Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问clear审计提醒

sc-workflowSC 工作流程

Agent Skill

sc-workflow 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。

总安装

652

周安装

28

GitHub Stars

17

下载量

228
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

3

许可证

MIT

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:sc-workflow(SC 工作流程)
来源仓库:https://github.com/tony363/superclaude
仓库路径:skills/sc-workflow
安装命令:
npx skills add https://github.com/tony363/superclaude --skill sc-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。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/tony363/superclaude --skill sc-workflow

简介

sc-workflow 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装使用。
  • 安装前建议确认权限范围和维护状态,避免触发不必要的联网或文件操作。
  • 可结合原始 README 文档进一步核验具体用法和功能边界。

SKILL.md

Implementation Workflow Generator Skill

Transform PRDs and requirements into structured implementation plans.

Quick Start

# PRD-based workflow
/sc:workflow feature-spec.md --strategy systematic --depth deep

# Feature workflow
/sc:workflow "user auth system" --strategy agile --parallel

# Enterprise planning
/sc:workflow enterprise-prd.md --strategy enterprise --validate

Behavioral Flow

  1. Analyze - Parse PRD and feature specifications
  2. Plan - Generate workflow structure with dependencies
  3. Coordinate - Activate personas for domain expertise
  4. Execute - Create step-by-step workflows
  5. Validate - Apply quality gates and completeness checks

Flags

FlagTypeDefaultDescription
--strategystringsystematicsystematic, agile, enterprise
--depthstringnormalshallow, normal, deep
--parallelboolfalseEnable parallel task generation
--validateboolfalseInclude quality gates

Personas Activated

  • architect - System design and technical planning
  • analyzer - Requirements analysis
  • frontend - UI/UX implementation planning
  • backend - API and data layer planning
  • security - Security requirements integration
  • devops - Infrastructure and deployment planning
  • project-manager - Timeline and resource coordination

MCP Integration

PAL MCP (Planning & Validation)

ToolWhen to UsePurpose
mcp__pal__plannerComplex workflowsSequential planning with branching
mcp__pal__consensusHigh-risk decisionsMulti-model validation of approach
mcp__pal__thinkdeepArchitecture planningDeep analysis of system design
mcp__pal__chatClarificationGet second opinion on workflow structure

PAL Usage Patterns

# Plan complex workflow
mcp__pal__planner(
    step="Planning authentication system implementation workflow",
    step_number=1,
    total_steps=5,
    is_branch_point=True,
    branch_id="auth-approach-oauth"
)

# Validate architectural decisions
mcp__pal__consensus(
    models=[
        {"model": "gpt-5.2", "stance": "for"},
        {"model": "gemini-3-pro", "stance": "against"},
        {"model": "deepseek", "stance": "neutral"}
    ],
    step="Evaluate: Should auth be microservice or monolith module?"
)

# Deep analysis for enterprise planning
mcp__pal__thinkdeep(
    step="Analyzing compliance requirements for enterprise auth",
    hypothesis="SOC2 requires audit logging at every auth event",
    confidence="medium",
    focus_areas=["compliance", "security", "scalability"]
)

Rube MCP (Project Management)

ToolWhen to UsePurpose
mcp__rube__RUBE_SEARCH_TOOLSProject toolsFind Jira, Asana, Linear, Notion
mcp__rube__RUBE_MULTI_EXECUTE_TOOLBacklog creationCreate tasks, epics, stories
mcp__rube__RUBE_CREATE_PLANComplex workflowsGenerate execution plans
mcp__rube__RUBE_CREATE_UPDATE_RECIPEReusable workflowsSave workflow templates

