BB adu-corrections-complete
Generates the final response package for ADU permit corrections — the second half of the corrections pipeline. This skill should be used after adu-corrections-flow has produced its analysis files and the contractor has answered questions. It reads the research artifacts (categorized corrections, state law findings, city research, sheet observations) plus contractor answers, and produces four deliverables — a response letter to the building department, a professional scope of work, a corrections status report, and per-sheet annotations. Triggers when a session directory contains corrections analysis files and a contractor_answers.json has been provided. This skill runs as a cold start — it has no conversation history from the analysis phase and relies entirely on the file artifacts.
Generates the final response package for ADU permit corrections — the second half of the corrections pipeline.
As a process B 70/100 · Nearly there — weak spots: failures and branches, running it twice, progress reporting
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 70/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 47 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2350 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 792: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 47 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.