code-summarizer

Generate concise summaries of source code at multiple scales. Use when users ask to summarize, explain, or understand code - whether it's a single function, a class, a module, or an entire codebase. Handles function-level code by explaining intention and core logic, and large codebases by providing high-level overviews with drill-down capabilities for specific modules.

1.11x

Quality

77%

Does it follow best practices?

Impact

94%

1.11x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/code-summarizer/SKILL.md

Quality

Content

62%

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

This skill provides a solid framework for code summarization with clear workflow structure and good example output formats. However, it suffers from verbosity - explaining concepts Claude already knows (writing style best practices, strategic reading approaches) and lacking concrete executable examples. The skill would benefit from trimming obvious guidance and adding more specific, actionable techniques.

Suggestions

Remove the 'Writing Style' and 'Code Analysis Approach' subsections under Best Practices - these describe general competencies Claude already has

Cut the 'Handling Different Languages' section which just lists obvious terminology without adding actionable guidance

Add concrete code examples showing actual analysis techniques (e.g., how to identify entry points, how to trace dependencies)

Move 'Common Scenarios' to a separate SCENARIOS.md file and keep only the decision tree and output format templates in the main skill

Dimension	Reasoning	Score
Conciseness	The skill contains useful information but is verbose in places. The 'Best Practices' and 'Common Scenarios' sections explain concepts Claude already knows (like reading strategically, being concise in writing). The language-specific section lists obvious terminology without adding value.	2 / 3
Actionability	Provides good structural templates and example formats, but lacks executable code examples. The guidance is more descriptive than prescriptive - it tells Claude what to include in summaries but doesn't provide concrete code analysis techniques or tools to use.	2 / 3
Workflow Clarity	The decision tree clearly distinguishes small-scale vs large-scale approaches. The three-phase workflow for large codebases (overview → prompt for drill-down → detailed analysis) is well-sequenced with clear transitions between phases.	3 / 3
Progressive Disclosure	Content is reasonably organized with clear sections, but the skill is monolithic at ~250 lines when some sections (Common Scenarios, Best Practices) could be separate reference files. The 'Limitations' section at the end is appropriate but the middle sections are bloated.	2 / 3
	Total	9 / 12 Passed

Description

92%

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 a strong skill description that clearly articulates its purpose (code summarization at multiple scales) and provides explicit trigger conditions. The description uses appropriate third-person voice and includes natural user language. Minor weakness is potential overlap with other code explanation or documentation skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'generate concise summaries', 'explaining intention and core logic', 'providing high-level overviews with drill-down capabilities'. Covers multiple scales (function, class, module, codebase) with distinct handling for each.	3 / 3
Completeness	Clearly answers both what ('Generate concise summaries of source code at multiple scales') and when ('Use when users ask to summarize, explain, or understand code') with explicit trigger guidance and scope clarification.	3 / 3
Trigger Term Quality	Includes natural keywords users would say: 'summarize', 'explain', 'understand code', 'function', 'class', 'module', 'codebase'. These are terms users naturally use when seeking code comprehension help.	3 / 3
Distinctiveness Conflict Risk	While focused on code summarization, terms like 'explain' and 'understand code' could overlap with general code explanation or documentation skills. The multi-scale aspect helps distinguish it, but 'explain code' is a common request that other skills might also handle.	2 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: ArabelaTso/Skills-4-SE
Commit: 0f00a4f

Reviewed: 4 months ago

Table of Contents

Discovery Implementation Validation

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.