AB coolify
Operate a Coolify self-hosted PaaS through the @masonator/coolify-mcp server. Use this skill whenever the user asks Claude to inspect, deploy, restart, debug, or manage anything on Coolify — including applications, databases, services, servers, projects, environments, deployments, environment variables, private keys, GitHub apps, teams, or cloud provider tokens. Trigger even when the user does not say the word "Coolify" but clearly refers to their self-hosted infra (e.g. "redeploy my-api", "why is my postgres down", "restart the staging app", "what's running on my Hetzner box"). Prefer this skill over generic shell or HTTP tools whenever Coolify MCP tools are available.
The skill wraps a Coolify MCP server to let Claude manage self-hosted infrastructure. Promises app deployment, database control, env vars, and service restarts through a single interface instead of shell commands and API calls.
One instruction file, 2094 tokens, no scripts, no critical issues. Safety 100, quality 90, process 66 — the last score hints at reproducibility or documentation gaps, but the skill itself works. Supports Claude, Cursor, DeepSeek, and eight other platforms.
Install if you run Coolify on your own server and want an AI agent to manage it. The skill triggers even without saying "Coolify" — just say "redeploy staging" or "why is Postgres down". Skip if you don't have Coolify running or use managed services like Vercel. Worth installing.
Operate a Coolify self-hosted PaaS through the @masonator/coolify-mcp server.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 41 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 39 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2094 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 678: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 39 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.