learning-opportunities
Facilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises after architectural work (new files, schema changes, refactors). Use when completing features, making design decisions, or when user asks to understand code better. Triggers on "learning exercise", "help me understand", "teach me", "why does this work", or after creating new files/modules. Do NOT use for urgent debugging, quick fixes, or when user says "just ship it".
96
95%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured description with strong trigger terms, clear 'use when' and 'do not use' guidance, and a distinctive niche. Its main weakness is that the specific capabilities (what the skill actually does/produces) could be more concrete — 'interactive learning exercises' is somewhat vague compared to listing specific actions like 'generates quiz questions, explains design patterns, walks through code step-by-step'.
Suggestions
Make the capabilities more concrete by specifying what 'interactive learning exercises' entail — e.g., 'generates comprehension questions, explains design trade-offs, walks through code logic step-by-step'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (skill development during AI-assisted coding) and some actions (offers interactive learning exercises after architectural work), but the concrete actions are somewhat vague — 'facilitates deliberate skill development' and 'offers interactive learning exercises' don't specify what those exercises look like or what concrete outputs are produced. | 2 / 3 |
Completeness | Clearly answers both 'what' (facilitates skill development, offers interactive learning exercises after architectural work) and 'when' (explicit 'Use when' clause with triggers, plus a 'Do NOT use' clause for exclusions). Both dimensions are explicitly addressed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'learning exercise', 'help me understand', 'teach me', 'why does this work', plus contextual triggers like 'after creating new files/modules'. These are phrases users would naturally say, and the negative triggers ('just ship it', urgent debugging) further refine matching. | 3 / 3 |
Distinctiveness Conflict Risk | This skill occupies a clear niche — learning/teaching during coding — that is distinct from typical coding, debugging, or documentation skills. The explicit negative triggers ('NOT for urgent debugging, quick fixes') further reduce conflict risk with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that is concise, highly actionable, and well-structured. The core principle of 'pause for input' is clearly emphasized with explicit [STOP] markers in examples, and the graduated hands-on exploration guidance shows thoughtful design. The anti-patterns section effectively prevents common failure modes without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. Every section serves a clear purpose, and there's no unnecessary explanation of concepts Claude would already know. The examples are illustrative without being verbose, and the anti-patterns section is a concise bullet list. | 3 / 3 |
Actionability | The skill provides highly concrete, actionable guidance with specific dialogue examples showing exact phrasing, clear behavioral rules (stop after question mark), and graduated examples for hands-on exploration. The exercise types include complete interaction scripts that are directly usable. | 3 / 3 |
Workflow Clarity | The workflow is crystal clear: when to offer → how to offer → core interaction rule (pause for input) → exercise types with step-by-step interaction flows → after-response handling. Each exercise type has explicit [STOP] markers as validation checkpoints, and the 'when NOT to offer' section provides clear guardrails. | 3 / 3 |
Progressive Disclosure | The skill appropriately references `references/PRINCIPLES.md` for deeper learning science content rather than inlining it. The main file is well-organized with clear sections that progress from triggers → constraints → core principle → exercise types → techniques → anti-patterns, all at a single level of depth. | 3 / 3 |
Total | 12 / 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
- tech-leads-club/agent-skills
- Commit
81e7e0d
- 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.