New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Uncle Bob Craft

by sickn33 in sickn33/agentic-awesome-skills

A skill your agent uses when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.

MITAuto-check passedDevelopment

Install Uncle Bob Craft

skills CLI
$ npx skills add sickn33/agentic-awesome-skills --skill uncle-bob-craft -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sickn33/agentic-awesome-skills uncle-bob-craft --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/uncle-bob-craft .claude/skills/uncle-bob-craft && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
uncle-bob-craft
GitHub stars
47k
Used in
2 other repos
Token cost
~2.6k tokens
SKILL.md length
1,146 words
Files
8 (incl. references)
Skills in repo
1,497
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.

  • Works in 5 steps: Boundaries and Dependency Rule: Check… → SOLID in context: Check Single… → Smells: Scan for rigidity, fragility,… → …
  • Performing code review
  • SKILL.md covers Overview, When to Use This Skill, Aggregators by Source and Design Patterns: Use vs Misuse, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Uncle Bob Craft is an agent skill from sickn33/agentic-awesome-skills. Use when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `README.md`, `examples/code-review-checklist.md` and `reference.md`).

It sits in Development, covering Linting and formatting, Refactoring and Code quality. The repository describes itself as: AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,400+ agentic skills. Includes… The licence is MIT.

When your agent uses it

  • Performing code review
  • Refactoring code
  • Discussing architecture
  • Complements clean-code and does not replace project linter/formatter

Example prompts

  • “/uncle-bob-craft”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Boundaries and Dependency Rule: Check that dependencies point inward (e.g., use cases do not depend on UI or DB details). See…
  2. SOLID in context: Check Single Responsibility, Open/Closed, Liskov, Interface Segregation, Dependency Inversion where they apply to the…
  3. Smells: Scan for rigidity, fragility, immobility, viscosity, needless complexity/repetition, opacity; list them with file/area.
  4. Concrete suggestions: Propose one or two refactors (e.g., "Extract this into a function named X," "Introduce an interface so this layer…
  5. Tests and craft: Note if tests exist and if the change respects sustainable pace (no obvious "we'll fix it later" comments that violate…

What it can do on your machine

Read from SKILL.md and the folder at commit b84d35a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Uncle Bob Craft loads about 2.6k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 1,146 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sickn33/agentic-awesome-skills at commit b84d35a, republished under its MIT licence (© sickn33). 1,146 words, ~2,608 tokens.

Download SKILL.mdSave it as .claude/skills/uncle-bob-craft/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
uncle-bob-craft
description
Use when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.
category
code-quality
risk
safe
source
community
date_added
2026-03-06
author
antigravity-contributors
tags
clean-code, clean-architecture, solid, code-review, craftsmanship, uncle-bob
tools
claude, cursor, gemini

Uncle Bob Craft

Apply Robert C. Martin (Uncle Bob) criteria for code review and production: Clean Code, Clean Architecture, The Clean Coder, Clean Agile, and design-pattern discipline. This skill is complementary to the existing @clean-code skill (which focuses on the Clean Code book) and to your project's linter/formatter—it does not replace them.

Overview

This skill aggregates principles from Uncle Bob's body of work for reviewing and writing code: naming and functions (via @clean-code), architecture and boundaries (Clean Architecture), professionalism and estimation (The Clean Coder), agile values and practices (Clean Agile), and design-pattern use vs misuse. Use it to evaluate structure, dependencies, SOLID in context, code smells, and professional practices. It provides craft and design criteria only—not syntax or style enforcement, which remain the responsibility of your linter and formatter.

When to Use This Skill

  • Code review: Apply Dependency Rule, boundaries, SOLID, and smell heuristics; suggest concrete refactors.
  • Refactoring: Decide what to extract, where to draw boundaries, and whether a design pattern is justified.
  • Architecture discussion: Check layer boundaries, dependency direction, and separation of concerns.
  • Design patterns: Assess correct use vs cargo-cult or overuse before introducing a pattern.
  • Estimation and professionalism: Apply Clean Coder ideas (saying no, sustainable pace, three-point estimates).
  • Agile practices: Reference Clean Agile (Iron Cross, TDD, refactoring, pair programming) when discussing process.
  • Do not use to replace or override the project's linter, formatter, or automated tests.

