BD experiment-audit
Audit experiment integrity before claiming results. Uses fresh-agent GPT-6-Astra review (same-family provisional in the base Codex mirror) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
Audit experiment integrity before claiming results.
As a process D 38/100 · Unfinished process — References files that are not bundled: ../shared-references/reviewer-backends.md
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
- The text references files that are not there: add them or drop the references.
- 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: Bash(*)allowed-tools: Bash(*) Read Write Edit Grep Glob mcp__antigravity__antigravity mcp__antigravity__antigravity-reply mcp__grok__grok mcp__grok__grok-reply mcp__claude-review__review mcp__claude-review__
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../shared-references/reviewer-backends.md
Process rating: all ten parameters 38/100
- 0Tools and files. 1 referenced file(s) missing: ../shared-references/reviewer-backends.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2824 tokens
- 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
- +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 2 example trigger phrases
- +3Description length 374: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.