Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/bias-detection
Assess systematic biases in the evidence body — publication bias, reporting bias, and selective outcome reporting. Budget: 40 studies, 40 effect sizes, 40 web searches.
3 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 5 comparable cases; this report requires 8.
A test case the skill fixed. Same model, same prompt, with and without the skill.
I am designing a meta-analytic study examining the cardiovascular impacts of GLP-1 receptor agonists. Before synthesizing the data, I need a structured bias detection strategy formatted as YAML. The plan should outline approaches for detecting small study effects, language and citation biases, registry-based outcome comparisons, selection modeling for sensitivity checks, and alignment with PRISMA guidelines.
| Checked | Without skill | With skill |
|---|---|---|
| The output uses protocol as the root YAML key rather than alternative top-level metadata wrappers. | Missed | Passed |
| The outcome reporting bias section specifies ROB-ME or ORBIT as detection tools. | Missed | Passed |
The instructions your model reads when the skill loads.
Design a protocol to systematically assess biases that threaten the validity of meta-analytic conclusions.
Bias in the evidence body (publication bias, outcome reporting bias, citation bias, time-lag bias, language bias) can invalidate pooled estimates. This strategy designs the complete bias detection and adjustment protocol — funnel plots, statistical tests, sensitivity analyses, and GRADE certainty downgrading.
| Resource | Floor | Target |
|---|---|---|
| Studies identified | 28 | 40 |
| Effect sizes extracted | 28 | 40 |
| Web searches | 28 | 40 |
| Bias domains assessed | 5 | 8 |
| Quality assessments | 20 | 40 |
Budget gate: cannot exit until 80% of floor met.
<HARD-GATE>
| Metric | Current | Floor | Target | Status |
|--------|---------|-------|--------|--------|
| Studies found | 0 | 28 | 40 | BLOCKED |
| Effect sizes planned | 0 | 28 | 40 | BLOCKED |
| Web searches done | 0 | 28 | 40 | BLOCKED |
| Bias domains assessed | 0 | 5 | 8 | BLOCKED |
| Quality assessed | 0 | 20 | 40 | BLOCKED |
</HARD-GATE>
| Tactic | When to Use |
|---|---|
| effect-size-extraction | Extract effect sizes with precision (SE, CI) |
| quality-assessment-protocol | Full RoB2 assessment per study |
test cases passed with the skill
More skills from the same source and nearby in the registry, with their headline benchmark lift.