code-refactor-for-reproducibility
Transforms research code into publication-ready, reproducible workflows. Adds documentation, implements error handling, creates environment specifications, and ensures computational reproducibility for scientific publications.
74
68%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Data analysis/code-refactor-for-reproducibility/SKILL.mdQuality
Discovery
67%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 effectively communicates specific capabilities for transforming research code into reproducible scientific workflows. Its main weakness is the absence of an explicit 'Use when...' clause, which limits Claude's ability to know exactly when to select this skill. The trigger terms could also be expanded to include more natural user language.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when preparing code for journal submission, sharing research code, or when the user mentions reproducibility, publication, or scientific workflows'
Include additional natural trigger terms users might say: 'paper', 'journal', 'share code', 'reproduce results', 'clean up research code', 'computational notebook'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Adds documentation, implements error handling, creates environment specifications, and ensures computational reproducibility.' These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' with specific actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied through context (scientific publications). | 2 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'research code', 'publication-ready', 'reproducible workflows', 'scientific publications', but missing common variations users might say like 'paper', 'journal', 'reproduce results', 'share code', or 'clean up code'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche targeting scientific/research code for publications. The combination of 'research code', 'publication-ready', 'reproducible workflows', and 'scientific publications' creates a distinct domain unlikely to conflict with general code refactoring or documentation skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has strong structure and workflow clarity with explicit validation steps and good progressive disclosure. However, it suffers from generic boilerplate content (response templates, output requirements) that doesn't add domain-specific value, and the core refactoring guidance lacks concrete, executable code examples that would make it truly actionable.
Suggestions
Replace the abstract refactoring descriptions in Step 2 with concrete before/after code examples (e.g., show a hardcoded path being parameterized with argparse)
Remove or significantly condense the generic 'Output Requirements' and 'Response Template' sections, which add tokens without research-code-specific value
Add a concrete code example showing how to add random seed handling (e.g., `np.random.seed(SEED)`, `torch.manual_seed(SEED)`) rather than just mentioning 'SEED = 42'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some generic workflow boilerplate (e.g., the 5-step workflow section and response template) that doesn't add research-code-specific value. The output requirements and response template sections feel like padding. | 2 / 3 |
Actionability | Provides CLI usage examples and parameter tables, but the refactoring steps are described at a high level without executable code examples. The 'Quick Check' commands are concrete, but the actual refactoring guidance (Step 2) uses descriptions rather than copy-paste code snippets. | 2 / 3 |
Workflow Clarity | Clear 4-step refactoring process (Analyze → Refactor → Environment → Validate) with explicit validation checkpoint in Step 4 (diff outputs, confirm checksums, run pytest). Fallback template provides error recovery guidance. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections, appropriate length for an overview, and a single-level reference to detailed patterns in 'references/guide.md'. Content is appropriately split between quick-start and detailed guidance. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
ca9aaa4
- 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.