BB Prisma
Designs Prisma schemas, writes type-safe queries, and fixes migrations, connection pools, and N+1 relation loads in Node and TypeScript. Use when editing schema.prisma, modeling relations, indexes, enums, JSON or Decimal columns, or choosing between db push, migrate dev and migrate deploy; when a migration drifts, fails, or would drop a column on rename, or a database needs baselining; on errors P2002, P2025, P2024, P2034 or P3009; when connections run out on Lambda, Vercel or behind PgBouncer; when queries are slow or include loads too much; on transaction timeouts, deadlocks and optimistic locking; when Decimal or BigInt break JSON.stringify; for $queryRaw and TypedSQL; when porting $use middleware to client extensions; when prisma generate fails in Docker, Alpine or CI; and for seeding and test isolation. Not for database-server tuning or hand-written SQL (pg, sql), or other ORMs.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 5699 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 59 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5699 tokens
- 100Steps. 60 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
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
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 896: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 60 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.