mirror of
https://github.com/sweetwisdom/everything-claude-code-zh.git
synced 2026-03-22 06:20:10 +00:00
feat: package as Claude Code plugin with marketplace distribution
- Add .claude-plugin/plugin.json manifest for direct installation - Add .claude-plugin/marketplace.json for marketplace distribution - Reorganize skills to proper skill-name/SKILL.md format - Update hooks.json with relative paths for portability - Add new skills: continuous-learning, strategic-compact, eval-harness, verification-loop - Add new commands: checkpoint, eval, orchestrate, verify - Update README with plugin installation instructions Install via: /plugin marketplace add affaan-m/everything-claude-code /plugin install everything-claude-code@everything-claude-code
This commit is contained in:
63
skills/strategic-compact/SKILL.md
Normal file
63
skills/strategic-compact/SKILL.md
Normal file
@@ -0,0 +1,63 @@
|
||||
---
|
||||
name: strategic-compact
|
||||
description: Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
|
||||
---
|
||||
|
||||
# Strategic Compact Skill
|
||||
|
||||
Suggests manual `/compact` at strategic points in your workflow rather than relying on arbitrary auto-compaction.
|
||||
|
||||
## Why Strategic Compaction?
|
||||
|
||||
Auto-compaction triggers at arbitrary points:
|
||||
- Often mid-task, losing important context
|
||||
- No awareness of logical task boundaries
|
||||
- Can interrupt complex multi-step operations
|
||||
|
||||
Strategic compaction at logical boundaries:
|
||||
- **After exploration, before execution** - Compact research context, keep implementation plan
|
||||
- **After completing a milestone** - Fresh start for next phase
|
||||
- **Before major context shifts** - Clear exploration context before different task
|
||||
|
||||
## How It Works
|
||||
|
||||
The `suggest-compact.sh` script runs on PreToolUse (Edit/Write) and:
|
||||
|
||||
1. **Tracks tool calls** - Counts tool invocations in session
|
||||
2. **Threshold detection** - Suggests at configurable threshold (default: 50 calls)
|
||||
3. **Periodic reminders** - Reminds every 25 calls after threshold
|
||||
|
||||
## Hook Setup
|
||||
|
||||
Add to your `~/.claude/settings.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"hooks": {
|
||||
"PreToolUse": [{
|
||||
"matcher": "tool == \"Edit\" || tool == \"Write\"",
|
||||
"hooks": [{
|
||||
"type": "command",
|
||||
"command": "~/.claude/skills/strategic-compact/suggest-compact.sh"
|
||||
}]
|
||||
}]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
Environment variables:
|
||||
- `COMPACT_THRESHOLD` - Tool calls before first suggestion (default: 50)
|
||||
|
||||
## Best Practices
|
||||
|
||||
1. **Compact after planning** - Once plan is finalized, compact to start fresh
|
||||
2. **Compact after debugging** - Clear error-resolution context before continuing
|
||||
3. **Don't compact mid-implementation** - Preserve context for related changes
|
||||
4. **Read the suggestion** - The hook tells you *when*, you decide *if*
|
||||
|
||||
## Related
|
||||
|
||||
- [The Longform Guide](https://x.com/affaanmustafa/status/2014040193557471352) - Token optimization section
|
||||
- Memory persistence hooks - For state that survives compaction
|
||||
Reference in New Issue
Block a user