reflect

读凭据执行命令改身份文件写文件联网严重 1 · 高危 23haddock-development/claude-reflect-system

它会碰到什么

扫了多少21 个文本文件，133 KB

它会碰到什么读凭据执行命令改身份文件写文件联网

命中总数34 处

命中统计严重 1 · 高 23 · 中 8 · 低 1

逐条看命中（24 条严重或高危）

严重 scripts/scope_analyzer.py:28cred-paths
```
(r'\.env\.', 2),
```
高 scripts/extract_signals.py:249cred-envread
```
if os.getenv('TRANSCRIPT_PATH'):
```
高 scripts/extract_signals.py:250cred-envread
```
return os.getenv('TRANSCRIPT_PATH')
```

高 scripts/extract_signals.py:252cred-envread

session_dir = Path(os.getenv('SESSION_DIR', Path.home() / '.claude' / 'session-env')).expanduser()

高 scripts/learning_ledger.py:88exec-spawn
```
result = subprocess.run(
```

高 scripts/promote_learning.py:3identity-write

Promote Learning - Move skill-level learnings to global CLAUDE.md

高 scripts/promote_learning.py:6identity-write
```
for promotion to the global CLAUDE.md file.
```

高 scripts/promote_learning.py:25identity-write

GLOBAL_CLAUDE_MD = Path.home() / ".claude" / "CLAUDE.md"

高 scripts/promote_learning.py:44identity-write

"""Preview what would be added to CLAUDE.md."""

高 scripts/promote_learning.py:56identity-write
```
# Generate the entry for CLAUDE.md
```
高 scripts/promote_learning.py:69identity-write
```
"""Format learning as CLAUDE.md entry."""
```

高 scripts/promote_learning.py:89identity-write

backup_path = BACKUP_DIR / f"CLAUDE.md.{timestamp}.bak"

高 scripts/promote_learning.py:95identity-write
```
"""Promote a learning to global CLAUDE.md."""
```
高 scripts/promote_learning.py:121identity-write
```
# Append to CLAUDE.md
```

高 scripts/reflect.py:24cred-envread

transcript_path = os.getenv('TRANSCRIPT_PATH') or (sys.argv[1] if len(sys.argv) > 1 else None)

高 scripts/reflect.py:114cred-envread

session_id = os.getenv('SESSION_ID', 'unknown')

高 scripts/reflect.py:115cred-envread

auto_reflected = os.getenv('AUTO_REFLECTED', 'false')

高 scripts/reflect.py:126exec-spawn

subprocess.run(['git', 'add', '.'], cwd=skills_dir, check=True, capture_output=True)

高 scripts/reflect.py:129exec-spawn

subprocess.run(['git', 'commit', '-m', commit_message], cwd=skills_dir, check=True, capture_output=True)

高 scripts/semantic_detector.py:83exec-spawn
```
result = subprocess.run(
```

高 USER_GUIDE.md:587identity-config-write

cat ~/.claude/settings.local.json | grep -A 10 hooks

高 USER_GUIDE.md:591identity-config-write
```
"hooks": {
```
高 USER_GUIDE.md:593identity-config-write
```
"hooks": [{
```

高 USER_GUIDE.md:986identity-config-write

~/.claude/settings.local.json          # Hook-Konfiguration

这一栏是扫描器报的事实，不是结论。命中多不等于有毒（安全工具、规则库、示例脚本本来就会包含危险写法），命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系，需要你自己看。

技能内容

Reflect - Self-Improving Skills

Overview

This skill enables Claude Code to learn from conversations by analyzing corrections,

approvals, and patterns, then proposing updates to relevant skills. It implements

a "correct once, never again" learning system.

Usage Modes

1. Manual Reflection (/reflect)

Trigger analysis of the current conversation:

/reflect [skill-name]

Without skill-name: Analyzes all skills used in conversation
With skill-name: Focuses on specific skill

2. Automatic Reflection

When enabled via /reflect-on, runs automatically at session end via Stop hook.

3. Toggle Commands

/reflect-on - Enable automatic reflection
/reflect-off - Disable automatic reflection
/reflect-status - Show current configuration

Confidence Levels

HIGH - Explicit corrections:

User contradicts Claude's approach with specific alternative
Pattern: "Don't do X, do Y instead"
Action: Direct updates with deprecation warnings

MEDIUM - Approvals and patterns:

User approves specific approach
Pattern succeeds multiple times
Action: Add to "Best Practices" section

LOW - Observations:

User questions or suggests alternatives
Pattern: "Have you considered..." or "Why not try..."
Action: Add to "Considerations" section

Workflow

Signal Detection - Scan transcript for corrections/patterns
Context Analysis - Extract 5-message context around signals
Skill Mapping - Match signals to relevant skills
Change Proposal - Generate diff of proposed updates
User Review - Interactive approval with natural language editing
Application - Safe YAML/markdown updates with backups
Git Commit - Automatic commit with descriptive message

Scripts

Core Engine

scripts/reflect.py - Main orchestration logic
scripts/extract_signals.py - Pattern detection engine
scripts/update_skill.py - Safe skill file updates
scripts/present_review.py - Interactive review interface

Automation

scripts/hook-stop.sh - Stop hook integration
scripts/toggle-on.sh - Enable auto-reflection
scripts/toggle-off.sh - Disable auto-reflection
scripts/toggle-status.sh - Show status

Safety Features

Timestamped backups before all edits
YAML validation before writing
Lock files prevent concurrent runs
Graceful error handling with rollback
Git status checks before commits

References

See references/signal-patterns.md for detailed pattern library.

想直接用这个技能？

本站把开放许可（MIT / Apache 等）的技能按仓库打包整理到网盘，点一下转存到你自己的网盘，不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接，不打包。

去原始仓库

它属于哪个仓库

仓库haddock-development/claude-reflect-system

星标★ 378

本站分层T2

该仓技能数2

原文件路径reflect/SKILL.md

同一个仓库里的其他技能

python-project-creator

看这个仓库的全部 2 个技能