legacy-code-summarizer
Produces comprehensive summaries and insights about legacy codebases to help understand unfamiliar code. Use when onboarding to a new project, planning refactoring efforts, assessing code for acquisition/migration, or generating documentation for undocumented systems. Analyzes architecture, dependencies, code quality issues, and test coverage. Creates high-level overviews with architecture diagrams, key components, entry points, and actionable insights for understanding and improving legacy code.
Install with Tessl CLI
npx tessl i github:ArabelaTso/Skills-4-SE --skill legacy-code-summarizer79
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/skillValidation for skill structure
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 hits all the key criteria. It uses third person voice, provides specific concrete actions, includes a comprehensive 'Use when' clause with multiple natural trigger scenarios, and carves out a distinct niche around legacy code understanding that minimizes conflict with other code-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'produces comprehensive summaries', 'analyzes architecture, dependencies, code quality issues, and test coverage', 'creates high-level overviews with architecture diagrams, key components, entry points'. | 3 / 3 |
Completeness | Clearly answers both what (analyzes architecture, dependencies, creates overviews with diagrams) AND when with explicit 'Use when' clause covering onboarding, refactoring, acquisition/migration, and documentation scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'legacy codebases', 'onboarding', 'new project', 'refactoring', 'acquisition/migration', 'documentation', 'undocumented systems', 'architecture', 'code quality'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on legacy codebase analysis and understanding unfamiliar code, with distinct triggers like 'legacy', 'onboarding to new project', 'undocumented systems' that differentiate it from general code analysis skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides highly actionable, executable guidance for legacy code analysis with comprehensive bash commands and templates. However, it is severely bloated—the massive inline summary template, extensive example outputs, and explanations of concepts Claude already knows (architecture patterns, code smells) waste significant token budget. The content would be far more effective split into a concise overview with references to detailed templates.
Suggestions
Move the 200+ line 'Summary Template' and example summaries to a separate reference file (e.g., references/summary_template.md) and link to it
Remove explanations of concepts Claude knows (what MVC is, what code smells are, what test coverage means) and keep only the specific commands and patterns
Add explicit validation checkpoints between workflow steps (e.g., 'Verify you found at least one entry point before proceeding to Step 3')
Consolidate the Quick Reference table at the top as a TL;DR and move detailed command explanations to a reference file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 700+ lines with extensive explanations Claude already knows (what MVC is, what code smells are, basic bash commands). The summary template alone is ~200 lines of boilerplate that could be a separate reference file. | 1 / 3 |
Actionability | Provides fully executable bash commands, concrete code examples, and copy-paste ready templates. Commands for finding entry points, analyzing dependencies, and measuring coverage are specific and immediately usable. | 3 / 3 |
Workflow Clarity | Clear 7-step workflow with logical sequencing, but lacks explicit validation checkpoints between steps. No feedback loops for error recovery (e.g., what to do if commands fail or produce unexpected output). | 2 / 3 |
Progressive Disclosure | References external files (references/architecture_patterns.md, etc.) appropriately, but the main skill file is monolithic with massive inline templates and examples that should be in separate reference files. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (784 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- 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.