Pre action fact gate

Reusable AI agent skills, project templates, and guardrails for safer software maintenance and delivery.

Install

npx -y skills add jukrap/ai-agent-playbook --skill pre-action-fact-gate

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

Copied from the file, not written here

Use when risky edits need importers, schemas, owner search, blast radius, or rollback facts first.

1.2 KB, as published. Nobody here has run it

Use this as the primary AI harness skill for gathering concrete facts before broad, destructive, owner-creating, or high-blast-radius actions.

Restate the latest user intent, target action, target paths, risk type, and whether the action is advisory or applied.
Gather bounded facts: existing owners, importers/callers, public APIs, data schemas, contracts, nearby patterns, verification commands, and rollback path.
For new files or ownership changes, search for existing domain clusters, naming patterns, lifecycle owners, and deletion path before creating a new surface.
For destructive or applied actions, require explicit instruction, dry-run or write-gate preview evidence, resolved target list, and rollback evidence.

Read references/fact-gate-checks.md for bounded fact sets by action type and evidence standards.

Read references/destructive-action-review.md for deletes, moves, rewrites, migrations, publish/deploy actions, and write-tier escalation.