prd-auto-executor
Skill0 starsChanged 9 months agoApache-2.0View on GitHub
Semi-automated PRD execution with Git safety and intelligent MCP selection
In this repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-councilSkill
- decision-workflowSkill
- deployment-checklistSkill
- frontend-designSkill
- implementation-workflowSkill
- mcp-management-workflowSkill
- mcp-selectorSkill
- multidimensional-analysisSkill
- prd-implementation-trackerSkill
- research-workflowSkill
- session-continuitySkill
The file
Files
prd-auto-executor Skill
Semi-automated PRD checklist execution with Git safety.
Mission
Execute PRD checklists with:
- Git checkpoint safety (automatic rollback on failure)
- SDD-style verification (test/build/lint)
- User approval at every step
- State persistence for session resume
Execution Flow
Phase 1: Initialize
- Load
execution_state.json(resume if exists) - Load checklist JSON from prd-implementation-tracker
Phase 2: Task Loop
FOR EACH task:
1. Create Git checkpoint
2. Request user approval (승인/건너뛰기/중단)
3. Execute task (Claude performs work)
4. Validate (npm test/build/lint)
5. Success → Git commit | Failure → Rollback
6. Save statePhase 3: Complete
- Summary report (completed/failed/skipped)
Safety Rules
| Rule | Description |
| Checkpoint First | Always create checkpoint BEFORE task |
| Rollback on Fail | Rollback on any validation failure |
| Save State | Save after every operation |
| Approval Required | Never auto-execute without approval |
Detailed protocol and examples: See prompt.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.