mirrors / superclaude-org--superclaude_framework

项目文件夹

superclaude-org--superclaude_framework
文件
master
T
Mithun Gowda B 116e9fc5f9 fix: fill implementation gaps across core modules (#544) 
* fix: fill implementation gaps across core modules

- Replace ConfidenceChecker placeholder methods with real implementations
  that search the codebase for duplicates, verify architecture docs exist,
  check research references, and validate root cause specificity
- Fix intelligent_execute() error capture: collect actual errors from
  failed tasks instead of hardcoded None, format tracebacks as strings,
  and fix variable shadowing bug where loop var overwrote task parameter
- Implement ReflexionPattern mindbase integration via HTTP API with
  graceful fallback when service is unavailable
- Fix .gitignore: remove duplicate entries, add explicit !-rules for
  .claude/settings.json and .claude/skills/, remove Tests/ ignore
- Remove unnecessary sys.path hack in cli/main.py
- Fix FailureEntry.from_dict to not mutate input dict
- Add comprehensive execution module tests: 62 new tests covering
  ParallelExecutor, ReflectionEngine, SelfCorrectionEngine, and the
  intelligent_execute orchestrator (136 total, all passing)

https://claude.ai/code/session_01AnGJMAA6Qp2j9WKKHHZfB9

* chore: include test-generated reflexion artifacts

https://claude.ai/code/session_01AnGJMAA6Qp2j9WKKHHZfB9

* fix: address 5 open GitHub issues (#536, #537, #531, #517, #534)

Security fixes:
- #536: Remove shell=True and user-controlled $SHELL from _run_command()
  to prevent arbitrary code execution. Use direct list-based subprocess.run
  without passing full os.environ to child processes.
- #537: Add SHA-256 integrity verification for downloaded docker-compose
  and mcp-config files. Downloads are deleted on hash mismatch. Gateway
  config supports pinned hashes via docker_compose_sha256/mcp_config_sha256.

Bug fixes:
- #531: Add agent file installation to `superclaude install` and `update`
  commands. 20 agent markdown files are now copied to ~/.claude/agents/
  alongside command installation.
- #517: Fix MCP env var flag from --env to -e for API key passthrough,
  matching the Claude CLI's expected format.

Usability:
- #534: Replace Japanese trigger phrases and report labels in pm-agent.md
  and pm.md (both src/ and plugins/) with English equivalents for
  international accessibility.

https://claude.ai/code/session_01AnGJMAA6Qp2j9WKKHHZfB9

* docs: align documentation with Claude Code and fix version/count gaps

- Update CLAUDE.md project structure to include agents/ (20 agents),
  modes/ (7 modes), commands/ (30 commands), skills/, hooks/, mcp/,
  and core/ directories. Add Claude Code integration points section.
- Fix version references: 4.1.5 -> 4.2.0 in installation.md,
  quick-start.md, and package.json (was 4.1.7)
- Fix feature counts across all docs:
  - Commands: 21 -> 30
  - Agents: 14/16 -> 20
  - Modes: 6 -> 7
  - MCP Servers: 6 -> 8
- Update README.md agent count from 16 to 20
- Add docs/user-guide/claude-code-integration.md explaining how
  SuperClaude maps to Claude Code's native features (commands,
  agents, hooks, skills, settings, MCP servers, pytest plugin)

https://claude.ai/code/session_01AnGJMAA6Qp2j9WKKHHZfB9

* chore: update test-generated reflexion log

https://claude.ai/code/session_01AnGJMAA6Qp2j9WKKHHZfB9

* docs: comprehensive Claude Code gap analysis and integration guide

- Rewrite docs/user-guide/claude-code-integration.md with full feature
  mapping: all 28 hook events, skills system with YAML frontmatter,
  5 settings scopes, permission rules, plan mode, extended thinking,
  agent teams, voice, desktop features, and session management.
  Includes detailed gap table showing where SuperClaude under-uses
  Claude Code capabilities (skills migration, hooks integration,
  plan mode, settings profiles).
- Add Claude Code native features section to CLAUDE.md with extension
  points we use vs should use more (hooks, skills, plan mode, settings)
- Add Claude Code integration gap analysis to KNOWLEDGE.md with
  prioritized action items for skills migration, hooks leverage,
  plan mode integration, and settings profiles

https://claude.ai/code/session_01AnGJMAA6Qp2j9WKKHHZfB9

* chore: update test-generated reflexion log

https://claude.ai/code/session_01AnGJMAA6Qp2j9WKKHHZfB9

* chore: bump version to 4.3.0

Bump version across all 15 files:
- VERSION, pyproject.toml, package.json
- src/superclaude/__init__.py, src/superclaude/__version__.py
- CLAUDE.md, PLANNING.md, TASK.md, CHANGELOG.md
- README.md, README-zh.md, README-ja.md, README-kr.md
- docs/getting-started/installation.md, quick-start.md
- docs/Development/pm-agent-integration.md

