Skill para migracoes, modernizacao de legacy e refactors estruturais. Use quando precisar fazer upgrades grandes, extracao incremental, strangler pattern, compatibilidade de transicao e rollout seguro.
55
44%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/23-migration-refactor-specialist/SKILL.mdQuality
Discovery
67%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 establishes a clear domain around legacy migration and modernization with an explicit 'Use when' clause, which is its strongest aspect. However, it lacks concrete specific actions (it describes concepts rather than operations) and could benefit from more natural trigger terms and variations. The Portuguese language may limit discoverability for non-Portuguese users.
Suggestions
Add concrete actions such as 'create adapter layers', 'generate migration plans', 'wrap legacy modules with new interfaces', or 'produce rollback scripts' to increase specificity.
Expand trigger terms with more natural variations users might say, such as 'upgrade framework version', 'replace old module', 'deprecate legacy service', 'backward compatibility layer', 'phased migration'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (migrations, legacy modernization, structural refactors) and mentions some patterns (strangler pattern, incremental extraction), but doesn't list concrete actions like 'extract module X', 'create adapter layers', or 'generate migration scripts'. The terms are more conceptual than actionable. | 2 / 3 |
Completeness | Explicitly answers both 'what' (migrations, legacy modernization, structural refactors) and 'when' with a clear 'Use quando precisar fazer...' clause listing specific trigger scenarios like upgrades, incremental extraction, strangler pattern, transition compatibility, and safe rollout. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'migracoes', 'legacy', 'refactors', 'strangler pattern', 'upgrades grandes', and 'rollout seguro'. However, it misses common natural variations users might say such as 'migrate database', 'upgrade framework', 'deprecate old code', 'backward compatibility', or specific technology terms. The Portuguese language also limits trigger matching for English-speaking users. | 2 / 3 |
Distinctiveness Conflict Risk | Terms like 'refactors estruturais' and 'modernizacao de legacy' carve out a reasonable niche, but 'refactors' could overlap with general code refactoring skills, and 'upgrades grandes' is somewhat vague and could conflict with dependency update or version upgrade skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a high-level role description or checklist rather than actionable migration guidance. It lacks any concrete examples, executable steps, or workflow sequences — critical for a skill dealing with risky, multi-step operations like framework migrations and strangler patterns. The content tells Claude what outcomes to produce but never shows how to produce them.
Suggestions
Add a concrete, step-by-step workflow for executing a migration (e.g., 1. Audit current state → 2. Define compatibility layer → 3. Implement strangler pattern → 4. Validate phase → 5. Cut over), with explicit validation checkpoints and rollback triggers at each phase.
Include at least one concrete example — e.g., a sample migration plan structure, a strangler pattern implementation sketch, or a compatibility shim template — so Claude knows the expected output format and level of detail.
Replace the abstract 'Checklist Base' with actionable verification steps that include specific commands or checks (e.g., 'Run integration tests against both old and new paths before proceeding to next phase').
Briefly describe what each referenced policy/template contains (e.g., 'templates/migration-plan.md — phase/risk/rollback table structure') so Claude can decide whether to consult them without navigating away.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but includes some redundancy between sections (e.g., 'Checklist Base' and 'Evidencia de Conclusao' overlap significantly with rollback/phases/risks mentioned in both). The 'Governanca Global' section listing many policy files adds tokens without actionable value inline. | 2 / 3 |
Actionability | The skill provides no concrete code, commands, examples, or templates. It describes what should happen ('plano incremental', 'estrategia de compatibilidade') but never shows how — no strangler pattern example, no migration plan structure, no executable steps. It reads as an abstract checklist rather than actionable guidance. | 1 / 3 |
Workflow Clarity | There is no sequenced workflow for performing a migration. The checklist items are unordered concerns rather than steps. For a skill dealing with destructive/risky operations like migrations, the absence of explicit validation checkpoints, feedback loops, and a clear step-by-step process is a significant gap. | 1 / 3 |
Progressive Disclosure | The skill references external files (policies, templates/migration-plan.md) which is good progressive disclosure in principle, but the references are not well-signaled with descriptions of what each contains. The main content itself is thin enough that it doesn't need splitting, but it also doesn't provide enough substance to serve as a useful overview. | 2 / 3 |
Total | 6 / 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.
e9f6648
Table of Contents
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.