engineering-tutor

Teach engineering concepts for real understanding using the Feynman technique, strong metaphors, and diagrams (render via beautiful-mermaid). Use when users ask to explain/teach/break down engineering concepts, build intuition/mental models, understand trade-offs/failure modes/design choices, or want a visual diagram.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%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.

A tight, well-structured instruction-only teaching skill with concrete actionable guidance and a teach-back feedback loop. The main gaps are the redundant Output-format section restating the protocol and the absence of a worked example.

Suggestions

Remove the "Output format (default)" section's restated steps or replace it with a one-line pointer to the Protocol (e.g. "Deliver in this order: Intuition → Metaphor → Visual → Steps → Misunderstandings → Teach-back") to eliminate the duplication.

Add one short worked example of metaphor mapping (e.g., a one-line physical metaphor and where it breaks) so the metaphor step is copy-paste clear rather than described.

Move the learning-save reference into its own labeled "## Persistence" section so the docs/REPO-STRUCTURE.md reference is clearly signaled rather than buried in the protocol.

Dimension	Reasoning	Score
Conciseness	Lean bullet-style protocol that assumes Claude's competence and never over-explains known concepts, but the "Output format (default)" section restates steps 1-6 of the Protocol, a minor redundancy that could be trimmed; sits at 4 rather than 5.	4 / 5
Actionability	Concrete, specific guidance throughout ("Pick everyday physical metaphor. Map parts explicitly. Say where metaphor breaks + why," "Choose type: flowchart / sequenceDiagram / stateDiagram / block") with no absent-code penalty for an instruction-only skill, but lacks a worked example to fully reach 5.	4 / 5
Workflow Clarity	An 8-step protocol clearly sequenced with a genuine feedback loop (teach-back in step 7) and a context-check fallback, but checkpoints are implicit rather than explicit validation steps, keeping it at 4.	4 / 5
Progressive Disclosure	Well-organized into clear sections (Protocol, Engineering mindset, Simplifications, Output format) and self-contained under ~50 lines, but the reference to docs/REPO-STRUCTURE.md is somewhat buried and the Output-format duplication is a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

91%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, specific description that clearly states both capability and trigger conditions with rich natural-language synonyms. The only weakness is the somewhat broad "visual diagram" trigger that risks overlap with other diagram skills.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "Teach engineering concepts," "using the Feynman technique, strong metaphors, and diagrams (render via beautiful-mermaid)" — but they are methods of one function rather than broad functional coverage, so it sits at 4 rather than 5.	4 / 5
Completeness	Explicitly answers both what ("Teach engineering concepts...") and when ("Use when users ask to explain/teach...") with concrete trigger phrases, matching the level-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural terms including synonyms — "explain/teach/break down," "build intuition/mental models," "understand trade-offs/failure modes/design choices," "want a visual diagram" — matching the level-5 anchor for synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Clear niche (engineering-concept teaching via Feynman/metaphors/diagrams), but the standalone trigger "want a visual diagram" is broad and could overlap with general diagram/dataviz skills, keeping it just below 5.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: marchatton/agent-skills
Path: .agents/skills/00-utilities/engineering-tutor/SKILL.md
Commit: a0eadb2

Reviewed: 3 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.