BB research-grill
Interviews a researcher in rounds until a research idea, design, or draft has no unexamined decision. Numbers every question, explains "why this matters", recommends an answer, fetches facts rather than asking for them, and records settled decisions. Three stages cover idea, a topic or hunch to a falsifiable question and contribution claim, design, a question to estimand, identification, sample and power, measurement, pre-registration, analysis plan, and venue, and defend, reviewer objections to a finished design or draft. Use when the user says "grill me", "grill this", "stress-test my idea/design/plan", "interview me about this project", "poke holes in this", "what am I assuming", or brings an idea that is not yet a design. Use `--plan` for software or process plans.
Interviews a researcher in rounds until a research idea, design, or draft has no unexamined decision.
As a process B 70/100 · Nearly there — weak spots: result and completion, failures and branches, running it twice
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
- 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
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Glob Grep Bash Write Edit Agent WebSearch WebFetch AskUserQuestion
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. 1 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1854 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 779: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.