CtrlK
BlogDocsLog inGet started
Tessl Logo

biomarker-landscape-scanner

Scans the biomarker landscape of a disease area by biomarker type, clinical/research use case, evidence layer, validation status, and maturity level. Use this skill when a user wants a field-level biomarker evidence map rather than a generic literature summary. Always separate exploratory biomarkers from externally validated or clinically embedded biomarkers, and never imply clinical maturity without explicit evidence support.

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 thoroughly structured, actionable instruction skill with strong progressive disclosure via 8 reference modules and clear output scaffolding. Main weakness is redundancy across the rules, exclusions, and self-review sections that inflates token cost without adding guidance.

Suggestions

Consolidate the overlapping constraints in 'Hard Rules', 'What This Skill Should Not Do', and the Step 8 self-check into a single canonical list to reduce restatement and save context tokens.

Add an explicit validate→fix→retry loop note for the literature/citation-certainty checks so the workflow's error-recovery checkpoints are as explicit as its sequencing.

Consider folding the repeated maturity/validation-separation rules into the maturity-table section as a single source of truth rather than restating them across Steps 6, Section D, and Hard Rules 1, 5, 12.

DimensionReasoningScore

Conciseness

Mostly efficient with no padding of concepts Claude already knows, but several constraints are restated across 'Hard Rules', 'What This Skill Should Not Do', and Step 8 — the body could be tightened by consolidating these. Not a 4 because the redundancy is noticeable rather than minor.

3 / 5

Actionability

Provides concrete, executable guidance: 8 ordered steps, a mandatory A–J output structure with required fields per section, a maturity tier table, and concrete trigger/redirect templates. Not a 5 only because the per-section field lists are procedural rather than copy-paste-ready artifacts.

4 / 5

Workflow Clarity

Clear sequenced 8-step process with an explicit scope-check (Step 1.5), self-critical review checklist (Step 8), and retrieval-fallback labeling. Not a 5 because some checkpoints are implicit rather than explicit validate/fix/retry loops.

4 / 5

Progressive Disclosure

Body is a well-organized overview that maps each of 8 reference modules to specific output sections with one-level-deep references; all referenced files exist in references/, giving clear navigation with no nested indirection.

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, third-person description that clearly states capability, scope, and trigger conditions with concrete guardrails distinguishing exploratory from validated biomarkers. Only minor room for more exhaustive trigger-term synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete scanning/classification actions across explicit axes — 'by biomarker type, clinical/research use case, evidence layer, validation status, and maturity level' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what ('Scans the biomarker landscape...') and when ('Use this skill when a user wants a field-level biomarker evidence map...') with concrete trigger phrases and guardrail conditions.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('biomarker landscape', 'validation status', 'evidence map', 'biomarker maturity') and an explicit trigger clause, though a few common synonyms are absent. Not a 5 because coverage of natural-term variants is good but not exhaustive.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche — 'a field-level biomarker evidence map rather than a generic literature summary' — with distinct, domain-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.