writing-plans
Writing Plans creates structured implementation blueprints with defined goals, approaches, ordered steps, risk mitigation, and completion criteria before development begins. Use this skill after brainstorming options but before writing code to prevent wasted effort and ensure clear, verifiable progress, especially for multi-session projects requiring checkpoint documentation.
git clone --depth 1 https://github.com/ArchieIndian/openclaw-superpowers /tmp/writing-plans && cp -r /tmp/writing-plans/skills/core/writing-plans ~/.claude/skills/writing-plansSKILL.md
# Writing Plans
Plans prevent wasted work. Write one before implementing anything significant.
## Plan Format
1. **Goal** - one sentence, what success looks like
2. **Approach** - which option from brainstorming, and why
3. **Steps** - ordered list, each step verifiable
4. **Risks** - what could go wrong, and mitigation
5. **Definition of Done** - how you'll know it's complete
## OpenClaw-Specific: Checkpoint Steps
For tasks that may span multiple sessions, add explicit checkpoint steps:
[ ] Step 3: Create the API endpoint [CHECKPOINT - save progress here]
At each checkpoint, update memory/YYYY-MM-DD.md with current state.Syncs agent daily memory and MEMORY.md to an Obsidian vault so notes are human-browsable. Use nightly or on demand.
Structured ideation before any implementation. Use when starting any non-trivial task.
Scaffolds and validates new superpowers skills. Use when creating a new skill for this repository.
Executes plans task-by-task with verification. Use when implementing a plan.
Triggers a secondary verification pass for any agent output containing factual claims, numbers, dates, or named entities before the output is acted on
Crawls a new codebase to infer stack, conventions, and key invariants, then generates a PROJECT.md context file for the agent
Handles PR review feedback by fetching comments, grouping issues, fixing one group at a time, and verifying before replies.
Detects skill name shadowing and description-overlap conflicts that cause OpenClaw to trigger the wrong skill or silently ignore one when two skills compete for the same intent.