Aggregators by Source

SourceFocusWhere to go
Clean CodeNames, functions, comments, formatting, tests, classes, smellsUse @clean-code for detail; this skill references it for review/production.
Clean ArchitectureDependency Rule, layers, boundaries, SOLID in architectureSee reference.md and references/clean-architecture.md.
The Clean CoderProfessionalism, estimation, saying no, sustainable paceSee reference.md and references/clean-coder.md.
Clean AgileValues, Iron Cross, TDD, refactoring, pair programmingSee reference.md and references/clean-agile.md.
Design patternsWhen to use, misuse, cargo cultSee reference.md and references/design-patterns.md.

Design Patterns: Use vs Misuse

  • Use patterns when they solve a real design problem (e.g., variation in behavior, lifecycle, or cross-cutting concern), not to look "enterprise."
  • Avoid cargo cult: Do not add Factory/Strategy/Repository just because the codebase "should" have them; add them when duplication or rigidity justifies the abstraction.
  • Signs of misuse: Pattern name in every class name, layers that only delegate without logic, patterns that make simple code harder to follow.
  • Rule of thumb: Introduce a pattern when you feel the third duplication or the second reason to change; name the pattern in code or docs so intent is clear.

Smells and Heuristics (Summary)

Smell / HeuristicMeaning
RigiditySmall change forces many edits.
FragilityChanges break unrelated areas.
ImmobilityHard to reuse in another context.
ViscosityEasy to hack, hard to do the right thing.
Needless complexitySpeculative or unused abstraction.
Needless repetitionDRY violated; same idea in multiple places.
OpacityCode is hard to understand.

Full lists (including heuristics C1–T9-style) are in reference.md. Use these in review to name issues and suggest refactors (extract, move dependency, introduce boundary).

Review vs Production

ContextApply
Code reviewDependency Rule and boundaries; SOLID in context; list smells; suggest one or two concrete refactors (e.g., extract function, invert dependency); check tests and professionalism (tests present, no obvious pressure hacks).
Writing new codePrefer small functions and single responsibility; depend inward (Clean Architecture); write tests first when doing TDD; avoid patterns until duplication or variation justifies them.
RefactoringIdentify one smell at a time; refactor in small steps with tests green; improve names and structure before adding behavior.

How It Works

When reviewing code
  1. Boundaries and Dependency Rule: Check that dependencies point inward (e.g., use cases do not depend on UI or DB details). See references/clean-architecture.md.
  2. SOLID in context: Check Single Responsibility, Open/Closed, Liskov, Interface Segregation, Dependency Inversion where they apply to the changed code.
  3. Smells: Scan for rigidity, fragility, immobility, viscosity, needless complexity/repetition, opacity; list them with file/area.
  4. Concrete suggestions: Propose one or two refactors (e.g., "Extract this into a function named X," "Introduce an interface so this layer does not depend on the concrete DB client").
  5. Tests and craft: Note if tests exist and if the change respects sustainable pace (no obvious "we'll fix it later" comments that violate professionalism).
Show full SKILL.md (456 more words)Show less
When writing or refactoring code
  1. Prefer small, single-purpose functions and classes; use @clean-code for naming and structure.
  2. Keep dependencies pointing inward; put business rules in the center, adapters at the edges.
  3. Introduce design patterns only when duplication or variation justifies them.
  4. Refactor in small steps with tests staying green.

Examples

Example 1: Code review prompt (copy-pasteable)

Use this to ask for an Uncle Bob–oriented review:

markdown
Please review this change using Uncle Bob craft criteria (@uncle-bob-craft):
1. Dependency Rule and boundaries — do dependencies point inward?
2. SOLID in context — any violations in the touched code?
3. Smells — list rigidity, fragility, immobility, viscosity, needless complexity/repetition, or opacity.
4. Suggest one or two concrete refactors (e.g., extract function, invert dependency).
Do not duplicate lint/format; focus on structure and design.
Example 2: Before/after (extract and name)

Before (opacity, does more than one thing):

python
def process(d):
    if d.get("t") == 1:
        d["x"] = d["a"] * 1.1
    elif d.get("t") == 2:
        d["x"] = d["a"] * 1.2
    return d

After (clear intent, single level of abstraction):

python
def apply_discount(amount: float, discount_type: int) -> float:
    if discount_type == 1:
        return amount * 1.1
    if discount_type == 2:
        return amount * 1.2
    return amount

def process(order: dict) -> dict:
    order["x"] = apply_discount(order["a"], order.get("t", 0))
    return order

Best Practices

  • ✅ Use @clean-code for naming, functions, comments, and formatting; use this skill for architecture, boundaries, SOLID, smells, and process.
  • ✅ In review, name the smell or principle (e.g., "Dependency Rule violation: use case imports from the web framework").
  • ✅ Suggest at least one concrete refactor per review (extract, rename, invert dependency).
  • ✅ Run the project linter and formatter separately; this skill does not replace them.
  • ❌ Do not use this skill to enforce syntax or style; that is the linter's job.
  • ❌ Do not add design patterns without a clear duplication or variation reason.

