AB defluff
Reverse the AI in corporate email. Detect whether a message was written by AI, AI-assisted, or by a human. When AI was involved, guess the prompt the sender probably gave an LLM. Classify urgency, extract the actual intent, name scam patterns (invoice fraud / BEC, phishing, fake recruiters, conference scams, crypto / MLM pitches). Output mirrors the email's language. Handles single messages, threads, and batches.
As a process B 74/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "displayName"
Process rating: all ten parameters 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 14 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
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3019 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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 416: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 24 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.