coding-tutor
Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that compounds over time using the power of AI, spaced repetition and quizes.
61
41%
Does it follow best practices?
Impact
94%
1.91xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/coding-tutor/skills/coding-tutor/SKILL.mdQuality
Discovery
32%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 conveys a general sense of the skill's purpose—personalized coding education with spaced repetition—but lacks concrete action verbs, explicit trigger guidance, and natural user-facing keywords. It also uses second person ('your existing knowledge', 'your actual codebase') which violates the third-person voice guideline, and contains a typo ('quizes'). The marketing-style language ('the power of AI', 'compounds over time') adds fluff without aiding skill selection.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms like 'teach me', 'learn', 'tutorial', 'practice coding', 'explain concept', 'quiz me'.
Replace vague/marketing language ('the power of AI', 'compounds over time') with specific actions like 'Generates coding exercises, creates quizzes, tracks learning progress, adapts difficulty based on prior sessions'.
Rewrite in third person voice (e.g., 'Creates personalized coding tutorials based on the user's existing knowledge') and fix the typo 'quizes' → 'quizzes'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (coding tutorials) and some actions (creates learning trail, uses spaced repetition and quizzes), but the actions are not very concrete—'personalized coding tutorials' and 'persistent learning trail' are somewhat vague about what specific operations are performed. | 2 / 3 |
Completeness | Describes what it does (personalized coding tutorials with spaced repetition) but has no explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is entirely missing, which per the rubric should cap completeness at 2, and the 'what' is also somewhat weak, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'coding tutorials', 'spaced repetition', 'quizzes', and 'codebase', but misses common user-facing trigger terms like 'learn', 'teach me', 'explain', 'practice', 'exercises', or 'study'. Users seeking tutorials might not say 'learning trail'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of coding tutorials + spaced repetition + quizzes is somewhat distinctive, but 'coding tutorials' could overlap with general code explanation or documentation skills. The lack of explicit triggers increases conflict risk. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with concrete scripts, file templates, and clear commands, but suffers significantly from verbosity — extensive teaching philosophy, writing style guidance, and pedagogical advice that Claude doesn't need. The workflow is understandable but lacks explicit validation checkpoints and error recovery steps. The monolithic structure would benefit from splitting into separate files for onboarding, teaching, and quizzing workflows.
Suggestions
Cut the 'Teaching Philosophy', 'Tutorial Writing Style', and 'What Makes Great Teaching' sections down to 3-5 bullet points total — Claude already knows how to teach well; focus on project-specific constraints only.
Add explicit validation steps: verify setup script succeeded, verify tutorial file was created before editing, validate frontmatter format after writing.
Split into separate files: ONBOARDING.md for the interview process, QUIZ_MODE.md for quiz details and spaced repetition, keeping SKILL.md as a concise overview with references.
Remove explanatory prose like 'Learning from abstract examples is forgettable; learning from YOUR code is sticky' — these are justifications Claude doesn't need.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It explains teaching philosophy, writing style guidance ('like Julia Evans, Dan Abramov'), and meta-commentary about what makes great teaching — all things Claude already knows how to do. Sections like 'What Makes Great Teaching' with DO/DON'T/CALIBRATE are generic pedagogical advice that waste tokens. The onboarding interview questions and teaching philosophy could be dramatically condensed. | 1 / 3 |
Actionability | The skill provides concrete, executable commands (setup script, index script, create_tutorial script, quiz_priority script), specific file paths, exact YAML frontmatter templates, and clear examples of quiz recording format. The workflow is copy-paste ready with real bash commands and file structures. | 3 / 3 |
Workflow Clarity | The multi-step processes (onboarding → profile creation → tutorial planning → tutorial creation → quizzing) are described but spread across many sections without a clear sequential overview. There are no explicit validation checkpoints — e.g., no verification that the setup script succeeded, no check that the tutorial file was created correctly before editing, no validation of frontmatter format. The curriculum approval step is a good checkpoint but overall the workflow lacks explicit error recovery. | 2 / 3 |
Progressive Disclosure | The content is monolithic — everything is in one long file with no references to separate documentation for advanced topics. The teaching philosophy, tutorial writing style, quiz mode, and onboarding could each be separate files referenced from a concise overview. The scripts are referenced but no bundle files were provided, making it impossible to verify their existence or content. | 2 / 3 |
Total | 8 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- EveryInc/compound-engineering-plugin
- Commit
422ffc7
- 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.