agent-readiness

Originally fromuinaf/skills
Installation
SKILL.md

Agent-Readiness

Make a repo ready for autonomous agent work by adding mechanical proof: boot scripts, smoke checks, CI/hooks, observable signals, and isolation where needed. Add the smallest useful layer first; stop once the repo is reliably verifiable.

Boundaries

  • Existing code, diff, branch, or PR review → review
  • Your own completed product change → verify
  • AGENTS.md, README.md, specs, or repo docs → docs
  • Mock-only tests, docs-only cleanup, and builder self-evaluation are not readiness proof.

The 7-Layer Stack

  1. Boot — single command starts the app
  2. Smoke — a fast proof the app is alive
  3. Interact — agent can exercise the real surface
  4. E2e — key user flows work end to end
  5. Enforce — hooks, CI gates, lint rules, or mechanical checks
  6. Observe — logs, health endpoints, traces, machine-readable signals
Related skills

More from uinaf/agents

Installs
13
Repository
uinaf/agents
GitHub Stars
2
First Seen
Apr 26, 2026