Replace placeholder files with originals from system

Found and copied original files from ~/.claude installation:

- hooks/ - Original Qwen and Ralph hook scripts with full functionality
- commands/ - Original command definitions (brainstorm, write-plan, execute-plan)
- bin/ralphloop - Original 223-line Python wrapper (6,290 bytes)
- scripts/sync-agents.sh - Original sync script with GitHub/Gitea backup
- templates/ - Original config templates from working installation
- plugins/ - Original comprehensive plugin README

Files sourced from:
- ~/.claude/skills/skills/hooks/
- ~/.claude/skills/skills/commands/
- ~/.claude/skills/skills/templates/
- /home/uroma/obsidian-web-interface/bin/ralphloop
- ~/.claude/agents/sync-agents.sh

These are the production files from the working Claude Code
installation, replacing the placeholder files I created earlier.

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
uroma
2026-01-23 18:23:28 +00:00
Unverified
parent 62bec9d554
commit 932529d37f
21 changed files with 1439 additions and 898 deletions

View File

@@ -1,44 +1,6 @@
# /brainstorm
---
description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements and design before implementation."
disable-model-invocation: true
---
Multi-AI brainstorming session with Ralph integration.
## Usage
```
/brainstorm "Design a feature for user authentication"
```
## Description
Launches a collaborative brainstorming session using multiple AI perspectives:
- Claude (primary)
- Qwen (consultation)
- Ralph Orchestrator (autonomous iteration)
## Modes
**Direct Mode** (simple tasks):
- Quick ideation
- Feature exploration
- Design discussions
**Ralph Mode** (complex tasks):
- Architecture design
- System planning
- Multi-phase projects
## Environment Variables
```bash
QWEN_CONSULT_MODE=always|delegate|off
RALPH_AUTO=true|false
QWEN_MAX_ITERATIONS=3
```
## Examples
```
/brainstorm "How should we structure the API?"
/brainstorm "Design a notification system"
/brainstorm "Plan the database schema"
```
Invoke the superpowers:brainstorming skill and follow it exactly as presented to you

View File

@@ -1,52 +1,6 @@
# /execute-plan
---
description: Execute plan in batches with review checkpoints
disable-model-invocation: true
---
Execute a previously created implementation plan.
## Usage
```
/execute-plan
/execute-plan my-plan.md
/execute-plan --review
```
## Description
Executes implementation plans created with `/write-plan`:
- Reads plan from `.claude/plans/`
- Executes each step in order
- Creates checkpoints for rollback
- Validates each step completion
## Options
```
--review # Review plan before executing
--from=N # Start from step N
--to=N # Execute through step N
--dry-run # Show what would be done
--continue # Continue after error
```
## Execution Process
1. **Load Plan** - Read and parse plan file
2. **Review** (optional) - Show steps and confirm
3. **Execute** - Run each step sequentially
4. **Validate** - Verify each step completed
5. **Checkpoint** - Save progress after each step
6. **Report** - Summary of changes
## Examples
```
/execute-plan # Execute latest plan
/execute-plan auth-plan.md # Execute specific plan
/execute-plan --review # Review before executing
/execute-plan --from=5 # Start from step 5
```
## Checkpoints
Each step creates a checkpoint in `.claude/plans/<plan-name>.checkpoint/`
Use `--continue` to resume from last checkpoint after failure.
Invoke the superpowers:executing-plans skill and follow it exactly as presented to you

View File

@@ -1,40 +1,6 @@
# /write-plan
---
description: Create detailed implementation plan with bite-sized tasks
disable-model-invocation: true
---
Create implementation plans from requirements or specifications.
## Usage
```
/write-plan "Add user authentication with OAuth"
```
## Description
Creates detailed, step-by-step implementation plans including:
- Technical approach
- File changes needed
- Testing strategy
- Dependencies
- Risks and mitigations
## Plan Structure
1. **Summary** - High-level overview
2. **Technical Approach** - Architecture decisions
3. **Implementation Steps** - Ordered task list
4. **Files to Create/Modify** - Specific files
5. **Testing Strategy** - Validation approach
6. **Dependencies** - Required packages/changes
7. **Risks & Mitigations** - Potential issues
## Examples
```
/write-plan "Implement Stripe subscriptions"
/write-plan "Add real-time notifications with WebSockets"
/write-plan "Migrate from REST to GraphQL"
```
## Output
Saves plan to `.claude/plans/` directory for later execution with `/execute-plan`.
Invoke the superpowers:writing-plans skill and follow it exactly as presented to you