mapper-creator
Creates a mapper between an entity and a DTO (MapStruct or custom converter). Use this skill when a mapper/converter between entity and DTO needs to be created, either standalone or as part of a larger task (e.g. after DTO creation, during CRUD setup).
60
68%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/mapper-creator/SKILL.mdQuality
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 solid skill description that clearly communicates its purpose and when to use it. The 'Use this skill when...' clause is well-constructed with practical context about standalone vs. composite usage. The main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., generating field mappings, handling nested objects, creating bidirectional conversions).
Suggestions
Expand the capability description with more specific actions, e.g., 'Creates a mapper between an entity and a DTO using MapStruct annotations or custom converter classes, including field mappings, nested object conversion, and collection handling.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (mapper between entity and DTO) and mentions specific approaches (MapStruct or custom converter), but doesn't list multiple concrete actions beyond 'creates a mapper'. It could elaborate on what the mapper includes (e.g., field mappings, null handling, collection conversions). | 2 / 3 |
Completeness | Clearly answers both 'what' (creates a mapper between entity and DTO using MapStruct or custom converter) and 'when' (explicit 'Use this skill when...' clause with triggers including standalone use and as part of larger tasks like DTO creation or CRUD setup). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'mapper', 'converter', 'entity', 'DTO', 'MapStruct', 'CRUD setup', 'DTO creation'. These are terms a developer would naturally use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche focused specifically on entity-to-DTO mapping/conversion. It's distinct from general code generation, DTO creation, or CRUD skills, and the specific mention of MapStruct and converter patterns makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has excellent workflow clarity with well-defined steps, decision hierarchies, and a thorough anti-hallucination checklist. However, it is significantly over-verbose — much of the content is meta-instruction about how to interact with the user (when to ask, how to batch questions, how to recognize answers) rather than actionable mapper creation guidance. The progressive disclosure structure references external files appropriately but the main file itself contains too much inline content that could be extracted.
Suggestions
Reduce verbosity by 40-50%: consolidate the repeated 'don't re-ask' instructions (appears in CRITICAL header, Step 0, Smart answer recognition, and Decision-making principle) into a single concise section. Claude doesn't need the same instruction stated four different ways.
Extract the AskUserQuestion usage guidelines and the Decision-making principle into a separate reference file (e.g., references/interaction-guidelines.md) — these are generic interaction patterns, not mapper-specific content.
Add at least one concrete code example of a generated mapper (even a minimal one) directly in the SKILL.md so the skill is partially actionable without the external reference files.
Remove the extensive Step 0 context-scanning table — Claude inherently reads conversation context. A single line like 'Extract all already-provided inputs from conversation before asking questions' suffices.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines. It over-explains decision-making principles, repeats instructions multiple times (e.g., 'NEVER re-ask' appears in multiple places), includes extensive tables for context scanning that Claude could infer, and restates the same logic in different forms (Step 0 vs Decision-making principle vs Smart defaults). Much of the content is meta-instruction about how to ask questions rather than actionable mapper creation guidance. | 1 / 3 |
Actionability | The skill provides a clear step-by-step workflow and references specific tools and file paths (e.g., `references/mapstruct-java.md`, `examples/_skeletons/{variant}-{language}.md`), but contains no actual executable code examples — all code generation is delegated to external reference/example files that are not provided. The variable substitution rules and dependency addition instructions are concrete but incomplete without the referenced files. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 0-5) with explicit validation via the anti-hallucination checklist, clear decision trees for each step, and feedback loops (e.g., 'If errors: fix and re-validate' pattern for build files, asking user only when context is ambiguous). The decision-making hierarchy (context unambiguous → strong signal → ask → ask plainly) provides clear guidance for each branching point. | 3 / 3 |
Progressive Disclosure | The skill references multiple external files (references/mapstruct-java.md, references/mapping-annotations.md, examples/_skeletons/, examples/_fragments/) which is good progressive disclosure structure, but no bundle files were provided to verify these exist. The SKILL.md itself is monolithic — the extensive decision-making principles, AskUserQuestion guidelines, and Step 0 context-scanning instructions could be extracted into separate reference files to keep the main skill leaner. | 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
- Amplicode/spring-skills
- Commit
1dd96ad
- 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.