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.

62

Quality

78%

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/treatment-response-predictor-planner/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 protocol-design skill with excellent navigation to its 11 reference files, a clearly sequenced 11-step workflow with explicit checkpoints, and concrete per-section output requirements. Its main weakness is verbosity: the same distinctions and prohibitions are repeated across four or five sections, inflating token cost without adding guidance.

Suggestions

Consolidate the repeated predictive-vs-prognostic and 'do not assume' rules into a single Hard Rules section (or a reference file) and remove the duplicated 'must distinguish', Core Function 'should not', and 'What This Skill Should Not Do' lists.

Drop or merge the 'Sample Triggers' section, which duplicates the description and the Input Validation examples.

Move the distinction taxonomies (endpoint families, biomarker-use families) into an existing reference module so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The ~430-line body restates the same rules many times: the predictive-vs-prognostic distinction appears in the description, the 'must distinguish' list, 'must not confuse', Core Function, Hard Rules, and 'What This Skill Should Not Do'; 'do not assume regimen uniformity / response assessment harmonization' recurs in at least four places; and 'Sample Triggers' largely duplicates the description and Input Validation examples. This matches anchor 2 ('Noticeably verbose; several unnecessary explanations or padded sections'); it is not 3 because the duplication is systematic across whole sections rather than a few tightenable spots, and not 1 because it avoids explaining basic concepts Claude already knows.

2 / 5

Actionability

Steps 1-11 each give an explicit 'State:' checklist, the mandatory A-L output structure defines every section's required content, and the out-of-scope redirect supplies literal response text — concrete, executable guidance for an instruction-only skill. This matches anchor 4 ('Mostly executable guidance... minor gaps'); it is below 5 because there is no worked example of a filled-in output section, and above 3 because the guidance is specific and directly followable rather than high-level hints.

4 / 5

Workflow Clarity

The 11-step Execution sequence is clearly ordered with each step mapped to its reference module, and checkpoints exist: Input Validation with a redirect, the Clarification Rule (2-6 questions before locking the design), and 'If any output section is generated without using its corresponding reference module, the output should be treated as incomplete'. This matches anchor 4 ('Clear sequence with most checkpoints present; minor validation gaps'); it is below 5 because there are no feedback/recovery loops (e.g., what to do when a step's assumptions fail), and above 3 because validation checkpoints are explicit rather than absent.

4 / 5

Progressive Disclosure

The 'Reference Module Integration' section clearly signals each of the 11 real, one-level-deep reference files and maps them to specific workflow steps and output sections, and the bundle structure matches those paths. This matches anchor 4 ('Good structure; most content is appropriately placed; references mostly clear; minor organization gaps'); it is below 5 because substantial rule content (distinction lists, Hard Rules) remains inline in SKILL.md while the reference files are thin, so the split is not fully optimized, and above 3 because navigation and signaling are explicit and complete.

4 / 5

Total

14

/

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.

A strong description: third-person voice, explicit what-and-when, concrete focus areas, and deliberate disambiguation from prognostic/diagnostic/causal neighbors. The only weaknesses are a few missing natural trigger phrasings (e.g., 'responders/non-responders', 'therapy response') and reliance on one broad verb ('designs studies') for the action statement.

Suggestions

Add common user phrasings such as 'responders / non-responders', 'therapy response', or 'predictive biomarker study' to the trigger coverage.

Convert one or two of the 'Focus on...' focus areas into distinct action verbs (e.g., 'defines responder endpoints, structures multimodal feature integration, and plans validation architecture') to raise action specificity.

DimensionReasoningScore

Specificity

"Designs studies for predicting treatment response or resistance in biomedical and clinical research" names the domain and core action, and "Focus on responder definition, treatment context, baseline comparability, feature integration strategy, model development logic, validation architecture, and interpretation boundaries" enumerates several concrete facets of the deliverable. This matches the anchor 'Lists several specific actions; minor gaps in coverage' (score 4); it falls short of 5 because 'designs studies' is one verb elaborated by focus areas rather than multiple distinct concrete actions, and above 3 because coverage of the design workflow is comprehensive, not just 1-2 actions.

4 / 5

Completeness

Both questions are explicitly answered: the 'what' in "Designs studies for predicting treatment response or resistance in biomedical and clinical research" and an explicit, concrete 'when' in "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". This matches the anchor 'Clearly and explicitly answers both what AND when with concrete trigger phrases' (score 5); it is above 4 because the 'when' clause is explicit with specific trigger scenarios rather than merely implied.

5 / 5

Trigger Term Quality

Natural domain keywords are present: "predicting treatment response or resistance", "treatment-response or resistance prediction study blueprint", "prognostic biomarker protocol", "diagnostic test design", "causal treatment-effect estimation". Good keyword coverage matching anchor 4 ('a few natural terms missing') — common phrasings a user might say such as "responders / non-responders", "therapy response", or "predictive biomarker study" are absent, keeping it below the comprehensive-synonym level 5.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche and actively disambiguates from adjacent skills ("rather than a prognostic biomarker protocol, diagnostic test design, causal treatment-effect estimation, or a completed manuscript"), which matches anchor 5 ('Clear niche with distinct triggers; minimal conflict risk'). It is above 4 because the negative boundary explicitly separates the most likely confusable neighbors rather than leaving only minor overlap risk.

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.

Validation — 15 / 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.