reproducibility-check

Comprehensive reproducibility tool — audit Methods completeness for replication AND promote open science best practices (pre-registration, FAIR data, code sharing, replication design, reporting transparency); trigger when preparing a manuscript, reviewing methodological comple...

Quality

57%

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/Other/reproducibility-check/SKILL.md

Quality

Content

56%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 a thorough, well-structured, and actionable instruction-only skill with a concrete output template and clear sequenced workflow, but it suffers from notable redundancy across multiple sections and inlines reference content already present in guide.md. Consolidating the duplicated Mode B material and offloading quick-reference tables to the reference file would meaningfully improve it.

Suggestions

Consolidate the redundant Mode B material — 'Key Features', 'Implementation Details', 'Key Platforms and Tools', and 'Quality Checklist' restate the same platforms/FAIR/reporting content; keep one authoritative procedural version and reference the others.

Move the platform/FAIR/repository/reporting-guideline tables out of SKILL.md into references/guide.md (where they already largely exist) and link to them, so the body stops inlining reference content.

Tighten verbose enumerated option lists in the Mode B Processing Workflow into concrete decision guidance to lift actionability from 4 toward 5.

Dimension	Reasoning	Score
Conciseness	The same Mode B material (platforms, FAIR principles, reporting guidelines, code/environment sharing) is restated across 'Key Features', 'Implementation Details' (Processing Workflow), 'Key Platforms and Tools', 'Output Requirements', and 'Quality Checklist' — several padded, redundant sections. Not a 3 because the duplication is substantial rather than a single tighten-able spot.	2 / 5
Actionability	Provides concrete, specific guidance (named platforms like OSF Registries/AsPredicted/PROSPERO, dependency files like requirements.txt/renv.lock/environment.yml, methods like TOST and Bayesian replication factors) plus a copy-paste-ready structured output example. Not a 5 because some Mode B steps enumerate options rather than giving a precise procedure.	4 / 5
Workflow Clarity	Workflow is clearly sequenced with numbered Mode A (steps 1-4) and Mode B (steps 5-11) phases, explicit mode-selection logic, an input-validation gate, and an error-handling/manual-fallback section. Not a 5 because validation is input-gating rather than in-process validate-fix-retry loops, though that is appropriate for this non-destructive read-only skill.	4 / 5
Progressive Disclosure	Bundle files references/guide.md and assets/reproducibility_checklist.md are real, one-level-deep, and signaled in a Dependencies section, but the body inlines platform/FAIR/reporting-guideline content that duplicates guide.md's tables — content that should live in the reference is inline. Not a 4 because the inline bulk is more than 'a few key examples'.	3 / 5
	Total	13 / 20 Passed

Description

58%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 clearly conveys a specialized reproducibility/open-science capability with concrete actions and a distinct niche, but the YAML description field is literally truncated mid-word ('comple...'), which damages the trigger clause and overall completeness. Fixing the truncation would likely raise completeness and trigger_term_quality.

Suggestions

Complete the truncated description field — it currently ends mid-word at 'reviewing methodological comple...', cutting off the trigger clause and leaving the 'when' guidance incomplete.

Expand the trigger phrase to include natural user variations and synonyms (e.g., 'reproducibility check', 'methods section review', 'open science practices', 'pre-registration help') for better trigger_term_quality.

Tighten the description so it explicitly pairs the concrete 'what' with a complete, explicit 'when' clause rather than relying on a semi-colon-joined, cut-off sentence.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('audit Methods completeness for replication', 'promote open science best practices (pre-registration, FAIR data, code sharing, replication design, reporting transparency)') with only minor coverage gaps. It stops short of a 5 because the field is truncated mid-sentence, leaving the action list incomplete.	4 / 5
Completeness	The 'what' is clear and fairly comprehensive, but the 'when' trigger clause is truncated mid-word ('reviewing methodological comple...'), so the trigger guidance is only weakly/partially present. Per the rubric, incomplete explicit trigger guidance caps this near 3 rather than 4.	3 / 5
Trigger Term Quality	Contains a relevant trigger phrase ('trigger when preparing a manuscript, reviewing methodological comple...') but the clause is cut off mid-word, so common variations and synonyms are missing. Not a 4 because the truncation prevents good keyword coverage; not a 2 because at least one natural trigger phrase is present.	3 / 5
Distinctiveness Conflict Risk	Targets a specialized research-reproducibility niche with distinct triggers (pre-registration, FAIR data, replication design), giving mostly distinct, low-conflict behavior. Not a 5 because the two-mode 'comprehensive' scope creates minor overlap risk with related open-science skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/reproducibility-check/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.