legacy-modernizer
Designs incremental migration strategies, identifies service boundaries, produces dependency maps and migration roadmaps, and generates API facade designs for aging codebases. Use when modernizing legacy systems, implementing strangler fig pattern or branch by abstraction, decomposing monoliths, upgrading frameworks or languages, or reducing technical debt without disrupting business operations.
91
92%
Does it follow best practices?
Impact
88%
1.18xAverage score across 6 eval scenarios
Passed
No known issues
Quality
Discovery
100%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 an excellent skill description that clearly articulates specific capabilities (migration strategies, service boundary identification, dependency maps, API facades) and provides comprehensive trigger guidance via an explicit 'Use when...' clause with domain-specific terminology. It uses proper third-person voice throughout and covers both common and advanced terms that practitioners would naturally use when seeking help with legacy modernization.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'designs incremental migration strategies', 'identifies service boundaries', 'produces dependency maps and migration roadmaps', and 'generates API facade designs for aging codebases'. | 3 / 3 |
Completeness | Clearly answers both 'what' (designs migration strategies, identifies service boundaries, produces dependency maps, generates API facade designs) and 'when' with an explicit 'Use when...' clause listing five distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'legacy systems', 'strangler fig pattern', 'branch by abstraction', 'decomposing monoliths', 'upgrading frameworks or languages', 'technical debt', 'modernizing'. These are terms practitioners naturally use when facing these challenges. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around legacy system modernization with highly specific triggers like 'strangler fig pattern', 'branch by abstraction', and 'monolith decomposition' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with strong workflow clarity, excellent progressive disclosure via the reference table, and actionable code examples. Its main weakness is moderate verbosity — the constraints lists contain some obvious guidance, the output templates section is vague, and the keyword list at the bottom wastes tokens without adding value.
Suggestions
Remove the 'Knowledge Reference' keyword list at the bottom — it provides no actionable guidance and wastes tokens.
Tighten the 'Output Templates' section by either providing a concrete template/example or removing it in favor of a reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary content. The 'Knowledge Reference' section at the bottom is just a keyword list that adds no actionable value. The 'MUST DO' and 'MUST NOT DO' lists contain some obvious items (e.g., 'Communicate progress and risks transparently'). The 'Output Templates' section is vague and could be tightened or removed. | 2 / 3 |
Actionability | The skill provides fully executable Python code examples for the strangler fig facade, feature flags, and characterization tests. The code is copy-paste ready with clear comments, and the workflow steps include specific, concrete guidance like coverage targets and traffic increment percentages. | 3 / 3 |
Workflow Clarity | The 5-step workflow has explicit validation checkpoints at each stage with clear criteria (e.g., 'test suite passes green on unmodified legacy system', 'error rates and latency within baseline thresholds'). Feedback loops are present — fix and re-validate patterns, gradual traffic shifting with monitoring, and a requirement for stability before legacy removal. | 3 / 3 |
Progressive Disclosure | The reference guide table is excellently structured with clear 'Load When' context for each reference file, providing one-level-deep navigation. The main skill serves as a concise overview with detailed guidance appropriately delegated to five separate reference files. | 3 / 3 |
Total | 11 / 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
- jeffallan/claude-skills
- Commit
3d95bb1
- 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.