CtrlK
BlogDocsLog inGet started
Tessl Logo

sample-size-and-power-planning-assistant

Plans sample size estimation logic, power assumptions, feasibility checks, and fallback enrollment strategies for clinical and translational study protocols.

57

Quality

66%

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/sample-size-and-power-planning-assistant/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 is well-structured, actionable, and uses progressive disclosure effectively with clearly signaled reference files. Its main weakness is conciseness: the anti-fake-precision guidance is restated across multiple sections, adding padding that could be consolidated.

Suggestions

Consolidate the repeated anti-fake-precision guidance: merge 'What This Skill Should Not Do' and 'Quality Standard' into the existing 'Hard Rules' section to reduce restatement.

Add one short worked example (a brief scenario mapping inputs to a recommended planning stance) to push actionability from concrete guidance toward copy-paste-ready.

Trim the 'Important Distinction' list to the distinctions that actually change the planning logic, removing items already implied by the Hard Rules.

DimensionReasoningScore

Conciseness

The body is mostly efficient for an instruction skill, but the anti-fake-precision message is restated across 'Scope Boundary', 'Important Distinction', 'Hard Rules', 'What This Skill Should Not Do', and 'Quality Standard', adding noticeable padding. It is above a 2 because each section does carry distinct content, but below a 4 due to the repeated restatements that could be consolidated.

3 / 5

Actionability

Guidance is concrete and specific: an 8-step execution sequence, a mandatory 12-section output structure, and explicit assumption classification taxonomies give Claude clear, executable direction. It is not a 5 because there are no worked examples or concrete numeric/template anchors, and not a 3 because the guidance is largely complete rather than pseudocode-level hints.

4 / 5

Workflow Clarity

Steps are clearly sequenced (Clarify -> Identify driver -> Select family -> Audit -> Stance -> Scenarios -> Fragility -> Memo) with a clarification gate in Step 1 and checkpoints such as the mandatory output structure. It is not a 5 because there is no explicit validate/fix/retry feedback loop, and not a 3 because checkpoints are present and the sequence is well defined.

4 / 5

Progressive Disclosure

The body is a clear overview that signals five one-level-deep reference files (all confirmed present in references/), each annotated with its purpose and when to use it, with no nested references. This matches the 'clear overview with well-signaled one-level-deep references' anchor directly.

5 / 5

Total

16

/

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 occupies a distinct, low-conflict niche, but lacks an explicit 'Use when...' trigger clause, which caps completeness and leaves trigger-term coverage incomplete. Adding concrete usage triggers would lift the two capped dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when planning sample size or power for a clinical/translational protocol, or when a user asks how many patients/events are needed.'

Add natural phrasings users actually say (e.g. 'How many patients do I need', 'Is this study underpowered', 'target N') to broaden trigger-term coverage.

Tighten the action list to distinct, non-overlapping verbs to push specificity toward a 5.

DimensionReasoningScore

Specificity

The description lists several concrete actions ('sample size estimation logic, power assumptions, feasibility checks, and fallback enrollment strategies') rather than vague language, with only minor coverage gaps. It falls below a 5 because the actions are planning-framing verbs rather than a fully comprehensive set of distinct operations, and above a 3 because more than 1-2 specific actions are named.

4 / 5

Completeness

It has a clear 'what' but no 'Use when...' or equivalent explicit 'when' guidance, so per the rubric a missing trigger clause caps completeness at 3. It is above a 2 because the 'what' is specific and multi-part, but cannot reach 4 without an explicit usage-trigger clause.

3 / 5

Trigger Term Quality

It includes relevant keywords a user might say ('sample size', 'power', 'feasibility', 'enrollment', 'clinical and translational study protocols') but omits common variations and natural phrasings like 'How many patients do I need' or 'underpowered'. It is not a 4 because several natural trigger phrases are missing, and not a 2 because the terms present are domain-relevant rather than generic.

3 / 5

Distinctiveness Conflict Risk

It carves a clear niche (sample size and power planning for clinical/translational protocols) with distinct triggers and minimal overlap risk against other skills. It sits cleanly at the 'clear niche with distinct triggers' anchor rather than the 4 anchor's 'minor overlap risk'.

5 / 5

Total

15

/

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.