Agent skill · luongnv89
website-agent-readiness
Scan a live site with isitagentready.com, then approve each step: triage the 0-5 agent-readiness score, write agent-ready-plan.md, file issues via /plan-to-issues. Don't use for applying llms.txt/SEO fixes (seo-ai-optimizer) or app-store ASO.
What it needs
About 10k tokens when loaded.
What this skill does
Website Agent Readiness Takes a website URL and produces a tracked backlog for making that site usable by AI agents. Four phases, each behind a human approval gate: It plans and files; it never fixes. No robots.txt is edited, no file is published to the target site. The output is a reviewed plan and a set of issues someone then works. When to use Trigger when the user asks to: Make a website agent-ready, or check whether a site is ready for AI agents Score a site on llms.txt / MCP / robots.txt / agent-protocol support and plan the gaps Turn an agent-readiness scan into a tracked backlog Do not use for: Applying the fixes to a site's codebase — that is /seo-ai-optimizer (it owns llms.txt, robots.txt, and AI-bot directives as edits). This skill stops at the plan. App Store / Play Store optimisation — /aso-marketing, /aso-audit. A plan you already have — go straight to /plan-to-issues <path.md>. Repo Sync Before Edits (mandatory) Phase 3 writes agent-ready-plan.md into the repo and Phase 4 files issues against it. Before Phase 3, sync the current branch: If the working tree is dirty, stash first, sync, then restore: If origin is missing or the rebase conflicts, stop and ask the user — do not continue with a partial sync. Not in a git repo at all? Phases 1–3 still run; write the plan to the working directory and report that Phase 4 needs a git repo with a GitHub remote. Dependency Preflight (mandatory) This skill invokes /plan-to-issues in Phase 4. Verify it before Phase 3 writes anything — a preflight that clears after the plan is written just moves the failure: Where asm is not on PATH, test the install directly: test -f "$HOME/.claude/skills/plan-to-issues/SKILL.md". /plan-to-issues carries its own chain — an authenticated gh and the issue-creator skill. Check them here too, or Phase 4 fails inside someone else's skill: On a miss, stop before Phase 3. Phases 1–2 are read-only and may still be reported. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills luongnv89/website-agent-readiness