CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 tutoring workflow with explicit validation checkpoints, evidence gates, and error-recovery fallbacks throughout. The main improvements are trimming a few peripheral sections and moving the inlined progress template into a reference file.

Suggestions

Move the blank MCP-LEARNING.md template into a bundle file (e.g. references/progress-template.md) and reference it from the 'Locate or create progress' section, slimming SKILL.md by ~50 lines.

Condense the host-invocation table to a single line (e.g. 'Invoke via the host's skill syntax; the portable name is learn-mcp') since hosts already surface their own syntax.

Shorten the optional lesson-screen section to its trigger condition and the events-command rule, cutting the explanatory sentences about what the screen shows.

DimensionReasoningScore

Conciseness

Efficient, rule-dense prose with no explanations of concepts Claude already knows; every section carries operational instructions. Minor trimmable parts remain: the host-invocation table, the optional lesson-screen section, and the detailed legacy-rename procedure.

4 / 5

Actionability

Fully executable guidance: 'python3 phases/13-tools-and-protocols/06-mcp-fundamentals/code/main.py', the raw GitHub URL pattern, the exact 17-lesson sequence, a complete copy-paste state-file template, and the exact quiz-hint format 'Reply with one letter: <A|B|C|D>.'

5 / 5

Workflow Clarity

Clear sequence (manifest, evidence mode, progress, teach, close) with 8 numbered teaching steps, explicit validation via required checkpointEvidence and quiz gating, and feedback loops such as 'If any required evidence is missing, teach or rerun Lesson 15 and keep the deployment action pending' plus the conceptual fallback when the command cannot run.

5 / 5

Progressive Disclosure

Well-organized sections with external files clearly signaled and read on demand ('Read or run code/ and outputs/ only when the current teaching step needs them'). However, the ~50-line blank MCP-LEARNING.md template is inlined in full, which could be split into a bundle file.

4 / 5

Total

18

/

20

Passed

Description

88%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: third-person, concrete, and explicit about both purpose and trigger conditions, with a clear niche tied to a specific learning path. Keyword coverage is good but misses a few natural phrasings a learner might use, giving slight conflict risk with generic MCP-building skills.

DimensionReasoningScore

Specificity

Multiple specific concrete actions with comprehensive coverage: 'Teaches one lesson per invocation and records wire evidence in MCP-LEARNING.md' plus 'build, secure, debug, verify, or operate MCP clients, servers, transports, gateways, registries, or conformance gates'. The action list spans the whole route rather than leaving minor gaps.

5 / 5

Completeness

Clearly answers both 'what' (focused interactive tutor for the MCP route, one lesson per invocation, records wire evidence in MCP-LEARNING.md) and 'when' ('Start or resume this route when a learner wants to build, secure, debug, verify, or operate...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good keyword coverage including the synonym pair 'Model Context Protocol (MCP)' and natural objects like 'clients, servers, transports, gateways, registries'. A few natural user terms are missing, e.g. 'MCP tutorial', 'learn MCP', and MCP primitives such as 'tools', 'prompts', or 'resources'.

4 / 5

Distinctiveness Conflict Risk

A distinct niche (a tutoring route within 'AI Engineering from Scratch') with MCP-specific triggers, but the 'when' clause ('a learner wants to build... MCP clients, servers') creates minor overlap risk with general MCP-development skills.

4 / 5

Total

18

/

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

Path

skills/learn-mcp/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.