CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

85

1.13x
Quality

81%

Does it follow best practices?

Impact

90%

1.13x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced analysis workflow with strong executable commands and properly signaled one-level references. The main weakness is verbosity from the large placeholder report template and two full example reports that bloat the token budget.

Suggestions

Move the full report template and the two worked example reports into a reference file (e.g. references/report_template.md), keeping only a condensed outline inline in SKILL.md to cut roughly 250 lines of placeholder boilerplate.

Trim inline explanations of concepts Claude already knows, such as the 'Common patterns to look for: src/ or lib/ (source code)' directory glossary, to improve conciseness.

Add an explicit validation checkpoint after the dependency/quality analysis steps (e.g. 'Confirm findings against actual file contents before writing the summary') to strengthen the workflow's feedback loop.

DimensionReasoningScore

Conciseness

The discovery commands are lean and earn their tokens, but the ~260-line report template is largely placeholder boilerplate ([X], [Project Name]) and the two full worked example reports pad the skill noticeably.

3 / 5

Actionability

Provides copy-paste-ready, executable commands across Python, Java, and JavaScript (e.g. 'find . -name "*.py" | xargs wc -l', 'pytest --cov=src --cov-report=term-missing', 'mvn clean test jacoco:report') covering the common analysis cases.

5 / 5

Workflow Clarity

A clear 7-step sequence (survey → entry points → architecture → dependencies → quality → tests → report) with a test-quality checklist, but no explicit validate→fix→retry feedback loop; read-only analysis so the destructive/batch cap does not apply.

4 / 5

Progressive Disclosure

Three references are one level deep and clearly signaled both inline ('See references/architecture_patterns.md') and in the Resources section; the inlined report template and full examples are a minor organization gap that could live in a reference.

4 / 5

Total

16

/

20

Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states concrete capabilities and provides explicit, natural-language use-when triggers. The main gap is a few missing synonym trigger terms and minor overlap with dedicated documentation/refactoring skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — analyzes architecture, dependencies, code quality, test coverage, and creates overviews with diagrams, key components, and entry points — giving comprehensive coverage rather than just a few actions.

5 / 5

Completeness

Explicitly answers both what ('Produces comprehensive summaries… Analyzes architecture, dependencies, code quality…') and when ('Use when onboarding… planning refactoring… assessing code for acquisition/migration…') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'onboarding to a new project', 'planning refactoring efforts', 'acquisition/migration', and 'undocumented systems' give good coverage, though a few natural synonyms (e.g. 'technical debt', 'code audit') are missing.

4 / 5

Distinctiveness Conflict Risk

The 'legacy codebases' niche with onboarding/refactoring/acquisition triggers is mostly distinct, but 'generating documentation' and 'planning refactoring' create minor overlap risk with dedicated doc or refactor skills.

4 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (784 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
ArabelaTso/Skills-4-SE
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.