mit einem Klick
execute
Execute an implementation plan step by step
Menü
Execute an implementation plan step by step
This skill should be used when the user asks to "install openclaw", "set up openclaw", "configure openclaw channels", "openclaw gateway", "openclaw troubleshooting", "add whatsapp to openclaw", "add telegram to openclaw", "openclaw agent", "openclaw models", "openclaw cron", "openclaw memory", "openclaw skills", "openclaw security", "openclaw browser", "openclaw sessions", "openclaw workspace", "openclaw docker", "openclaw not working", "debug openclaw", "connect discord to openclaw", "openclaw setup guide", or mentions openclaw setup, configuration, troubleshooting, or daily usage.
Write BDD requirements in Gherkin format. Guides the user through the process.
Guided implementation planning with codebase understanding and requirement focus
Manage tech stack and architecture decisions
Document domain knowledge including entities, processes, and ubiquitous language
Manage product backlog as an ordered priority list
| name | execute |
| description | Execute an implementation plan step by step |
| argument-hint | Plan filename (e.g., user-registration) |
You are helping a developer implement a plan from docs/plans/. Follow the plan systematically, implementing each step while keeping the user informed and involved.
Goal: Read and understand the plan
Initial request: $ARGUMENTS
Actions:
docs/plans/Goal: Verify we're ready to implement
Actions:
Goal: Execute ALL steps from the plan autonomously
IMPORTANT: Execute the entire plan without stopping. Only stop if you hit a roadblock.
For each step:
Read all relevant files first
Implement the changes:
Mark step complete in todo list
Continue immediately to next step (do not wait for user)
STOP IMMEDIATELY if:
When stopping:
"I hit a roadblock at Step [X]:
[Clear description of the problem]
The plan expected [X] but I found [Y].
Options:
A) [Proposed solution]
B) [Alternative approach]
C) [Skip and continue]
What would you like to do?"
If NO roadblocks: Complete all steps, then proceed to Phase 4.
Goal: Ensure code is simple, DRY, elegant, and functionally correct
Actions:
Launch 3 code-reviewer agents in parallel with different focuses:
Consolidate findings and identify highest severity issues
Present findings to user:
"Code Review Results:
High Priority Issues:
1. [Issue] (file:line) - [why it matters]
Medium Priority:
1. [Issue] - [suggestion]
What would you like to do?
A) Fix high priority issues now
B) Fix all issues
C) Proceed without fixing"
Address issues based on user decision
Goal: Verify implementation meets requirements
Actions:
"Acceptance Criteria:
✓ [Criterion 1]
✓ [Criterion 2]
✗ [Criterion 3] - [issue]"
Goal: Wrap up and document
Actions:
"I'll execute the plan for [name].
Summary:
- [X] steps to implement
- Requirements: [REQ-IDs]
- Key files: [list]
I'll implement all steps and only stop if I hit a roadblock.
Ready to start?"
"I hit a roadblock at Step [X]:
[Clear description of problem]
The plan expected [X] but I found [Y].
Options:
A) [Proposed solution]
B) [Alternative approach]
C) [Skip and continue]
What would you like to do?"
"Got it. Continuing with the plan..."
[Resume autonomous execution]
"Code Review Results:
High Priority Issues:
1. Missing error handling in [file:line]
2. Potential memory leak in [file:line]
Medium Priority:
1. Could simplify [logic] in [file]
2. Consider extracting [component]
All tests pass. Code follows project conventions.
What would you like to do?
A) Fix high priority issues now
B) Fix all issues
C) Proceed without fixing"
"Implementation complete!
Steps completed: [X/X]
Created:
- [new files]
Modified:
- [changed files]
Acceptance Criteria: [X/Y] passing
Code Review: [X] issues fixed
Want me to commit these changes?"
When something doesn't match the plan: