CtrlK
BlogDocsLog inGet started
Tessl Logo

learn-mcp

Focused interactive tutor for the Model Context Protocol (MCP) path in AI Engineering from Scratch. Start or resume this route when a learner wants to build, secure, debug, verify, or operate MCP clients, servers, transports, gateways, registries, or conformance gates. Teaches one lesson per invocation and records wire evidence in MCP-LEARNING.md.

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is learn-mcp in rohitg00/ai-engineering-from-scratch

SKILL.md
Quality
Evals
Security

Quality

Content

77%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-sequenced tutor skill with explicit validation and feedback loops throughout its workflow. The main weaknesses are a sizable inlined template that bloats conciseness and the absence of any split-out reference files for progressive disclosure.

Suggestions

Move the full MCP-LEARNING.md state-file template into a references/ file (e.g. references/initial-state.md) and link to it from the body, which would tighten conciseness and give progressive disclosure a real one-level-deep reference to point at.

Trim repeated procedural phrasing in the 'Teach one lesson' and 'Locate or create progress' sections into tighter bullet steps so each token earns its place.

Extract the manifest navigation details (the required sequence 06,07,...,31 and the Lesson 23 capstone prerequisites) into a references/route-map.md, keeping the body as a concise overview that signals the detail file.

DimensionReasoningScore

Conciseness

The body is dense and procedural and does not explain concepts Claude already knows, but it inlines a ~50-line state-file template and repeats some procedural phrasing that could be tightened, keeping it mostly efficient rather than lean.

3 / 5

Actionability

It provides a copy-paste-ready command with an exact path, a specific error code (-32022), concrete fields to identify, an explicit redaction list, and a complete fill-in state template — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

The 'Teach one lesson' section is an 8-step sequenced workflow with explicit validation checkpoints and feedback loops (checkpoint + quiz gating before marking Done, rerun-and-keep-pending on missing evidence, verify-before-remove rename), matching the checklist-and-recovery anchor.

5 / 5

Progressive Disclosure

It is well-sectioned with headers, but there are no bundle reference files to navigate to and a large inlined template that could live in a separate file, so the structure is present without clear one-level-deep references.

3 / 5

Total

16

/

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, specific description that clearly answers both what the skill does and when to invoke it, with a well-defined niche. The only slight gap is trigger-term breadth, where a few more common synonyms would round out the coverage.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ('build, secure, debug, verify, or operate') applied across the full MCP component set ('clients, servers, transports, gateways, registries, or conformance gates'), giving comprehensive coverage rather than just a few actions with minor gaps.

5 / 5

Completeness

It explicitly states what it does ('Focused interactive tutor... Teaches one lesson per invocation and records wire evidence') and when to start it ('Start or resume this route when a learner wants to...'), with concrete trigger phrases for both.

5 / 5

Trigger Term Quality

It uses natural domain keywords a learner would say (build, secure, debug, verify, operate MCP clients/servers/transports), but lacks common synonyms or file extensions and leans on specialized phrasing like 'conformance gates', so it falls short of comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche around the Model Context Protocol learning route with distinct, specific triggers, making overlap with unrelated skills minimal.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rohitg00/ai-engineering-from-scratch
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.