CtrlK
BlogDocsLog inGet started
Tessl Logo

treatment-response-predictor-planner

Designs studies for predicting treatment response or resistance in biomedical and clinical research. Always use this skill when the user needs a treatment-response or resistance prediction study blueprint rather than a prognostic biomarker protocol, diagnostic test design, causal treatment-effect estimation, or a completed manuscript. Focus on responder definition, treatment context, baseline comparability, feature integration strategy, model development logic, validation architecture, and interpretation boundaries. Do not invent response rates, cohort size, assay readiness, regimen uniformity, literature support, or validation access.

72

Quality

89%

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

78%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 body is a well-structured, highly actionable design-planning skill with excellent progressive disclosure through its reference bundle. Its main weakness is redundancy: the same dos and don'ts are restated across multiple sections, inflating length without adding operational value.

Suggestions

Consolidate the overlapping prohibition lists: 'Core Function > should not', 'Hard Rules', and 'What This Skill Should Not Do' repeat the same items (no post-treatment baseline predictors, no fabricated rates/sizes, no prognostic-as-predictive) — merge into one canonical rules section and reference it.

The intro 'must always distinguish between' bullet list and 'must not confuse' paragraph duplicate content already enforced in Hard Rules; consider reducing the opening to a short scope statement and letting the rules section carry the detail.

Trim the description-field prohibitions that are repeated verbatim in the body's Feasibility and Literature Integrity rules so each rule appears in exactly one place.

DimensionReasoningScore

Conciseness

Mostly actionable and free of basic-concept fluff, but the same prohibitions recur across the intro distinctions list, Core Function, Hard Rules, and What This Skill Should Not Do (e.g. no post-treatment baseline predictors, do not invent response rates/cohort size appear in several forms), so it could be tightened meaningfully.

3 / 5

Actionability

Highly actionable for an instruction-only skill: 11 execution steps each enumerate exactly what to 'State:', a fixed A–L output structure, formatting rules, clarification guardrails, and a copy-ready out-of-scope redirect template.

5 / 5

Workflow Clarity

Clear 11-step sequence with checkpoints (Step 1 predictive-fit gate, input-validation redirect-and-stop, clarification rule with 2–6 follow-up questions), but no true validate→fix→retry loop — acceptable here since the skill produces a blueprint rather than executing destructive or batch operations.

4 / 5

Progressive Disclosure

Reference Module Integration maps each of the 11 real references/ files to specific output sections, every execution step names its reference, and the bundle files are one level deep with no nesting — well-signaled and easy to navigate.

5 / 5

Total

17

/

20

Passed

Description

100%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 third-person, concise, and explicitly covers both capability and trigger conditions while sharply delineating the skill from adjacent workflows. It is a strong, low-conflict description with no notable gaps.

DimensionReasoningScore

Specificity

Lists multiple concrete actions/focus areas — 'Designs studies for predicting treatment response or resistance', responder definition, treatment context, baseline comparability, feature integration, model development, validation architecture, interpretation boundaries — giving comprehensive coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both what ('Designs studies for predicting treatment response or resistance...') and when ('Always use this skill when the user needs a treatment-response or resistance prediction study blueprint rather than...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural terms users would say — 'treatment-response', 'resistance prediction', 'predictive biomarker', plus discriminating synonyms (prognostic, diagnostic, causal treatment-effect) that map to real phrasings.

5 / 5

Distinctiveness Conflict Risk

Clear niche — explicitly carves the skill away from prognostic biomarker, diagnostic test, causal effect-estimation, and manuscript workflows, minimizing wrong-skill triggering.

5 / 5

Total

20

/

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.