AB geotechnical-investigation-report-drafter
Use this skill when a geotechnical engineer or junior staff engineer needs to draft a subsurface investigation report for a building, infrastructure, or earthwork site. Guides field exploration logging, ASTM lab testing, ASCE 7 Site Class determination, and foundation/earthwork recommendations. Produces a DRAFT ten-section report with boring logs, lab data appendices, and an ASFE-style limitations statement for the Geotechnical Engineer of Record to verify, stamp, and seal.
Guides field exploration logging, ASTM lab testing, ASCE 7 Site Class determination, and foundation/earthwork recommendations.
As a process B 73/100 · 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5705 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 70Failures and branches. 6 branches
- 70Execution cost. Instruction body is 5705 tokens
- 85Steps. 77 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 10 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 478: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 77 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.