CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-refactor-for-reproducibility

Use when refactoring research code for publication, adding documentation to existing analysis scripts, creating reproducible computational workflows, or preparing code for sharing with collaborators. Transforms research code into publication-ready, reproducible workflows. Adds documentation, implements error handling, creates environment specifications, and ensures computational reproducibility for scientific publications.

Quality

75%

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 ./scientific-skills/Data Analysis/code-refactor-for-reproducibility/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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 core domain content (Steps 1–5) is genuinely actionable with executable code and strong validation checkpoints, but it is buried in heavy template boilerplate and duplicated sections. Critically, all four referenced reference files/directories are missing from the bundle, breaking progressive disclosure entirely.

Suggestions

Create the referenced bundle files (references/guide.md, references/environment-setup.md, references/examples/, references/api-docs/) or remove the dangling references, and move the inlined README template and full conda/pip environment examples into them.

Delete the verbatim description repeats in 'When to Use' and 'Key Features', collapse the three command sections (Example Usage, Quick Check, Audit-Ready Commands) into one, and merge the generic meta-'Workflow' with the domain 'Workflow Overview' so a single sequence governs the skill.

Fix the broken nested code fence in the Step 4 README template, add a step showing how checksums_original.md5 is produced before refactoring, and make the Step 2b argparse example a complete runnable snippet (it currently uses pd without importing it).

DimensionReasoningScore

Conciseness

The body is noticeably padded: the frontmatter description is pasted verbatim three times ('When to Use', 'Key Features', and the scope line 'Scope-focused workflow aligned to:'), the same two commands ('python -m py_compile scripts/main.py', 'python scripts/main.py --help') appear in three separate sections (Example Usage, Quick Check, Audit-Ready Commands), and there are two competing workflow sections plus generic meta-boilerplate ('Output Requirements', 'Response Template', 'Input Validation'). Not 3: the redundancy is pervasive structural padding, not occasional over-explanation; not 1 because the core Steps 1–5 do contain useful non-obvious material.

2 / 5

Actionability

The domain steps provide mostly executable guidance: a runnable AST path-detector, pipreqs commands ('pipreqs src/ --output requirements.txt --force'), venv install verification, a concrete conda environment.yml, checksum/diff/pytest validation commands, and a real packaged script ('python scripts/main.py --help'). Not 5: gaps remain — the README template block has broken nested code fences, 'checksums_original.md5' is diffed without instructions for creating the pre-refactor baseline, and several before/after fragments (e.g., 2b) are excerpts rather than complete runnable code.

4 / 5

Workflow Clarity

The domain workflow is a clear sequence — Analyze, Refactor, Specify environment, Validate — with explicit validation checkpoints (Step 5: checksum comparison, pytest, two-run determinism diff, an 8-item checklist) and a backup instruction ('Always back up originals first'). Not 5: two competing numbered workflows coexist (the generic meta 'Workflow' vs the domain 'Workflow Overview'), and 'Implementation Details' points ambiguously to 'See ## Workflow above', which clouds which sequence to follow.

4 / 5

Progressive Disclosure

The References section and Step 3 point to 'references/environment-setup.md', 'references/guide.md', 'references/examples/', and 'references/api-docs/' — but the references/ directory does not exist in the bundle, so every reference is dangling and navigation dead-ends. Content that clearly belongs in those files (the full README template, conda/pip environment examples) is inlined instead. Not 3: the references, while clearly signaled, are broken rather than merely under-organized, and the inlining is substantial.

2 / 5

Total

12

/

20

Passed

Description

88%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.

A strong description: it clearly states both what the skill does and when to use it, with several concrete actions in third-person voice. Trigger terms are natural and the niche is well-differentiated; only minor synonym coverage (e.g., Python/R, 'make code reproducible') is missing.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'refactoring research code for publication, adding documentation to existing analysis scripts, creating reproducible computational workflows, or preparing code for sharing with collaborators' and 'Adds documentation, implements error handling, creates environment specifications, and ensures computational reproducibility' — comprehensive coverage of the skill's capabilities in third-person voice. Not 4: the action list covers documentation, error handling, environment specs, and reproducibility validation, leaving no notable gaps in coverage.

5 / 5

Completeness

Explicitly answers both questions: what it does ('Transforms research code into publication-ready, reproducible workflows. Adds documentation, implements error handling, creates environment specifications...') and when to use it ('Use when refactoring research code for publication... or preparing code for sharing with collaborators'). Not 4: both 'what' and 'when' are present with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'refactoring research code', 'publication', 'reproducible workflows', 'adding documentation', 'sharing with collaborators' — phrases a user would plausibly say. Not 5: common variations and specifics are missing, e.g. no mention of Python/R, 'make my code reproducible', 'clean up analysis scripts', or file formats a user might name.

4 / 5

Distinctiveness Conflict Risk

The scientific-publication reproducibility niche ('research code', 'scientific publications', 'computational reproducibility') is fairly distinct with clear triggers. Not 5: it could still overlap with general refactoring, documentation, or code-review skills when the research/publication context is not explicit in the user's request.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

14

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Data Analysis/code-refactor-for-reproducibility/SKILL.md

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.