BC Schema Sleuth
Infer clean, production-ready schemas from messy sample data. Paste 1-5 examples of any data format — JSON, CSV, API responses, plain text, LLM output — and get back a Pydantic model, Zod schema, TypeScript interface, JSON Schema, and/or Go struct with correct types, nullability, optional fields, and validation rules inferred from the samples. Also detects dates, UUIDs, emails, URLs, enums, and nested objects. Zero external API required — pure inference. Triggers on "infer schema", "generate schema", "generate types", "pydantic from json", "zod from json", "typescript interface from", "what's the schema for", "/schema-sleuth".
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (Schema Sleuth) differs from the folder (phy-schema-sleuth)
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 26 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 3009 tokens
- low 11 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 634: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (13 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.