CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

86%

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

The canonical home for this skill is course-guide in rohitg00/ai-engineering-from-scratch

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable, well-structured routing skill: every step names concrete sources, commands, and a link template, with explicit verification and no-match handling. Its main weakness is redundancy — the MCP, Agent Skills, and certification routing rules are repeated across three sections and could be stated once.

Suggestions

State the focused-route rules (MCP, Agent Skills, certification) once in the routing table and reference them from step 1 and the closing paragraph instead of restating them, which would remove roughly a third of the body.

Consolidate the closing command-reference paragraph to just the course-own command set (start-learning, learn, check-understanding, find-your-level) plus one line deferring all focused-route state files to the routing table above.

Trim micro-details that only matter at execution time (e.g., "the manifest order is 22, 24, 25, 26, 27") into the referenced manifest files, keeping the body at the routing-decision level.

DimensionReasoningScore

Conciseness

The body is dense and free of general-concept padding, but the focused-route rules (MCP, Agent Skills, certification) are stated three times: in the routing table, again in the step-1 "Interpret the ask" bullets, and again in the closing command-reference paragraph. Mostly efficient but includes repetition that could be consolidated into one statement, matching anchor 3; not 2 because there is no filler or explanation of concepts Claude already knows.

3 / 5

Actionability

Guidance is fully concrete and executable: exact source URL, specific file paths (README.md, glossary/terms.md, learning-paths/*.json, docs/en.md), the full command set (learn, check-understanding <phase>, start-learning, find-your-level), and a copy-paste lesson link template. As an instruction-only skill, the actionable guidance covers the common routing cases, matching anchor 5.

5 / 5

Workflow Clarity

The four-step routing sequence (Interpret → Scan → Answer → no-match fallback) includes an explicit verification checkpoint ("fetch each shortlisted lesson's docs/en.md ... and confirm it actually covers the failing concept before recommending it") and an error-recovery path for the no-match case ("say so plainly and name the closest phase. Never invent a lesson"). Clear sequence with explicit validation and failure handling matches anchor 5.

5 / 5

Progressive Disclosure

No bundle files exist, and the body is well-sectioned with clear headers pointing to one-level-deep external sources (repo README, glossary, per-route manifests) each with a clear local-first/raw-fallback rule. Not 5 because the focused-route details are inlined twice (routing table plus step-1 bullets) rather than consolidated or split, leaving a minor organization gap; not 3 because navigation is easy and references are clearly signaled.

4 / 5

Total

17

/

20

Passed

Description

86%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 description: it clearly states what the router does and gives an explicit, natural-language trigger list that covers the main ask shapes. The only deductions are a second-person phrase that incurs the voice penalty and minor trigger overlap with sibling focused-route skills.

DimensionReasoningScore

Specificity

"points at the exact lessons that teach it, plus the right next command" names the domain and two concrete actions, which sits at the 4 anchor ("several specific actions; minor gaps"), but the rubric's voice penalty applies for the second-person phrase "a bug you are fighting" (−1). Not a 2 because it is far more concrete than generic domain-naming like "Processes PDF files".

3 / 5

Completeness

Explicitly answers "what" ("Topic router... points at the exact lessons that teach it, plus the right next command") and "when" via a concrete, explicit trigger list ("Trigger phrases: ..."). Matches the anchor 5 example structure exactly; a 4 would require the "when" to be less explicit.

5 / 5

Trigger Term Quality

Eight explicit natural trigger phrases ("where do I learn", "I'm stuck on", "what should I do next", "teach me MCP", "teach me Agent Skills", "where do I prepare for a Claude certification") comprehensively cover the natural ways a learner would ask for routing, including synonyms across topic, struggle, meta, and certification intents. Not a 4 because no common variation for this domain is obviously missing.

5 / 5

Distinctiveness Conflict Risk

The niche (curriculum wayfinding for one specific course) is clear and most triggers are distinct, but "teach me MCP" and "teach me Agent Skills" risk overlapping with the sibling learn-mcp and learn-agent-skills skills. Mostly distinct with minor overlap risk against closely related skills, i.e. anchor 4; not 5 because those phrases would plausibly fire both this router and the focused skills.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

.claude/skills/course-guide/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.