Conciseness

The body is dense, gotcha-driven, and assumes Claude's competence (e.g., "Raw mode... forbids `build:` and external file mounts"), with no padding or explanations of known concepts. Not 5 because the time-sensitive version pin "Requires Coolify ≥ v4.0.0-beta.411" sits inline rather than in a deprecated/old-patterns section, which the rubric penalizes.

Actionability

Gives concrete tool calls with arguments (`env_vars` → `control action="restart"`, `database_backups action="create"` with cron `frequency` + `retention`) and a copy-paste-ready curl webhook command. Not 5 because complete MCP invocation examples are absent — e.g., no full call syntax or argument shape for `deploy`, `diagnose_app`, or `bulk_env_update`, leaving minor gaps.

Workflow Clarity

An entry point exists ("Start every session with `get_infrastructure_overview`") and the env-var change sequence is ordered, but the skill explicitly covers batch and destructive operations (`bulk_env_update`, restarts, deleting `ports:`) with no validate-then-verify loop after deploys or batch updates. Per the rubric's cap, batch/destructive workflows without validation steps cannot score above 3; the single error-recovery hint ("check `docker ps`") is not a general checkpoint.

Progressive Disclosure

At ~25 lines with no bundle files (references/, scripts/, assets/ absent) and no need for external references, the skill qualifies for the simple-skill exception: well-organized sections (MCP tools, Docker Compose gotchas) plus a single external docs link make navigation trivial.

Specificity

Lists several concrete actions — "Deploys and manages apps, databases and services", "env vars, diagnostics and batch operations" — going well beyond the 1-2 actions of a score-3 anchor. Not 5 because body topics like Docker Compose gotchas, backups, and deploy webhooks are absent from the description, leaving minor coverage gaps.

Completeness

Explicitly answers both questions: the "what" ("Deploys and manages apps, databases and services... with env vars, diagnostics and batch operations") and a concrete "Use when deploying to Coolify, debugging a Coolify deployment, or managing its servers" trigger clause, matching the score-5 anchor pattern.

Trigger Term Quality

Triggers use natural phrasing users would say: "deploying to Coolify", "debugging a Coolify deployment", "managing its servers". Not 5 because common variations such as "self-hosted", "redeploy", "restart", or "add a database" are missing; not 3 since the terms present are specific and natural rather than generic.

Distinctiveness Conflict Risk

"self-hosted Coolify instance" carves out a clear niche and every trigger names Coolify explicitly, so it is unlikely to fire for unrelated deployment or database skills — minimal conflict risk per the score-5 anchor.