uncle-bob-craft

Use when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/uncle-bob-craft/SKILL.md

Quality

Content

60%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 skill is well-structured with clear navigation to reference files and provides actionable review checklists and code examples. Its main weakness is significant verbosity and repetition—the same concepts (dependency rule, SOLID, smells, design patterns) are restated across multiple sections (Overview, When to Use, Review vs Production, How It Works, Best Practices, Common Pitfalls), and many of these concepts are things Claude already knows. Trimming redundancy and moving detailed tables to reference files would substantially improve token efficiency.

Suggestions

Consolidate the overlapping sections (Overview, When to Use, Review vs Production, How It Works, Best Practices) into fewer sections to eliminate the repeated mentions of dependency rule, SOLID, smells, and design patterns.

Move the Smells and Heuristics table and the Design Patterns: Use vs Misuse section into reference.md, keeping only a one-line pointer in SKILL.md, since Claude already understands these concepts.

Remove explanations of well-known concepts (e.g., what rigidity, fragility, and immobility mean) and trust Claude's existing knowledge—just list the smell names as a checklist.

Dimension	Reasoning	Score
Conciseness	The skill is significantly verbose, with extensive repetition across sections. The 'When to Use', 'Overview', 'Review vs Production', 'How It Works', and 'Best Practices' sections all restate the same ideas (dependency rule, SOLID, smells, patterns). The aggregator table, the smells table, and the design patterns section explain concepts Claude already knows well. Much of this could be condensed to half the length without losing actionable content.	2 / 5
Actionability	The skill provides a concrete code review checklist (Example 1), a before/after code example (Example 2), and specific refactoring suggestions (extract function, invert dependency). However, most guidance remains at the principle level rather than providing executable commands or scripts. The code examples are real Python and copy-pasteable, which is good.	4 / 5
Workflow Clarity	The 'When reviewing code' section provides a clear 5-step sequence, and 'When writing or refactoring code' gives a 4-step sequence. These are well-ordered and logical. However, there are no explicit validation checkpoints or feedback loops (e.g., 'if smell persists after refactor, re-evaluate'). Since this is not a destructive/batch operation, the missing feedback loops don't trigger the cap at 3, but the workflows could be tighter.	4 / 5
Progressive Disclosure	The skill has a clear aggregator table pointing to reference files (reference.md, references/clean-architecture.md, etc.) and references the @clean-code skill appropriately. Navigation is one level deep and well-signaled. However, since no bundle files were provided, we cannot verify the referenced files exist. The main content could benefit from moving more detail (e.g., the smells table, design patterns section) into the reference files to keep the SKILL.md leaner.	4 / 5
	Total	14 / 20 Passed

Description

32%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.

This description focuses almost entirely on when to use the skill but fails to explain what the skill actually does. It lacks concrete actions or capabilities, making it impossible to understand the skill's value proposition. The broad scope covering code review, refactoring, and architecture creates high overlap risk with other coding skills.

Suggestions

Add explicit capability statements describing what the skill does (e.g., 'Enforces SOLID principles, identifies code smells, suggests design pattern improvements').

Narrow the scope or add specifics that distinguish this from other code-related skills—what unique guidance does it provide that 'clean-code' doesn't?

Include more natural trigger terms and synonyms users might say (e.g., 'PR review', 'code quality', 'design patterns', 'best practices', 'technical debt').

Dimension	Reasoning	Score
Specificity	Names the domain (code review, writing/refactoring code, architecture) but provides no concrete actions—it says when to use it but not what it actually does. No specific capabilities are listed.	2 / 5
Completeness	Has a clear 'when' clause but the 'what' is essentially missing—we know when to use it but not what it actually does or provides. The description only tells us trigger conditions without explaining the skill's capabilities.	2 / 5
Trigger Term Quality	Includes some relevant keywords like 'code review', 'refactoring', and 'architecture' that users might naturally say, but misses many variations and synonyms (e.g., 'PR review', 'design patterns', 'code quality', 'best practices').	3 / 5
Distinctiveness Conflict Risk	Very broad scope covering code review, writing, refactoring, and architecture—this could overlap with many coding-related skills. The mention of 'complements clean-code' hints at differentiation but doesn't clearly carve out a distinct niche.	2 / 5
	Total	9 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/uncle-bob-craft/SKILL.md
Commit: 900c504

Reviewed: 6 hours 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.