompt → /run-prompt
Multi-stage features/create-meta-prompt
Approaching limits/whats-next for handoff document

Quick Reference

Common Commands

npm run dev          # Start dev server
npm run build        # Production build
npm run test         # Run tests
npm run type-check   # TypeScript check

File Naming

TypeConventionExample
ComponentsPascalCaseUserCard.tsx
Hooksuse prefixuseAuth.ts
UtilitiescamelCaseutils.ts
Tests.test.tsutils.test.ts

Resources

Official

Community


See Also

  • ~/.claude/rules/checklists/ - Task-type specific checklists
  • ~/.claude/rules/stacks/ - Stack-specific patterns
  • ~/.claude/rules/tooling/ - Tool configuration guides
  • ~/.claude/skills/MASTER_INDEX.md - Full skills catalog
  • ~/.claude/agents/README.md - Agents directory

平台分布

Codex

34.44%
按下载量换算162

Claude

28.99%
按下载量换算136

Cursor

17.3%
按下载量换算81

Gemini CLI

9.48%
按下载量换算45

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

权限未标注

当前来源未能明确判断权限范围,默认进入异常复核队列。

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。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