CtrlK
BlogDocsLog inGet started
Tessl Logo

prognostic-biomarker-protocol-designer

Designs discovery, modeling, and validation workflows for prognostic biomarkers in biomedical and clinical research. Always use this skill when the user needs a prognostic biomarker study blueprint rather than a diagnostic test protocol, predictive biomarker design, treatment recommendation, or a completed manuscript. Focus on endpoint family, follow-up horizon, time scale, candidate marker strategy, model-building logic, risk stratification framework, and internal/external validation requirements. Do not invent cohort size, event rate, assay readiness, literature support, or validation access.

63

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./awesome-med-research-skills/Protocol Design/prognostic-biomarker-protocol-designer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

The content is well-structured with excellent progressive disclosure (real one-level references mapped to sections) and a clear, actionable ten-step workflow plus a mandatory output structure. Its main weakness is verbosity from heavy duplication of the step list and prohibition rules across multiple sections.

Suggestions

Merge the "Core Function" list with the "Execution" steps to eliminate the duplicated ten-item sequence, or have Core Function point forward to Execution.

Consolidate the four overlapping prohibition lists ("This skill must not confuse", "This skill should not", "Study-Design Integrity Rules", "What This Skill Should Not Do") into a single Hard Rules section to remove padding.

Add an explicit final step that validates the completed A-L output against the Quality Standard checklist before finishing, which would also raise workflow_clarity.

DimensionReasoningScore

Conciseness

The body is noticeably verbose due to structural duplication: the ten core functions reappear as the ten Execution steps, and prohibitions are restated across four separate sections ("This skill must not confuse", "This skill should not", "Hard Rules / Study-Design Integrity", "What This Skill Should Not Do"), creating several padded sections.

2 / 5

Actionability

Guidance is concrete and specific: each execution step names its reference module and lists what to state, the A-L output structure defines each section's required contents, and formatting rules prescribe tables and necessary/recommended/optional splits; the minor gap is the absence of a worked example output section.

4 / 5

Workflow Clarity

A clearly sequenced ten-step workflow with per-step reference pointers, an input-validation gate (out-of-scope redirect and stop), a clarification gate, and a Quality Standard checklist, but the checklist is not wired into the execution as an explicit final validate-before-finish feedback loop, leaving a minor validation gap.

4 / 5

Progressive Disclosure

The body is an overview that delegates operational rules to eleven real, one-level-deep reference files, each clearly signaled in the Reference Module Integration section and mapped to specific output sections, giving easy navigation with no nested reference chains.

5 / 5

Total

15

/

20

Passed

Description

87%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.

The description is strong: it explicitly states what the skill does and when to use it, with concrete triggers and explicit out-of-scope contrasts that sharply reduce conflict risk. Its only weak spot is a slightly narrow action-verb set and a few missing natural trigger synonyms (survival/recurrence/progression).

Suggestions

Broaden the action verbs beyond "Designs" (e.g., add "structures", "specifies", "audits") to lift specificity toward 5.

Add common natural phrasings such as "survival biomarker", "recurrence-risk", or "progression biomarker" to the trigger terms so they match how users actually phrase requests.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("Designs discovery, modeling, and validation workflows") with a comprehensive focus list (endpoint family, follow-up horizon, time scale, candidate marker strategy, model-building logic, risk stratification, validation), but the governing verb set is narrow (design-centric), short of the multiple distinct operations of a 5.

4 / 5

Completeness

Clearly answers both "what" ("Designs discovery, modeling, and validation workflows for prognostic biomarkers") and "when" ("Always use this skill when the user needs a prognostic biomarker study blueprint rather than..."), with concrete trigger phrases and explicit negative triggers.

5 / 5

Trigger Term Quality

Good coverage of natural domain terms ("prognostic biomarker study blueprint", "predictive biomarker design", "validation") plus contrast terms, but common user phrasings like "survival", "recurrence", or "progression" biomarker are absent from the description, leaving a few natural terms missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (prognostic biomarker protocol design) and explicitly contrasts against diagnostic test protocol, predictive biomarker design, treatment recommendation, and completed manuscript, minimizing conflict risk with neighboring skills.

5 / 5

Total

18

/

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.