Get the FREE Ultimate OpenClaw Setup Guide →

executing-plans

Scanned
npx machina-cli add skill parthalon025/autonomous-coding-toolkit/executing-plans --openclaw
Files (1)
SKILL.md
2.5 KB

Executing Plans

Overview

Load plan, review critically, execute tasks in batches, report for review between batches.

Core principle: Batch execution with checkpoints for architect review.

Announce at start: "I'm using the executing-plans skill to implement this plan."

The Process

Step 1: Load and Review Plan

  1. Read plan file
  2. Review critically - identify any questions or concerns about the plan
  3. If concerns: Raise them with your human partner before starting
  4. If no concerns: Create TodoWrite and proceed

Step 2: Execute Batch

Default: First 3 tasks

For each task:

  1. Mark as in_progress
  2. Follow each step exactly (plan has bite-sized steps)
  3. Run verifications as specified
  4. Mark as completed

Step 3: Report

When batch complete:

  • Show what was implemented
  • Show verification output
  • Say: "Ready for feedback."

Step 4: Continue

Based on feedback:

  • Apply changes if needed
  • Execute next batch
  • Repeat until complete

Step 5: Complete Development

After all tasks complete and verified:

  • Announce: "I'm using the finishing-a-development-branch skill to complete this work."
  • REQUIRED SUB-SKILL: Use superpowers:finishing-a-development-branch
  • Follow that skill to verify tests, present options, execute choice

When to Stop and Ask for Help

STOP executing immediately when:

  • Hit a blocker mid-batch (missing dependency, test fails, instruction unclear)
  • Plan has critical gaps preventing starting
  • You don't understand an instruction
  • Verification fails repeatedly

Ask for clarification rather than guessing.

When to Revisit Earlier Steps

Return to Review (Step 1) when:

  • Partner updates the plan based on your feedback
  • Fundamental approach needs rethinking

Don't force through blockers - stop and ask.

Remember

  • Review plan critically first
  • Follow plan steps exactly
  • Don't skip verifications
  • Reference skills when plan says to
  • Between batches: just report and wait
  • Stop when blocked, don't guess
  • Never start implementation on main/master branch without explicit user consent

Integration

Required workflow skills:

  • superpowers:using-git-worktrees - REQUIRED: Set up isolated workspace before starting
  • superpowers:writing-plans - Creates the plan this skill executes
  • superpowers:finishing-a-development-branch - Complete development after all tasks

Source

git clone https://github.com/parthalon025/autonomous-coding-toolkit/blob/main/skills/executing-plans/SKILL.mdView on GitHub

Overview

Executing Plans enables you to load a written implementation plan, review it critically, and execute tasks in batches with review checkpoints. It emphasizes clear communication at the start, batch-by-batch verification, and reporting between batches to keep stakeholders aligned. This approach reduces risk, ensures verifications, and makes progress auditable.

How This Skill Works

Step 1 loads the plan file, reviews it for questions or concerns, and creates a TodoWrite if the plan is clear. Step 2 executes the first batch (default 3 tasks), marking tasks in_progress, following each step, running verifications, and marking completed. Step 3 reports batch results, then waits for feedback before continuing with the next batch or finishing development using the designated finishing-a-development-branch skill.

When to Use It

  • You have a written implementation plan and want to execute it in a separate session with review checkpoints.
  • You prefer batch execution with checkpoints between batches to validate progress.
  • You need to surface concerns or questions about the plan before starting.
  • The plan may be updated after feedback and requires revisiting Step 1.
  • All tasks are completed and you’re ready to finish work via the development-branch workflow.

Quick Start

  1. Step 1: Load the plan file, review critically, and raise concerns if any.
  2. Step 2: Execute the first batch of up to three tasks, marking progress and running verifications.
  3. Step 3: Report batch results, show verifications, and await feedback (or proceed to next batch).

Best Practices

  • Review the plan critically before starting to catch gaps.
  • Follow the plan steps exactly and perform all verifications.
  • Announce at the start: "I'm using the executing-plans skill to implement this plan."
  • Execute in batches (default first 3 tasks) and report between batches.
  • Don't proceed if blocked; ask for clarification instead of guessing; reference skills when the plan calls for them.

Example Use Cases

  • Implement a feature according to a formal task plan, in batches with checkpoints.
  • Migrate data using a written plan, verifying each batch before continuing.
  • Refactor a module following a plan, with per-batch verifications and reviews.
  • Perform a UI overhaul in staged batches, reporting results and receiving feedback.
  • Apply CI/CD changes in an isolated branch, using plan-based steps and checks.

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers