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

73%

Does it follow best practices?

Impact

94%

1.11x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

63%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.

The content is well-structured and actionable with clear decision logic and reusable summary templates, but it is over-length for a summarization skill and restates concepts Claude already knows. No reference files are used, so progressive disclosure is limited to in-file headings.

Suggestions

Trim or remove the 'Handling Different Languages' table and generic 'Best Practices' subsections — Claude already knows these language features and reading strategies.

Move the four 'Common Scenarios' (and optionally the worked example) into a references/ file and link to it from SKILL.md to improve progressive disclosure and cut inline length.

Tighten 'Output Format Guidelines' and 'Limitations' to a few bullets; the formatting rules (backticks, file paths, line numbers) can stand alone without restating them across sections.

Dimension	Reasoning	Score
Conciseness	The body is well-organized but noticeably padded with things Claude already knows — the 'Handling Different Languages' feature lists (decorators, list comprehensions, goroutines) and generic 'Best Practices' advice ('Be concise', 'Read strategically') — fitting 'mostly efficient but includes some unnecessary explanation' more than the lean 4.	3 / 5
Actionability	Provides concrete, reusable templates — a four-part small-scale summary structure, a worked example block, and a drill-down prompt format — giving specific guidance with only minor gaps, appropriate for an instruction-only skill.	4 / 5
Workflow Clarity	A clear decision tree branches small vs large scale, and large-scale work is sequenced into Phase 1 overview → Phase 2 interactive drill-down (a user checkpoint) → Phase 3 detail, with only minor validation gaps since summarization is not a fragile operation.	4 / 5
Progressive Disclosure	No bundle files exist and all ~245 lines live in one SKILL.md; sections like the four Common Scenarios and the language table are inlined detail that could be externalized, fitting 'some structure; content that should be separate is inline' rather than the well-split 4.	3 / 5
	Total	14 / 20 Passed

Description

83%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.

The description is strong: it answers both what and when with concrete, natural trigger phrases and uses proper third-person voice. It is slightly verbose and the triggers are broad enough to risk minor overlap with general code-assistance skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions across scales — 'explaining intention and core logic', 'providing high-level overviews with drill-down capabilities' — with only minor overlap among near-synonyms (summarize/explain/understand), fitting the 'several specific actions; minor gaps' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Explicitly states both what ('Generate concise summaries of source code at multiple scales') and when with concrete triggers ('Use when users ask to summarize, explain, or understand code...'), matching the anchor for clearly answering both what AND when.	5 / 5
Trigger Term Quality	Includes natural user phrasings ('summarize, explain, or understand code') and concrete scope tokens ('function, class, module, entire codebase'), but omits common synonyms like 'describe' or 'walk me through', matching 'good keyword coverage; a few natural terms missing'.	4 / 5
Distinctiveness Conflict Risk	Has a clear code-summarization niche, but broad triggers like 'explain or understand code' overlap somewhat with general coding-assistant skills, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict 5.	4 / 5
	Total	17 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ArabelaTso/Skills-4-SE
Path: skills/code-summarizer/SKILL.md
Commit: 4f38503

Reviewed: 8 days 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.