course-guide

Topic router for the AI Engineering from Scratch curriculum. Give it a topic, a question, or a bug you are fighting, and it points at the exact lessons that teach it, plus the right next command. Trigger phrases: "where do I learn", "which lesson covers", "course guide", "I'm stuck on", "what should I do next", "teach me MCP", "teach me Agent Skills", "where do I prepare for a Claude certification"

Quality

81%

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.

The body is a concrete, well-sequenced router with exact paths, URLs, commands, and a defined output shape. Its main weaknesses are triple-redundant restatement of the focused routes and a loose closing paragraph that lacks a heading.

Suggestions

State each focused route (claude-certification, learn-mcp, learn-agent-skills) once in the routing table and have step 1 and the closing paragraph reference rather than repeat them.

Give the closing command-reference paragraph a heading (e.g., '## Command reference') so it is not loose prose after the numbered workflow.

Add an explicit retry/fallback for the coverage check, e.g., 'if no shortlisted lesson covers the concept, drop it and re-scan, then fall back to step 4.'

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no generic concept padding, but the three focused routes (claude-certification, learn-mcp, learn-agent-skills) are restated in the routing table, again in step 1, and again in the closing paragraph, which could be tightened.	3 / 5
Actionability	Highly concrete for an instruction skill: exact file paths (README.md, glossary/terms.md, docs/en.md, learning-paths/*.json), URLs, commands, host-specific invocation syntax, and a specified ~12-line answer shape covering all six ask-shapes.	5 / 5
Workflow Clarity	A clear four-step sequence with an explicit verify-before-recommend checkpoint (fetch docs/en.md and confirm coverage) and a no-match fallback ('Never invent a lesson that does not exist'), but it lacks an explicit re-scan/retry loop when a shortlisted lesson fails the coverage check.	4 / 5
Progressive Disclosure	Well-organized into clear headed sections (Host invocation contract, Routing table, How to route), but no bundle reference files exist to split, the skill exceeds 50 lines so the simple-skill exception does not apply, and the closing un-headered reference paragraph is a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

81%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 is strong: explicit trigger phrases and a clear what/when make completeness and trigger quality excellent. Specificity is dragged down by second-person voice, and a few triggers overlap with sibling routing skills.

Suggestions

Rewrite in third person to avoid the specificity penalty, e.g., 'Routes a topic, question, or bug to the exact lessons that teach it plus the right next command.'

Disambiguate overlapping triggers so 'teach me MCP' clearly selects this router rather than learn-mcp directly, e.g., keep router triggers in the 'which lesson covers' framing.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('points at the exact lessons that teach it, plus the right next command'), a base of 3, but the second-person phrasing 'a bug you are fighting' triggers the rubric's voice penalty reducing the score by one.	2 / 5
Completeness	Clearly states what it does (routes to exact lessons plus the next command) and explicitly answers when with a concrete 'Trigger phrases:' list, satisfying both what and when with concrete triggers.	5 / 5
Trigger Term Quality	Explicitly lists eight natural trigger phrases ('where do I learn', 'which lesson covers', 'I'm stuck on', 'teach me MCP', etc.) spanning topic, struggle, meta, MCP, Agent Skills, and certification shapes—comprehensive coverage of phrases a learner would actually say.	5 / 5
Distinctiveness Conflict Risk	It occupies a clear curriculum-navigation niche, but shared triggers like 'teach me MCP' overlap with the very sub-skills it routes to (learn-mcp, learn-agent-skills), a minor conflict risk with closely related skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: rohitg00/ai-engineering-from-scratch
Path: skills/course-guide/SKILL.md
Commit: c02ca08

Reviewed: 4 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.