BB JSON
Parses, validates, transforms, and designs JSON payloads that survive real parsers, real clients, and real data sizes. Use when a parse fails at a byte offset or on a trailing comma, an id or an amount loses precision, accents and emoji come back as mojibake, a field is null when it should be absent, duplicate keys silently win, a JSON Schema passes what it should reject or a `$ref` will not resolve, a multi-gigabyte file will not fit in memory, a jq, JMESPath, or JSONPath expression returns nothing, two documents must be diffed or patched, a webhook signature fails after the body was re-serialized, untrusted input must be parsed safely, or a response shape has to change without breaking existing clients. Covers NDJSON, JSON Patch, canonical form, JSON columns in SQL, and JSON5/JSONC config files. Not for constraining LLM output (`structured-output`), for YAML, TOML, XML, or CSV (their own skills), or for designing REST endpoints (`rest-api`).
Parses, validates, transforms, and designs JSON payloads that survive real parsers, real clients, and real data sizes.
As a process B 72/100 · 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: 20. 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 ≈ 7312 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 72/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 7312 tokens
- 100Steps. 44 steps
- 100When it triggers. States when to use and when not to
- 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 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
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 957: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 14 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.