Rube Usage Patterns

# Create backlog items from workflow
mcp__rube__RUBE_MULTI_EXECUTE_TOOL(tools=[
    {"tool_slug": "JIRA_CREATE_ISSUE", "arguments": {
        "project": "AUTH",
        "summary": "Implement OAuth2 provider integration",
        "issue_type": "Epic",
        "description": "## Scope\n- Google OAuth\n- GitHub OAuth\n- SAML support"
    }},
    {"tool_slug": "JIRA_CREATE_ISSUE", "arguments": {
        "project": "AUTH",
        "summary": "Set up JWT token generation",
        "issue_type": "Story",
        "description": "Implement JWT with refresh tokens"
    }},
    {"tool_slug": "JIRA_CREATE_ISSUE", "arguments": {
        "project": "AUTH",
        "summary": "Add rate limiting to auth endpoints",
        "issue_type": "Task"
    }}
])

# Notify team of new workflow
mcp__rube__RUBE_MULTI_EXECUTE_TOOL(tools=[
    {"tool_slug": "SLACK_SEND_MESSAGE", "arguments": {
        "channel": "#project-planning",
        "text": "New implementation workflow created: Authentication System\nEpic: AUTH-123\n5 stories, 12 tasks"
    }},
    {"tool_slug": "NOTION_CREATE_PAGE", "arguments": {
        "title": "Auth System Implementation Plan",
        "content": "## Phases\n1. OAuth Integration\n2. JWT Implementation\n3. Rate Limiting\n\n## Timeline\nSprint 1-3"
    }}
])

# Save workflow as reusable template
mcp__rube__RUBE_CREATE_UPDATE_RECIPE(
    name="Auth System Workflow Template",
    description="Standard workflow for implementing authentication systems",
    workflow_code="..."
)

Flags (Extended)

FlagTypeDefaultDescription
--pal-planboolfalseUse PAL planner for complex workflows
--consensusboolfalseValidate approach with multi-model consensus
--create-backlogboolfalseCreate backlog items via Rube
--notifystring-Notify via Rube (slack, teams, email)
--save-templateboolfalseSave as reusable Rube recipe

Evidence Requirements

This skill does NOT require hard evidence. Deliverables are:

  • Structured workflow documentation
  • Task dependency maps
  • Implementation phases

Workflow Strategies

Systematic (--strategy systematic)

  • Comprehensive task decomposition
  • Full dependency mapping
  • Documentation-heavy approach

Agile (--strategy agile)

  • Sprint-oriented planning
  • User story focused
  • Iterative milestones

Enterprise (--strategy enterprise)

  • Compliance integration
  • Stakeholder alignment
  • Risk assessment included

Workflow Components

Task Decomposition

  • Feature breakdown into implementable units
  • Clear acceptance criteria
  • Effort estimation

Dependency Mapping

  • Task prerequisites
  • Blocking relationships
  • Parallel execution opportunities

Quality Gates

  • Testing requirements
  • Review checkpoints
  • Deployment criteria

Examples

PRD Analysis

/sc:workflow docs/PRD/feature.md --strategy systematic --depth deep
# Full PRD parsing with comprehensive workflow
# Multi-persona coordination for complete plan

Feature Implementation

/sc:workflow "payment integration" --strategy agile --parallel
# Sprint-ready task breakdown
# Parallel frontend/backend tracks

Enterprise Planning

/sc:workflow enterprise-spec.md --strategy enterprise --validate
# Compliance-aware workflow
# Security and devops integration

Quick Planning

/sc:workflow "add search feature" --depth shallow
# Rapid task list generation
# High-level milestone planning

Output Structure

Workflows include:

  1. Overview - Feature summary and scope
  2. Phases - Implementation stages
  3. Tasks - Detailed work items
  4. Dependencies - Task relationships
  5. Milestones - Key checkpoints
  6. Risks - Identified concerns

Tool Coordination

  • Read/Write - PRD analysis and documentation
  • TodoWrite - Progress tracking
  • Task - Parallel workflow generation
  • WebSearch - Technology research

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

27.42%
按下载量换算63

Claude Code

24.86%
按下载量换算57

windsurf

16.6%
按下载量换算38

trae

12.21%
按下载量换算28

OpenCode

8.38%
按下载量换算19

Cursor

3.88%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。

来源信息

继续浏览同类 Skills