legacy-modernizer
Use when modernizing legacy systems, implementing incremental migration strategies, or reducing technical debt. Invoke for strangler fig pattern, monolith decomposition, framework upgrades.
Install with Tessl CLI
npx tessl i github:jeffallan/claude-skills --skill legacy-modernizer62
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
Discovery
64%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 has strong trigger terms that developers would naturally use but inverts the typical structure by leading with 'when' rather than 'what'. It lacks explicit capability statements describing what actions Claude will perform, instead relying on pattern names to imply functionality. The description would benefit from concrete action verbs describing the skill's outputs.
Suggestions
Add explicit capability statements before the 'Use when' clause, e.g., 'Designs migration strategies, identifies service boundaries, creates incremental refactoring plans for legacy codebases.'
Specify concrete outputs or deliverables the skill produces, such as 'generates dependency maps', 'produces migration roadmaps', or 'creates API facade designs'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (legacy systems, migration) and mentions patterns like 'strangler fig pattern, monolith decomposition, framework upgrades' but lacks concrete actions - it describes concepts/patterns rather than specific actions Claude will perform (e.g., 'analyze dependencies', 'generate migration plans', 'refactor code'). | 2 / 3 |
Completeness | Has a 'Use when...' clause that addresses when to invoke, but the 'what does this do' is weak - it only implies capabilities through the trigger scenarios rather than explicitly stating what actions the skill performs. | 2 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'legacy systems', 'migration', 'technical debt', 'strangler fig pattern', 'monolith decomposition', 'framework upgrades' are all terms developers naturally use when discussing modernization work. | 3 / 3 |
Distinctiveness Conflict Risk | The specific patterns mentioned (strangler fig, monolith decomposition) provide some distinctiveness, but 'reducing technical debt' and 'framework upgrades' are broad enough to potentially overlap with general refactoring or code quality skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has good structural organization with clear progressive disclosure to reference files, but critically lacks actionability. It reads more like a role description than executable guidance—there are no code examples, specific commands, or concrete implementation patterns. The constraints are useful but the core content tells Claude what to think about rather than what to do.
Suggestions
Add concrete code examples for key patterns (e.g., a strangler fig facade implementation, a feature flag wrapper, a characterization test template)
Replace abstract workflow steps with specific commands or code snippets (e.g., 'Run `npm run test:characterization` to generate golden master files')
Remove the 'Role Definition' section entirely—Claude doesn't need persona framing, just actionable instructions
Add explicit validation checkpoints to the workflow (e.g., 'Verify test coverage meets 80% threshold before proceeding to step 4')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes some unnecessary framing ('Senior legacy modernization specialist with 15+ years of experience') and role-play setup that Claude doesn't need. The core workflow and constraints are reasonably efficient, but the 'Role Definition' section is verbose padding. | 2 / 3 |
Actionability | The skill provides no concrete code, commands, or executable examples. It describes what to do at a high level ('Apply strangler fig pattern with feature flags') but never shows how. The workflow steps are abstract concepts rather than actionable instructions. | 1 / 3 |
Workflow Clarity | The 5-step core workflow provides a clear sequence, and the MUST DO/MUST NOT DO constraints add validation guidance. However, there are no explicit validation checkpoints, feedback loops for error recovery, or concrete verification steps within the workflow itself. | 2 / 3 |
Progressive Disclosure | The reference table provides clear one-level-deep navigation to detailed guidance files with explicit 'Load When' conditions. The structure separates overview content from detailed references appropriately. | 3 / 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.
- 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.