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.

1.05x

Quality

88%

Does it follow best practices?

Impact

84%

1.05x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable examples and clear verification-backed workflows, but it is verbose with significant redundant sections, and its progressive-disclosure structure is undermined by reference files that are signaled but not actually shipped.

Suggestions

Ship the five referenced files under references/ (core-capabilities.md, matrices-linear-algebra.md, physics-mechanics.md, advanced-topics.md, code-generation-printing.md) or remove the dangling references, since the bundle directory is currently missing.

Remove redundant sections — 'Getting Started Examples', 'Quick Reference: Most Common Functions', and the NumPy/Matplotlib/SciPy integration blocks largely repeat code already shown in 'Core Capabilities' and 'Best Practices'.

Trim the body to a lean overview and move detailed API/catalog content into the reference files so SKILL.md earns its token budget rather than restating SymPy basics Claude already knows.

Dimension	Reasoning	Score
Conciseness	The ~490-line body is heavily padded with redundancy: 'Getting Started Examples' repeats derivative/integral/eigenvalue/lambdify examples already shown in 'Core Capabilities', 'Quick Reference' repeats shown imports, and 'Integration with Scientific Workflows' duplicates lambdify usage; not level 1 because it avoids conceptual fluff, but not level 3 because most tokens are not lean.	2 / 3
Actionability	Numerous copy-paste-ready executable Python blocks (symbols, diff, integrate, solveset, Matrix, lambdify, dsolve) with expected outputs as comments match the level-3 anchor for fully executable, specific examples; not level 2 because the code is complete, not pseudocode.	3 / 3
Workflow Clarity	Workflows are clearly sequenced with validation: 'Pattern 1: Solve and Verify' includes a verification loop with an assert checkpoint, and 'Pattern 2: Symbolic to Numeric Pipeline' is an explicit 4-step sequence; not level 2 because checkpoints are present rather than implicit.	3 / 3
Progressive Disclosure	References are clearly signaled one level deep ('See references/core-capabilities.md' etc.) with a 'Load when' guide, but the references directory does not exist, so the signaled paths are broken, and heavy inline content that should live in those files makes this a monolithic body rather than a lean overview; not level 3 because the referenced bundle files are absent.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 strong: specific, complete, well-triggered, and distinct, with explicit 'what' and 'when' guidance in third-person voice. Its only minor gap is that it never names the library itself ('SymPy'), which slightly weakens natural-term coverage.

Dimension	Reasoning	Score
Specificity	Lists many 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'), matching the level-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('symbolic computation tasks including...') and when ('Use this skill when...', 'Apply this skill when the user needs exact symbolic results rather than numerical approximations'), matching the level-3 anchor; not level 2 because the 'when' is explicit, not implied.	3 / 3
Trigger Term Quality	Covers natural user terms ('symbolic mathematics', 'equations', 'derivatives, integrals, limits', 'matrices', 'physics calculations', 'number theory', 'geometry', 'exact symbolic results', 'numerical approximations'); not level 2 because coverage is broad rather than 'some relevant keywords'.	3 / 3
Distinctiveness Conflict Risk	Clear niche of exact symbolic computation with a distinct trigger ('exact symbolic results rather than numerical approximations'), written in third person, unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 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
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 7 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/general/sympy/SKILL.md
Commit: df37802

Reviewed: 19 days 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.