OpenSkillIndex← back to search
claude-codeopenclaw

Openclaw-superpowers executing-plans

Executes plans task-by-task with verification. Use when implementing a plan.

install
source · Clone the upstream repo
git clone https://github.com/ArchieIndian/openclaw-superpowers
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/ArchieIndian/openclaw-superpowers "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/core/executing-plans" ~/.claude/skills/archieindian-openclaw-superpowers-executing-plans && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/ArchieIndian/openclaw-superpowers "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/core/executing-plans" ~/.openclaw/skills/archieindian-openclaw-superpowers-executing-plans && rm -rf "$T"
manifest: skills/core/executing-plans/SKILL.md
source content

Executing Plans

The Loop

For each step:

  1. Read the step carefully
  2. Do exactly what the step says
  3. Verify the step is complete
  4. Mark it done: [x]
  5. Continue to next step

Rules

  • Stay on task. Note other issues, do not fix them mid-step.
  • Verify before continuing. 'I think that worked' is not verification.
  • Handle failures explicitly. Stop and diagnose before retrying.

OpenClaw Checkpointing

At checkpoint steps, update memory/YYYY-MM-DD.md with:

  • Which steps are done
  • Current state of the work
  • Any decisions made
  • Next step to resume from