Also fixes __version__.py which was out of sync at 0.4.0.
Adds comprehensive CHANGELOG entry for v4.3.0.

https://claude.ai/code/session_01AnGJMAA6Qp2j9WKKHHZfB9

* i18n: replace all Japanese/Chinese text with English in source files

Replace CJK text with English across all non-translation files:

- src/superclaude/commands/pm.md: 38 Japanese strings in PDCA cycle,
  error handling patterns, anti-patterns, document templates
- src/superclaude/agents/pm-agent.md: 20 Japanese strings in PDCA
  phases, self-evaluation, documentation sections
- plugins/superclaude/: synced from src/ copies
- .github/workflows/readme-quality-check.yml: all Chinese comments,
  table headers, report strings, and PR comment text
- .github/workflows/pull-sync-framework.yml: Japanese comment
- .github/PULL_REQUEST_TEMPLATE.md: complete rewrite from Japanese

Translation files (README-ja.md, docs/user-guide-jp/, etc.) are
intentionally kept in their respective languages.

https://claude.ai/code/session_01AnGJMAA6Qp2j9WKKHHZfB9

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-03-22 22:57:15 +05:30

492 行
10 KiB
Markdown
原始文件 永久链接 Blame 文件历史

<div align="center">
# 🚀 SuperClaude Quick Start Guide
### **Context Engineering Framework for Claude Code**
<p align="center">
<img src="https://img.shields.io/badge/Framework-Context_Engineering-purple?style=for-the-badge" alt="Framework">
<img src="https://img.shields.io/badge/Version-4.3.0-blue?style=for-the-badge" alt="Version">
<img src="https://img.shields.io/badge/Time_to_Start-5_Minutes-green?style=for-the-badge" alt="Quick Start">
</p>
> **💡 Key Insight**: SuperClaude doesn't replace Claude Code - it **configures and enhances** it through behavioral context injection
<p align="center">
<a href="#-how-it-works">How It Works</a> •
<a href="#-instant-start">Instant Start</a> •
<a href="#-core-components">Components</a> •
<a href="#-workflow-patterns">Workflows</a> •
<a href="#-when-to-use">When to Use</a>
</p>
</div>
---
<div align="center">
## 📊 **Framework Capabilities**
| **Commands** | **AI Agents** | **Behavioral Modes** | **MCP Servers** |
|:------------:|:-------------:|:-------------------:|:---------------:|
| **30** | **20** | **7** | **8** |
| `/sc:` triggers | Domain specialists | Context adaptation | Tool integration |
</div>
---
## 🎯 **How It Works**
<div align="center">
### **Framework Architecture Flow**
```
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ User Input │────>│ Claude Code │────>│ Context Files │
│ /sc:command │ │ Reads Context │ │ (.md behaviors)│
└─────────────────┘ └──────────────────┘ └─────────────────┘
│ │
▼ ▼
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Enhanced │<─────│ Behavioral │<────│ MCP Servers │
│ Response │ │ Activation │ │ (if configured) │
└─────────────────┘ └──────────────────┘ └─────────────────┘
```
**The Magic**: When you type `/sc:brainstorm`, Claude reads behavioral instructions from installed `.md` files and responds with enhanced capabilities
</div>
---
## ⚡ **Instant Start**
<div align="center">
### **5-Minute Journey from Installation to First Command**
</div>
<table>
<tr>
<th width="50%">📦 Step 1: Install (Terminal)</th>
<th width="50%">💬 Step 2: Use (Claude Code)</th>
</tr>
<tr>
<td valign="top">
```bash
# Quick install with pipx
pipx install SuperClaude && SuperClaude install
# Or traditional pip
pip install SuperClaude && SuperClaude install
# Or via npm
npm install -g @bifrost_inc/superclaude && superclaude install
```
</td>
<td valign="top">
```text
# Interactive discovery
/sc:brainstorm "web app for task management"
# Analyze existing code
/sc:analyze src/
# Generate implementation
/sc:implement "user authentication"
# Activate specialist
@agent-security "review auth flow"
```
</td>
</tr>
</table>
<details>
<summary><b>🎥 What Happens Behind the Scenes</b></summary>
1. **Context Loading**: Claude Code imports behavioral `.md` files via `CLAUDE.md`
2. **Pattern Recognition**: Recognizes `/sc:` and `@agent-` trigger patterns
3. **Behavioral Activation**: Applies corresponding instructions from context files
4. **MCP Integration**: Uses configured external tools when available
5. **Response Enhancement**: Follows framework patterns for comprehensive responses
</details>
---
## 🔧 **Core Components**
<div align="center">
### **Four Pillars of SuperClaude**
<table>
<tr>
<td align="center" width="25%">
### 📝 **Commands**
<h2>21</h2>
**Slash Commands**
`/sc:brainstorm`
`/sc:implement`
`/sc:analyze`
`/sc:workflow`
*Workflow automation*
</td>
<td align="center" width="25%">
### 🤖 **Agents**
<h2>14</h2>
**AI Specialists**
`@agent-architect`
`@agent-security`
`@agent-frontend`
`@agent-backend`
*Domain expertise*
</td>
<td align="center" width="25%">
### 🎯 **Modes**
<h2>6</h2>
**Behavioral Modes**
Brainstorming
Introspection
Orchestration
Task Management
*Context adaptation*
</td>
<td align="center" width="25%">
### 🔌 **MCP**
<h2>6</h2>
**Server Integration**
Context7 (docs)
Sequential (analysis)
Magic (UI)
Playwright (testing)
*Enhanced tools*
</td>
</tr>
</table>
</div>
---
## 📚 **Workflow Patterns**
<div align="center">
### **Complete Development Lifecycle**
</div>
### **🌟 First Project Session**
<table>
<tr>
<th>Step</th>
<th>Command</th>
<th>What Happens</th>
</tr>
<tr>
<td><b>1. Discovery</b></td>
<td><code>/sc:brainstorm "e-commerce app"</code></td>
<td>Interactive requirements exploration</td>
</tr>
<tr>
<td><b>2. Load Context</b></td>
<td><code>/sc:load src/</code></td>
<td>Import existing project structure</td>
</tr>
<tr>
<td><b>3. Analysis</b></td>
<td><code>/sc:analyze --focus architecture</code></td>
<td>Deep architectural review</td>
</tr>
<tr>
<td><b>4. Planning</b></td>
<td><code>/sc:workflow "payment integration"</code></td>
<td>Generate implementation roadmap</td>
</tr>
<tr>
<td><b>5. Implementation</b></td>
<td><code>/sc:implement "Stripe checkout"</code></td>
<td>Build with best practices</td>
</tr>
<tr>
<td><b>6. Validation</b></td>
<td><code>/sc:test --coverage</code></td>
<td>Comprehensive testing</td>
</tr>
<tr>
<td><b>7. Save Session</b></td>
<td><code>/sc:save "payment-complete"</code></td>
<td>Persist for next session</td>
</tr>
</table>
### **🎨 Domain-Specific Workflows**
<div align="center">
| Domain | Trigger | Specialist Activation | MCP Server |
|--------|---------|----------------------|------------|
| **Frontend** | UI component request | `@agent-frontend` | Magic |
| **Backend** | API endpoint creation | `@agent-backend` | Sequential |
| **Security** | Auth implementation | `@agent-security` | Context7 |
| **Testing** | E2E test scenarios | `@agent-qa` | Playwright |
| **DevOps** | Deployment setup | `@agent-devops` | Morphllm |
</div>
---
## 🎯 **When to Use**
<div align="center">
### **SuperClaude vs Standard Claude Code**
<table>
<tr>
<th width="50%">✅ Use SuperClaude</th>
<th width="50%">💭 Use Standard Claude</th>
</tr>
<tr>
<td valign="top">
**Perfect for:**
- 🏗️ Building complete software projects
- 📊 Systematic workflows with quality gates
- 🔄 Complex, multi-component systems
- 💾 Long-term projects needing persistence
- 👥 Team collaboration with standards
- 🎯 Domain-specific expertise needs
**Examples:**
- "Build a full-stack application"
- "Implement secure authentication"
- "Refactor legacy codebase"
- "Create comprehensive test suite"
</td>
<td valign="top">
**Better for:**
- 💡 Simple questions or explanations
- ⚡ One-off coding tasks
- 📚 Learning programming concepts
- 🧪 Quick prototypes or experiments
- 🔍 Code snippet generation
- ❓ General programming help
**Examples:**
- "Explain how async/await works"
- "Write a sorting function"
- "Debug this error message"
- "Convert this loop to functional"
</td>
</tr>
</table>
</div>
---
## 🎓 **Learning Path**
<div align="center">
### **Your 4-Week Journey to Mastery**
<table>
<tr>
<th>Week</th>
<th>Focus</th>
<th>Skills</th>
<th>Milestone</th>
</tr>
<tr>
<td align="center"><b>1</b><br/>🌱</td>
<td><b>Core Commands</b></td>
<td>
• <code>/sc:brainstorm</code><br/>
• <code>/sc:analyze</code><br/>
• <code>/sc:implement</code>
</td>
<td>Complete first project</td>
</tr>
<tr>
<td align="center"><b>2</b><br/>🌿</td>
<td><b>Behavioral Modes</b></td>
<td>
• Mode combinations<br/>
• Flag usage<br/>
• Context optimization
</td>
<td>Optimize workflows</td>
</tr>
<tr>
<td align="center"><b>3</b><br/>🌿</td>
<td><b>MCP Servers</b></td>
<td>
• Server configuration<br/>
• Tool integration<br/>
• Enhanced capabilities
</td>
<td>Full tool utilization</td>
</tr>
<tr>
<td align="center"><b>4</b><br/>🌲</td>
<td><b>Advanced Patterns</b></td>
<td>
• Custom workflows<br/>
• Session management<br/>
• Team patterns
</td>
<td>Framework mastery</td>
</tr>
</table>
</div>
---
## 💡 **Key Insights**
<div align="center">
### **Understanding SuperClaude's Value**
<table>
<tr>
<td width="33%" align="center">
### 🧠 **Not Software**
**It's a Framework**
SuperClaude is behavioral configuration, not standalone software. Everything runs through Claude Code.
</td>
<td width="33%" align="center">
### 🔄 **Systematic**
**Not Ad-hoc**
Transforms random requests into structured workflows with quality gates and validation.
</td>
<td width="33%" align="center">
### 🚀 **Progressive**
**Not Complex**
Start simple with basic commands. Complexity emerges naturally as needed.
</td>
</tr>
</table>
</div>
---
## 📖 **Next Steps**
<div align="center">
### **Continue Your Learning Journey**
<table>
<tr>
<th>🌱 Beginner</th>
<th>🌿 Intermediate</th>
<th>🌲 Advanced</th>
</tr>
<tr>
<td valign="top">
**First Week:**
- [Installation Guide](installation.md)
- [Commands Reference](../user-guide/commands.md)
- [Examples Cookbook](../reference/examples-cookbook.md)
Start with `/sc:brainstorm`
</td>
<td valign="top">
**Growing Skills:**
- [Behavioral Modes](../user-guide/modes.md)
- [Agents Guide](../user-guide/agents.md)
- [Session Management](../user-guide/session-management.md)
Explore mode combinations
</td>
<td valign="top">
**Expert Usage:**
- [MCP Servers](../user-guide/mcp-servers.md)
- [Technical Architecture](../developer-guide/technical-architecture.md)
- [Contributing](../developer-guide/contributing-code.md)
Create custom workflows
</td>
</tr>
</table>
<p align="center">
<a href="../user-guide/commands.md">
<img src="https://img.shields.io/badge/📚_Explore-All_21_Commands-blue?style=for-the-badge" alt="Commands">
</a>
<a href="../reference/examples-cookbook.md">
<img src="https://img.shields.io/badge/🍳_Try-Real_Examples-green?style=for-the-badge" alt="Examples">
</a>
</p>
</div>
---
<div align="center">
### **🎉 Ready to Transform Your Development Workflow?**
<p align="center">
<b>Start now with</b> <code>/sc:brainstorm</code> <b>in Claude Code!</b>
</p>
<p align="center">
<sub>SuperClaude v4.3.0 - Context Engineering for Claude Code</sub>
</p>
</div>
在新工单中引用 查看 Git Blame 复制永久链接