一键导入
一键导入
Kubernetes cluster operations via dot-ai CLI - natural language cluster queries, AI-powered deployment recommendations, issue troubleshooting and remediation, Day 2 operations (scale, update, rollback, delete), resources, namespaces, events, logs, organizational knowledge base (ingest, search, query), organizational patterns/policies/capabilities management, project scaffolding and repo audit, and session history and visualization. Run `dot-ai --help` for commands.
Create a release tag based on accumulated changelog fragments. Run when ready to cut a release.
Create a git worktree for PRD work with a descriptive branch name. Infers PRD from context or asks user.
| name | dot-ai-prd-start |
| description | Start working on a PRD implementation |
| user-invocable | true |
You are helping initiate active implementation work on a specific Product Requirements Document (PRD). This command sets up the implementation context (validates readiness, creates branch, prepares environment) then hands off to /prd-next for task identification.
IMPORTANT: Do NOT include time estimates or effort estimates in your responses. Focus on setup and readiness without speculating on duration.
If prdNumber argument is provided ({{prdNumber}}):
If prdNumber argument is NOT provided:
Check if PRD context is already clear from recent conversation:
Skip detection if recent conversation shows:
/prd-update-progress, /prd-start with specific PRDIf context is clear:
If context is unclear:
Auto-detect the target PRD using these context clues (in priority order):
Git Branch Analysis - Check current branch name for PRD patterns:
feature/prd-12-* → PRD 12prd-13-* → PRD 13feature/prd-* → Extract PRD numberRecent Git Commits - Look at recent commit messages for PRD references:
Git Status Analysis - Check modified/staged files for PRD clues:
prds/12-*.md → PRD 12Available PRDs Discovery - List all PRDs in prds/ directory
Fallback to User Choice - Only if context detection fails, ask user to specify
Detection Logic:
feature/prd-12-documentation-testing)If context detection fails, ask the user:
## Which PRD would you like to start implementing?
Please provide the PRD number (e.g., "12", "PRD 12", or "36").
**Not sure which PRD to work on?**
Execute `dot-ai:prds-get` prompt to see all available PRDs organized by priority and readiness.
**Your choice**: [Wait for user input]
Once PRD is identified:
prds/[issue-id]-[feature-name].mdBefore starting implementation, validate that the PRD is ready:
For documentation-first PRDs:
## PRD Readiness Check
- [ ] All functional requirements defined
- [ ] Success criteria measurable
- [ ] Dependencies available
- [ ] Documentation complete
- [ ] Integration points clear
- [ ] Implementation approach decided
If PRD is not ready: Inform the user what's missing and suggest they complete PRD planning first.
⚠️ MANDATORY: Complete this step BEFORE proceeding to Step 4
Assign the GitHub issue to yourself to signal that work is in progress:
gh issue edit [issue-id] --add-assignee @me
This prevents others from picking up the same PRD and working on it in parallel.
git branch --show-currentmain or master: Create and switch to feature branch:
git checkout -b feature/prd-[issue-id]-[feature-name]
You MUST display this confirmation before proceeding to Step 4:
## Environment Setup ✅
- **Assignee**: @[username] ✅
- **Branch**: `[current-branch-name]` ✅
- **Status**: [Created new branch / Already on correct branch / Staying on main (reason)]
DO NOT proceed to Step 4 until branch setup is confirmed.
Once the implementation context is set up, present this message to the user:
## Ready for Implementation 🚀
**PRD**: [PRD Name] (#[PRD Number])
**Assignee**: @[username]
**Branch**: `[branch-name]`
**Status**: Ready for development
---
To identify and start working on your first task, run `/prd-next`.
⚠️ STOP HERE - DO NOT:
/prd-next handles all task identification and implementation guidance.
This command should:
/prd-next for task identification/prd-next handles all task identification, implementation guidance, and progress tracking