CtrlK
BlogDocsLog inGet started
Tessl Logo

sympy

Use when you need exact symbolic math in Python — algebra, calculus, equation solving, symbolic linear algebra, or code generation via lambdify/LaTeX. Prefer NumPy or SciPy when floating-point approximations are sufficient.

68

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 highly actionable with executable examples and reasonable workflow patterns, but it is verbose and redundant across overlapping sections, and its reference structure has a confusing near-duplicate core file that nests pointers.

Suggestions

Consolidate the redundant solve/diff/integrate/lambdify material so it appears once across Best Practices, Common Use Case Patterns, and Getting Started Examples rather than three times.

Resolve the core_capabilities.md vs core-capabilities.md duplication — keep one file and point the body directly at it to eliminate the 2-level pointer hop.

Move the long Quick Reference import block and Getting Started Examples into a reference file so SKILL.md stays a lean overview pointing one level deep.

DimensionReasoningScore

Conciseness

The 355-line body repeats the same ground three times — Best Practices, Common Use Case Patterns, and Getting Started Examples all cover solve/diff/integrate/lambdify — and re-lists the five reference files in both "Core Capabilities" and "Reference Files Structure", so it is mostly useful but noticeably could be tightened.

3 / 5

Actionability

Abundant copy-paste-ready Python with expected outputs in comments (e.g. solve(x**2-5*x+6) # [2, 3], lambdify examples, Matrix eigenvals), covering the common cases fully and executably.

5 / 5

Workflow Clarity

Sequenced pipelines appear (Pattern 2 numbers the symbolic-to-numeric steps) and Pattern 1 includes a solve-then-verify loop, but there is no single consolidated end-to-end workflow with explicit checkpoints across the skill.

4 / 5

Progressive Disclosure

References are one level deep and well-signaled ("see references/X.md", "Load when:"), all linked files exist, but both core_capabilities.md (underscore) and core-capabilities.md (hyphen) are linked while the former just points to the latter, creating a 2-level hop, and large overlapping sections are inlined rather than split out.

3 / 5

Total

15

/

20

Passed

Description

92%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, third-person description that states concrete capabilities, an explicit trigger, and a boundary against NumPy/SciPy. It is near-exemplary; only slightly broader trigger phrasing would push it higher.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — "algebra, calculus, equation solving, symbolic linear algebra, or code generation via lambdify/LaTeX" — giving comprehensive coverage of the domain, matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers both what (exact symbolic math in Python across named capability areas) and when ("Use when you need exact symbolic math") and adds a negative trigger ("Prefer NumPy or SciPy when floating-point approximations are sufficient").

5 / 5

Trigger Term Quality

Strong natural keyword coverage ("symbolic math", "algebra", "calculus", "equation solving", "lambdify", "LaTeX", "Python"), but a few common user phrases like "solve equations" or "simplify expressions" are absent, so it falls just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

The symbolic-vs-numerical niche is clear and the explicit boundary ("Prefer NumPy or SciPy when floating-point approximations are sufficient") steers away from sibling skills, minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
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.