AC doc-process
Document intelligence: categorize, autofill forms, analyze contracts, scan receipts/invoices, analyze bank statements, parse resumes/CVs, scan IDs/passports (MRZ), summarize medical records, redact PII (light/standard/full, 50+ rule types, global coverage), extract meeting minutes/action items, extract tables to CSV/JSON, translate documents, scan/dewarp document photos (edge detection, perspective correction, scan-quality output). Trigger: fill this form, autofill, review contract, red flags, scan receipt, log expense, bank statement, subscriptions, parse resume, scan passport, read id, lab report, redact, remove pii, anonymize, meeting minutes, action items, extract table, table to csv, translate, scan photo, make scanned, dewarp, correct perspective, what is this, analyze this.
As a process C 60/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Edit Bash Glob
Files scanned: 28. 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 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 65Failures and branches. 3 branches
- 70Execution cost. Instruction body is 4993 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- medium 6 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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)
- +3Output format is not stated: the model decides each time
- -31 of 10 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 791: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (14 of 14)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.