inclusion-criteria-gen

Generate and optimize clinical trial subject inclusion/exclusion criteria to balance scientific rigor with recruitment feasibility.

Quality

59%

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 ./scientific-skills/Protocol Design/inclusion-criteria-gen/SKILL.md

Quality

Content

61%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 highly actionable with accurate CLI commands, concrete JSON schemas, and well-signaled real reference files, but it is weighed down by redundant guardrail sections, a duplicated parameter table, a non-executable Python API example, and a workflow that lacks explicit validation feedback loops.

Suggestions

Consolidate the overlapping guardrail sections (When to Use, When Not to Use, Input Validation, Error Handling, Failure Handling, Output Contract, Output Requirements, User Checkpoints) into one compact block to remove redundancy.

Fix the Python API example to match the actual signature: construct a StudyDesign dataclass and pass it to generate(design), or update main.py to accept the documented kwargs.

Add an explicit validate-fix-retry checkpoint inside the Workflow (e.g. run analyze after optimize and only deliver when enrollment metrics meet the target) rather than leaving validation as a detached checklist.

De-duplicate the Parameters table, where --input and --output appear multiple times across the generate/optimize/analyze/benchmark subcommands.

Dimension	Reasoning	Score
Conciseness	The actionable core (CLI usage, JSON formats, category and strategy tables) is efficient and assumes Claude's competence, but the body carries many overlapping guardrail sections (When to Use / When Not to Use / Input Validation / Error Handling / Failure Handling / Output Contract / Output Requirements / User Checkpoints) plus a duplicated parameter table, fitting 'mostly efficient but includes some unnecessary padded sections'.	3 / 5
Actionability	Concrete CLI commands with accurate flags and full input/output JSON examples are copy-paste ready, but the Python API example calls generate(indication=..., phase=...) with kwargs while the bundled main.py defines generate(self, design: StudyDesign) taking a dataclass, so one example is non-executable, matching 'mostly executable guidance with minor gaps'.	4 / 5
Workflow Clarity	The 5-step Workflow is sequenced but stays abstract ('Confirm the user objective', 'Validate that the request matches') and lacks integrated validate-fix-retry checkpoints for the file-producing generate/optimize operations, and the separate Quick Validation list is not wired into the workflow, so per the batch-operation cap this stays at 3.	3 / 5
Progressive Disclosure	The References section lists five real, one-level-deep bundle files (all verified present in references/) and scripts/main.py with one-line descriptions, giving good structure and clear navigation; only minor organization gaps (inlined full JSON examples and parameter tables that could live in references) keep it from a 5.	4 / 5
	Total	14 / 20 Passed

Description

57%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 domain-specific and unlikely to misfire, but it only states the 'what' with two actions and omits any explicit 'when to use' trigger guidance, leaving it mid-range on completeness and trigger coverage.

Suggestions

Append an explicit trigger clause, e.g. 'Use when designing or refining clinical trial eligibility criteria, or when recruitment feasibility is at risk.'

Add common synonyms users would naturally say, such as 'eligibility criteria' and 'trial enrollment', to broaden trigger-term coverage.

Enumerate a couple more concrete actions (e.g. analyze complexity, benchmark against competitor trials) to lift specificity above the two-action floor.

Dimension	Reasoning	Score
Specificity	The description names the domain ('clinical trial subject inclusion/exclusion criteria') and two concrete actions ('Generate and optimize'), matching the 'names domain and 1-2 concrete actions' anchor; it does not enumerate the several specific actions (analyze, benchmark, optimize sub-operations) that would warrant a 4.	3 / 5
Completeness	It gives a clear 'what' (generate/optimize inclusion-exclusion criteria) but provides no explicit 'Use when...' trigger clause, so per the guideline a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	It includes relevant natural terms ('clinical trial', 'inclusion/exclusion criteria', 'recruitment feasibility') but misses common synonyms users would say such as 'eligibility criteria' or 'trial enrollment', fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Clinical trial subject inclusion/exclusion criteria' is a clear niche with distinct triggers and minimal overlap risk with unrelated skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	14 / 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: scientific-skills/Protocol Design/inclusion-criteria-gen/SKILL.md
Commit: 63c61d3

Reviewed: 10 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.