sympy
Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (derivatives, integrals, limits), manipulating algebraic expressions, working with matrices symbolically, physics calculations, number theory problems, geometry computations, and generating executable code from mathematical expressions. Apply this skill when the user needs exact symbolic results rather than numerical approximations, or when working with mathematical formulas that contain variables and parameters.
84
75%
Does it follow best practices?
Impact
89%
1.12xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/sympy/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates what the skill does (symbolic math operations across multiple domains) and when to use it (symbolic/exact results vs numerical, working with variables and parameters). The description is comprehensive with good trigger terms, though it uses second person ('Use this skill when') which is a minor style issue but the rubric specifically penalizes first/second person voice for specificity only. One minor weakness is that it doesn't mention the underlying library (e.g., SymPy) which could serve as an additional trigger term.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: solving equations algebraically, performing calculus operations (derivatives, integrals, limits), manipulating algebraic expressions, working with matrices symbolically, physics calculations, number theory problems, geometry computations, and generating executable code from mathematical expressions. | 3 / 3 |
Completeness | Clearly answers both 'what' (symbolic computation tasks including solving equations, calculus, algebra, matrices, etc.) and 'when' ('Use this skill when working with symbolic mathematics in Python', 'when the user needs exact symbolic results rather than numerical approximations, or when working with mathematical formulas that contain variables and parameters'). Has explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'symbolic mathematics', 'solving equations', 'calculus', 'derivatives', 'integrals', 'limits', 'algebraic expressions', 'matrices', 'physics calculations', 'number theory', 'geometry', 'exact symbolic results', 'numerical approximations', 'variables and parameters'. Good coverage of terms a user working with symbolic math would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly carved out niche: symbolic mathematics in Python, distinct from numerical computation skills or general math helpers. The emphasis on 'exact symbolic results rather than numerical approximations' and the Python context make it clearly distinguishable from other math or coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent, executable code examples covering SymPy's full breadth. However, it is severely bloated — it reads more like a comprehensive tutorial/reference than a concise skill file, with massive redundancy between sections (e.g., Getting Started Examples repeat earlier code patterns). The progressive disclosure structure exists but is undermined by including too much detail inline rather than delegating to the referenced files.
Suggestions
Cut the content by 50-60%: remove the 'When to Use This Skill' list (already in metadata), 'Getting Started Examples' (redundant with earlier sections), 'Quick Reference' imports list (Claude knows these), and 'Additional Resources' (external links Claude can't browse).
Remove explanatory text Claude already knows — e.g., 'SymPy is a Python library for symbolic mathematics that enables exact computation using mathematical symbols rather than numerical approximations' and integration examples with NumPy/Matplotlib/SciPy.
Lean heavily on the reference files: keep only 1-2 line summaries with one minimal example per section in SKILL.md, pushing all detailed examples into the referenced markdown files.
Consolidate the 'Best Practices' and 'Troubleshooting' sections into a single compact 'Gotchas' section with just the non-obvious items (exact arithmetic with Rational, lambdify for performance).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. The 'When to Use This Skill' section repeats the description. Sections like 'Overview', 'Getting Started Examples', and 'Quick Reference' heavily overlap with earlier content. Claude already knows what SymPy is, how imports work, and basic Python patterns. The 'Integration with Scientific Workflows' section explains trivial NumPy/Matplotlib usage. | 1 / 3 |
Actionability | All code examples are concrete, executable, and copy-paste ready with proper imports. Examples cover a wide range of use cases from basic symbol creation to physics calculations and code generation, with expected outputs shown in comments. | 3 / 3 |
Workflow Clarity | The 'Solve and Verify' pattern includes a verification step, and the 'Symbolic to Numeric Pipeline' shows a clear sequence. However, most sections are reference-style listings rather than workflows. The troubleshooting section helps but lacks structured error recovery loops for complex multi-step operations. | 2 / 3 |
Progressive Disclosure | References to modular files (core-capabilities.md, matrices-linear-algebra.md, etc.) are well-signaled with clear load-when guidance. However, the main SKILL.md contains far too much inline content that duplicates what the reference files presumably cover — the overview should be much leaner with more aggressive delegation to references. | 2 / 3 |
Total | 8 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
25e1c0f
- 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.