drug-target-evidence-landscape

Organizes the evidence and competitive landscape around a drug, target, or pathway by separating disease relevance, tractability, preclinical evidence, clinical evidence, modality fit, and crowding. Always map what is biologically supported, what is druggable, what has actually advanced, and what remains strategically open. Never confuse target relevance with druggability, preclinical activity with clinical promise, or narrative excitement with validated development maturity. Never fabricate references, trial status, approval status, company activity, or asset metadata.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./awesome-med-research-skills/Evidence Insight/drug-target-evidence-landscape/SKILL.md

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.

The body is well-structured with a clear ordered workflow, verification checkpoints, and clean one-level references, but it is hurt by repeated restatement of the same separations across multiple sections and by the absence of a concrete worked example.

Suggestions

Consolidate the repeated 'separate X from Y' rules that recur across Core Function, Hard Rules, and 'What This Skill Should Not Do' into a single canonical list to reduce token cost.

Add one short worked example (e.g. a condensed TIGIT or KRAS landscape walkthrough) showing the expected A–I output, to lift actionability.

Remove or explicitly wire up the 8 reference files in references/ that are not cited in the body (e.g. competition-landscape-rules, target-assessment-framework) to avoid bundle clutter.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept over-explanation, but the same distinctions are restated across Core Function, Execution steps, Mandatory Output Structure, Hard Rules, and 'What This Skill Should Not Do' (e.g. separating preclinical from clinical evidence appears four+ times), so it could be tightened.	3 / 5
Actionability	As an instruction-only skill it gives specific per-section content lists ('Map separately: preclinical efficacy evidence, translational biomarker / pharmacology / patient-selection bridge, clinical evidence'), but guidance is largely structural/descriptive with no worked example or concrete artifact template to make execution unambiguous.	3 / 5
Workflow Clarity	A clearly ordered 8-step sequence maps onto a mandatory A–I output structure, with explicit checkpoints (Step 2 'Retrieve and Verify Evidence Before Landscape Claims' and Step 8 'Perform Self-Critical Review'), leaving only minor validation gaps.	4 / 5
Progressive Disclosure	A dedicated 'Reference Module Integration' section cleanly signals eight one-level-deep reference files (all verified present), each mapped to a section; however the body still carries heavy inline content and the references/ bundle contains 8 additional unreferenced files, leaving minor organization gaps.	4 / 5
	Total	14 / 20 Passed

Description

66%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 gives a clear, specific picture of what the skill does and carves out a distinct niche, but it lacks an explicit 'Use when...' trigger clause, leaving the 'when to use' dimension only weakly implied and capped at 3.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g. 'Use when mapping the evidence landscape around a drug, target, or pathway, or comparing target druggability versus development maturity').

Lead with the primary action and trigger terms before the behavioral 'Always/Never' directives, so the natural trigger keywords appear earlier.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple specific actions ('separating disease relevance, tractability, preclinical evidence, clinical evidence, modality fit, and crowding'; 'map what is biologically supported, what is druggable, what has actually advanced'), giving broad coverage, though the verbs (organizes/separates/maps) stay somewhat abstract rather than naming discrete operations.	4 / 5
Completeness	The 'what' is clear and concrete, but there is no explicit 'Use when...' clause or equivalent trigger guidance — the 'Always map...' and 'Never confuse...' lines are behavioral directives, not usage triggers, so completeness is capped at 3.	3 / 5
Trigger Term Quality	Good coverage of natural domain terms a user would say ('drug, target, or pathway', 'competitive landscape', 'disease relevance', 'preclinical', 'clinical', 'druggability'), with only minor natural-phrase gaps (e.g. no 'target landscape' or 'whitespace').	4 / 5
Distinctiveness Conflict Risk	A clearly defined niche (drug/target/pathway evidence landscape) with low overlap risk against generic medical or literature skills, though the behavioral framing is less trigger-distinct than a pure trigger-phrase formulation.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Evidence Insight/drug-target-evidence-landscape/SKILL.md
Commit: 63c61d3

Reviewed: 7 hours ago

Table of Contents

Discovery Implementation Validation

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.