CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

math-model-selector

Routes problems to appropriate mathematical frameworks using expert heuristics

47

Quality

59%

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 ./bundled/skills/math-model-selector/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 a well-structured, actionable decision-tree skill with a concrete worked example and clear sequencing, though it carries some redundancy between the Process and Key Questions sections and references a script that is not bundled. Tightening the duplicated questions and clarifying tool references would lift it further.

Suggestions

Merge or remove the "Key Questions to Ask" section since its five questions duplicate the inline prompts already in the Process section, improving conciseness.

Clarify the status of the referenced "sympy_compute.py" tool (note it as external or remove the reference) so the example is fully self-contained and actionable.

Add a brief validation checkpoint confirming the selected framework matches all five answers before emitting the recommendation, to strengthen workflow clarity.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining concepts Claude already knows, but the "Key Questions to Ask" section restates the five questions already embedded in the Process section, creating noticeable redundancy that could be tightened.

3 / 5

Actionability

Concrete decision-tree mappings (e.g., "Continuous rate -> ODEs", "Convex objective -> linear/quadratic programming"), a specific output template, and a fully worked example give actionable guidance; the only gap is the referenced sympy_compute.py script that is not present in the bundle.

4 / 5

Workflow Clarity

The five-step decision process is clearly sequenced with explicit "Ask:" prompts and answer-to-framework mappings; this is a conversational routing skill rather than a destructive or batch operation, so the missing-validation cap does not apply, though no explicit feedback loop is present.

4 / 5

Progressive Disclosure

Content is well organized into clearly headed sections (When to Use, Process, Output Format, Example Interaction, Co-activates) with no bundle files to split out; the only organization gap is the redundant Key Questions section that overlaps the Process section.

4 / 5

Total

15

/

20

Passed

Description

30%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.

The description clearly states the skill's purpose but is written in technical jargon with no natural trigger terms and no explicit "Use when" guidance, capping its completeness and trigger quality. Adding concrete routing actions and a user-facing trigger clause would substantially improve it.

Suggestions

Add a "Use when the user asks which math to use, how to model a problem, or which framework applies" clause to provide explicit trigger guidance and lift completeness above 3.

Replace jargon ("expert heuristics," "mathematical frameworks") with natural user phrases such as "picks the right math approach" to improve trigger-term quality.

List 2-3 concrete routing actions (e.g., "maps problem traits to ODEs, probability, or optimization methods") to raise specificity beyond a single generic verb.

DimensionReasoningScore

Specificity

The description names the math domain but offers only one generic action ("Routes problems to appropriate mathematical frameworks"), with no list of concrete capabilities, matching the score-2 anchor "Names the domain but actions are minimal or generic".

2 / 5

Completeness

It clearly states what the skill does but includes no "Use when..." clause or explicit trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Phrases like "Routes problems," "mathematical frameworks," and "expert heuristics" are technical jargon; there are no natural keywords a user would actually say when they need this skill, matching the score-1 anchor for only technical jargon.

1 / 5

Distinctiveness Conflict Risk

The mathematical-framework-routing niche is somewhat specific but "appropriate mathematical frameworks" is broad enough to overlap with related math skills, fitting the score-3 anchor "Somewhat specific but could still overlap with similar skills".

3 / 5

Total

9

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

foryourhealth111-pixel/Vibe-Skills

Path

bundled/skills/math-model-selector/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.