randomization-gen

Generates randomization sequences for RCTs including simple, blocked, and stratified allocation. Produces sealed randomization lists ready for allocation concealment.

Quality

55%

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/randomization-gen/SKILL.md

Quality

Content

48%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 content has a well-sequenced workflow with validation checkpoints and one valid reference, but is dragged down by verbose generic boilerplate sections and an abstract, non-executable core example.

Suggestions

Remove or externalize the generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) to reduce padding and raise conciseness.

Replace the abstract Example with a concrete, copy-paste-ready invocation such as 'python scripts/main.py -n 120 -g Control,Treatment -b 6 -o randomization.csv' showing real output.

Drop the time-sensitive 'Next Review Date: 2026-03-06' or move it to a deprecated/maintenance section, as it penalizes conciseness per the rubric.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) that are not specific to this skill, plus time-sensitive content ('Next Review Date: 2026-03-06'), matching the 'noticeably verbose; several padded sections' anchor.	2 / 5
Actionability	Provides concrete executable commands ('python -m py_compile scripts/main.py', 'python scripts/main.py --help') and a parameters table, but the Example ('Input: n=120, 3 groups, block=6 / Output: Sealed randomization list') is abstract and lacks a copy-paste-ready invocation of the actual generator with real output.	3 / 5
Workflow Clarity	The 6-step Workflow includes explicit validation (step 2), a confirmation checkpoint (step 3), and a fallback loop (step 6 'proceed only after user confirmation'), giving a clear sequence with most checkpoints present; it stops short of 5 because the steps are prose without embedded executable commands.	4 / 5
Progressive Disclosure	There is one clearly signaled, one-level-deep reference to a real file (references/audit-reference.md), but the body inlines substantial generic template content (risk/security/evaluation/lifecycle/response-template) that should be removed or split out, fitting the 'some structure but content that should be separate is inline' anchor.	3 / 5
	Total	12 / 20 Passed

Description

62%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 specific and clearly niched, but lacks an explicit 'Use when' trigger clause and the natural trigger synonyms that appear only in the body, capping completeness and trigger-term quality.

Suggestions

Add a 'Use when ...' clause naming concrete user triggers like 'random allocation', 'block randomization', 'stratified randomization', and 'RCT design' to raise completeness above 3.

Surface the natural-language synonyms and file-format cues currently buried in the body directly into the description for better trigger-term coverage.

Lead with the most concrete action verb rather than the generic 'Generates randomization sequences' to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'simple, blocked, and stratified allocation' and 'sealed randomization lists ... for allocation concealment' — but is led by the somewhat abstract verb 'Generates randomization sequences', leaving minor coverage gaps rather than the fully comprehensive multi-verb list of a 5.	4 / 5
Completeness	Provides a clear 'what' (generates simple/blocked/stratified sequences and sealed lists) but no 'when' / 'Use when' trigger clause; per the rubric a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant domain keywords ('RCTs', 'randomization sequences', 'blocked', 'stratified', 'allocation concealment') but omits common natural variations and synonyms a user would say — e.g. 'random allocation', 'block randomization', 'RCT design' — which only appear in the body, not the description.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (RCT randomization / allocation concealment) with domain-specific terminology unlikely to collide with other skills, matching the anchor for minimal conflict risk.	5 / 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: scientific-skills/Protocol Design/randomization-gen/SKILL.md
Commit: 63c61d3

Reviewed: 8 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.