AC ask-human-expert
Ask real human experts a question through Instant Expert and get a written or voice answer or a short call. It finds executives, operators and domain specialists by description, or reaches one named person by name and company, LinkedIn URL or email, and sends each a paid ask. The buyer pays only if the person answers or books, and approves every live order first. Use when the agent or user needs first-hand knowledge that search can't give (how practitioners actually do something, an expert opinion, customer discovery or user interviews, feedback from a specific kind of professional), wants to reach a specific person, or wants to check replies to earlier asks. Starts in a free test mode with no account or card.
Ask real human experts a question through Instant Expert and get a written or voice answer or a short call.
As a process C 59/100 · Has gaps — weak spots: result and completion, 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-privilegescripts/ie.sh:105Privilege escalation / world-writable permissions (detector / deny-list definition; code comment)# scanners from reading the numeric mode as a setuid or root request.
detectorcomment
Files scanned: 4. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 19 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 39 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2995 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 719: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.