CtrlK
BlogDocsLog inGet started
Tessl Logo

confounder-and-bias-control-planner

Plans confounder control, variable adjustment logic, and bias mitigation strategies at the protocol stage for clinical, epidemiologic, translational, observational, and biomarker studies. Always use this skill when a user needs to identify major confounders, decide which variables should or should not be adjusted for, compare matching/stratification/weighting approaches, anticipate selection or measurement bias, or pressure-test a study design before execution. Focus on bias sensing, causal structure awareness, variable-role classification, and critical design review rather than generic statistical advice.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable instruction skill with excellent progressive disclosure via real, clearly-mapped reference modules. Its main weakness is redundancy — the same prohibitions and role distinctions are repeated across several sections.

Suggestions

Consolidate the repeated prohibition lists ('must not confuse', 'Hard Rules', 'What This Skill Should Not Do', 'Core Function should not') into a single canonical rules section to reduce token cost.

Add one short worked example of a completed output section (e.g., a filled Section F table) to make the actionable spec concrete.

Trim the overlapping variable-role descriptions between 'Variable Role Logic', 'Step 3', and Section B output guidance to a single source of truth.

DimensionReasoningScore

Conciseness

Mostly operational, but the same prohibitions are restated across 'This skill must not confuse', 'Core Function should not', 'Hard Rules', and 'What This Skill Should Not Do', creating several padded sections that could be consolidated.

3 / 5

Actionability

Highly concrete guidance for an instruction-only skill: an 8-step decision logic, Sections A–K with table column specs, a five-category handling taxonomy, and a ready out-of-scope redirect template, though no worked example of a completed section is provided.

4 / 5

Workflow Clarity

Steps 1–8 are clearly sequenced with input validation and a pressure-test/self-critical review checkpoint; minor gaps as the skill is planning rather than destructive/batch execution so the cap-3 rule does not bind.

4 / 5

Progressive Disclosure

All nine reference files exist and are signaled one level deep with explicit section mapping ('use when classifying variables in Sections B, C, and F'); the body is a lean overview pointing to the operational rules.

5 / 5

Total

16

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states capabilities and explicit trigger conditions for a well-scoped domain. Trigger-term coverage is the only soft spot, missing a few natural synonyms advanced users would say.

Suggestions

Add common user phrases such as 'overadjustment', 'collider bias', and 'propensity score' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — confounder control, variable adjustment logic, bias mitigation, matching/stratification/weighting comparison, and pressure-testing — with comprehensive coverage of the protocol-stage task.

5 / 5

Completeness

Explicitly answers both 'what' (plans confounder control, adjustment logic, bias mitigation at protocol stage) and 'when' ('Always use this skill when a user needs to...') with concrete trigger phrases, in third person.

5 / 5

Trigger Term Quality

Good coverage of natural terms users say ('confounders', 'which variables...adjust for', 'matching/stratification/weighting', 'selection/measurement bias'), but common variants like 'overadjustment', 'collider bias', and 'propensity score' are absent.

4 / 5

Distinctiveness Conflict Risk

A clear niche — protocol-stage confounder and bias control planning for biomedical studies — with distinct, specific triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.