CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mcpa-certification

AI-native tutor and onboarding workflow for the MCPA (Model Context Protocol Associate) certification in AI Engineering from Scratch. Use when a learner wants to prepare for the MCPA, resume their certification path, learn the next lesson interactively, run and verify practical labs, take the diagnostic or a full mock, or remediate weak exam domains from GitHub with Claude Code, Codex, ChatGPT, Cursor, or another agent.

Quality

91%

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 mcpa-certification in rohitg00/ai-engineering-from-scratch

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.

An instruction-heavy skill body that is exceptionally actionable and rigorously sequenced, with explicit validation gates, feedback loops, and honest-handling rules (lab pending, untimed attempts, no-pass guarantees). Its weaknesses are modest: a few trimmable passages and a long single-file layout where some reference material could be split out.

Suggestions

Tighten the longest enumerations (e.g., the capstone feature list and repeated single-track/no-overwrite statements) to reclaim tokens without losing directives.

Consider moving stable reference material such as the full MCPA-CERTIFICATION.md template or the lesson-screen operating details into a references/ file, keeping SKILL.md as a leaner overview with one-level-deep pointers.

Relocate the 'Lesson screen' section adjacent to 'Lesson mode' (or under it) so the mode-specific material is grouped together.

DimensionReasoningScore

Conciseness

The body is dense and imperative with essentially no explanation of concepts Claude already knows, and it handles time-sensitive protocol facts by explicitly framing older revisions as deprecated ('present Roots, Sampling, Logging, and Dynamic Client Registration as deprecated features'). However, a few passages could be tightened, such as the long capstone feature enumeration and restatements of the no-overwrite and single-track rules, so it fits anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Guidance is fully executable: exact commands ('python3 <lesson-path>/code/main.py', 'python3 -m unittest discover -s <lesson-path>/code/tests -v', 'python3 scripts/check_mcpa_wire.py <lesson-path>'), a complete copy-paste markdown template for MCPA-CERTIFICATION.md, exact file paths and raw-GitHub URLs, a numbered mode-selection decision list, and concrete thresholds (70 percent quiz, exact set-equality scoring, archive naming 'MCPA-CERTIFICATION-<YYYY-MM-DD>.md'). The <lesson-path> placeholders are justified because paths are read from the track JSON rather than invented.

5 / 5

Workflow Clarity

All four modes are clearly sequenced with explicit validation checkpoints and feedback loops: ordered mode-selection rules, a recall gate ('If both answers are wrong, offer review before advancing'), an all-conditions completion checklist, 'Do not mark practical work verified if the runtime or tests did not actually run', review-queue updates on quiz misses, untimed-attempt recording, and mock rotation for retakes. This matches the anchor-5 pattern of clear sequence with explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

There is no bundle (references/, scripts/, assets/ are absent), and the skill appropriately avoids inlining the curriculum by pointing one level deep into the upstream repository's files with a purpose-annotated list ('Program policy...: certifications/mcpa/program.json', 'Ordered route...: certifications/mcpa/tracks/mcpa-f.json'). Sections are well organized, but the ~330-line single file inlines content that could arguably live in reference files (the state-file template, lesson-screen details), and the 'Lesson screen' section is placed between Onboarding and Lesson mode, giving minor organization gaps consistent with anchor 4.

4 / 5

Total

18

/

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 description that states a concrete capability set in third person and pairs it with an explicit, multi-scenario 'Use when' clause covering every mode the skill supports. The only gap is a handful of common synonyms (e.g., 'study', 'practice exam') that would broaden natural trigger coverage.

Suggestions

Add one or two common user phrasings such as 'study for the MCPA' or 'take a practice exam' to the 'Use when' clause to catch natural trigger variants.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete, distinct actions covering all of the skill's modes: 'AI-native tutor and onboarding workflow', 'prepare for the MCPA', 'resume their certification path', 'learn the next lesson interactively', 'run and verify practical labs', 'take the diagnostic or a full mock', and 'remediate weak exam domains'. This is comprehensive coverage of the skill's capabilities, not vague domain naming, and it is written in third person.

5 / 5

Completeness

It explicitly answers both questions: the 'what' is stated up front ('AI-native tutor and onboarding workflow for the MCPA (Model Context Protocol Associate) certification in AI Engineering from Scratch') and the 'when' is an explicit 'Use when a learner wants to...' clause listing concrete trigger scenarios, matching the anchor-5 pattern exactly.

5 / 5

Trigger Term Quality

Trigger phrases are natural and broad ('prepare for the MCPA', 'take the diagnostic or a full mock', 'remediate weak exam domains') and even name host tools ('Claude Code, Codex, ChatGPT, Cursor'), but a few common natural variants are missing, such as 'study for the MCPA' or 'practice exam/practice questions'. This sits between anchor 4 (good coverage, a few natural terms missing) and anchor 5 (comprehensive including synonyms), closer to 4.

4 / 5

Distinctiveness Conflict Risk

The description names a very specific niche — MCPA certification preparation for a named repository ('AI Engineering from Scratch') with named agent hosts — so it is clearly distinguishable from generic tutoring, study, or document skills and is unlikely to trigger the wrong skill.

5 / 5

Total

19

/

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

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

rohitg00/ai-engineering-from-scratch

Path

.claude/skills/mcpa-certification/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.