Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Structures development work into staged, checkpoint-based execution. Defines success and failure criteria upfront, runs quality gates at each stage, and returns ranked findings with an action plan and fallback. Designed for migrations, risky refactors, or any task where reversibility and evidence matter.
Forces explicit assumptions, tradeoffs, and fallback plans before any action is taken, reducing the chance of unrecoverable mistakes during migrations or high-stakes changes.
When to use it
- Planning a database migration with rollback steps
- Turning rough notes into a sequenced deployment plan
- Breaking a risky refactor into safe, reversible checkpoints
- Reviewing infrastructure changes before a production cutover
- Auditing a codebase before a major version upgrade
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: I need to migrate our Postgres 12 database to Postgres 15 by end of week with minimal downtime.
- 1Define success criteria (zero data loss, under 5 minutes downtime) and failure conditions that trigger rollback
- 2Map the smallest valid execution path: dry run pg_upgrade on a copy before touching production
- 3Execute in checkpoints: schema diff, extension compatibility check, replication lag test
- 4Apply quality gates: confirm all checks pass before drafting production steps
- 5Return ranked findings, a today/this-week action plan, and a rollback command checklist
Staged migration plan with ranked risks, acceptance criteria per checkpoint, and a fallback restore procedure