AD neon
Overview of Neon, a complete set of cloud backend primitives for apps and agents, spanning Lakebase Postgres, Auth, the Data API, Object Storage, Compute Functions, and the AI Gateway. Start here to route to the right Neon skill, set up the CLI or MCP server, and follow the branch-first workflow. Use when "Neon" or "Lakebase Postgres" is mentioned, or when any of its individual capabilities are the trigger: "object storage" or "S3", "buckets", "serverless functions", "AI gateway", "call an LLM", "postgres", "database", or "backend".
Overview of Neon, a complete set of cloud backend primitives for apps and agents, spanning Lakebase Postgres, Auth, the Data API, Object Storage, Compute…
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5949 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 45/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 5949 tokens
- 85Steps. 32 steps, 3 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 538: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.