Common Pitfalls

  • Problem: Treating every class as needing a Factory or Strategy.
    Solution: Introduce patterns only when you have a real design need (third duplication, second axis of change).

  • Problem: Review only listing "violates SOLID" without saying where or how.
    Solution: Point to the file/function and which principle (e.g., "SRP: this function parses and persists; split into parse and persist").

  • Problem: Skipping the project linter because "we applied Uncle Bob."
    Solution: This skill is about craft and design; always run the project's lint and format.

  • @clean-code — Detailed Clean Code book material (names, functions, comments, formatting, tests, classes, smells). Use for day-to-day code quality; use uncle-bob-craft for architecture and cross-book criteria.
  • @architecture — General architecture decisions and trade-offs. Use when choosing high-level structure; use uncle-bob-craft for Dependency Rule and boundaries.
  • @code-review-excellence — Code review practices. Combine with uncle-bob-craft for principle-based review.
  • @refactor-clean-code — Refactoring toward clean code. Use with uncle-bob-craft when refactoring for boundaries and SOLID.
  • @test-driven-development — TDD workflow. Aligns with Clean Agile and Clean Coder (tests as requirement, sustainable pace).

Limitations

  • Does not replace the project linter or formatter. Run lint and format separately; this skill gives design and craft criteria only.
  • Does not replace automated tests. It can remind you to write tests (Clean Coder, Clean Agile) but does not run or generate them.
  • Complementary to tooling. Use it alongside existing CI, lint, and test suites.
  • No syntax or style enforcement. It focuses on structure, dependencies, smells, and professional practice, not on brace style or line length.
  • Summaries, not the books. Full Clean Code heuristics, component principles (REP/CCP/CRP, ADP/SDP/SAP), and detailed stories are in the books; we reference the most used parts. See reference.md "Scope and attribution."

© sickn33, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in skills/uncle-bob-craft of sickn33/agentic-awesome-skills.

  • SKILL.md
  • README.md
  • examples/code-review-checklist.md
  • reference.md
  • references/clean-agile.md
  • references/clean-architecture.md
  • references/clean-coder.md
  • references/design-patterns.md

Open the folder on GitHubat commit b84d35a

Used in 2 other repositories

We found 11 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in sickn33/agentic-awesome-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Uncle Bob Craft next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Uncle Bob Craft compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Uncle Bob Craft this skillsickn33/agentic-awesome-skills47k2 repos~2.6kAutomated safety check: PassMIT
Brooks Reviewhyhmrright/brooks-lint1.5k1 repos~430Automated safety check: PassMIT
Expert Code ReviewerGulajavaMinistudio/Mayukai-Theme139—~1.4kAutomated safety check: PassMIT
Dignified Python Standardsdocling-project/docling69k—~1.5kAutomated safety check: PassApache-2.0
Clean Code GuardamElnagdy/guard-skills1.3k2 repos~4.3kAutomated safety check: PassMIT
Maintainable Code for iPolloWorkDevin-AXIS/iPolloWork6.8k—~2.7kAutomated safety check: PassCustom licence

Similar skills

  • Brooks Review

    hyhmrright/brooks-lint

    PR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Consequence → Remedy findings, drawing on twelve classic engineering books.

    1.5k GitHub starsUsed in 1 repo~430 tokens
    DevelopmentAuto-check passed

  • Expert Code Reviewer

    GulajavaMinistudio/Mayukai-Theme

    Language-agnostic workflow for code reviews and security audits against Clean Code/SOLID principles, generating formal refactoring plans.

    139 GitHub stars~1.4k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed

  • Dignified Python Standards

    docling-project/docling

    Applies opinionated production Python conventions chosen by the project's Python version: modern type syntax, pathlib, explicit checks and interface guidance.

    69k GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed

  • Clean Code Guard

    amElnagdy/guard-skills

    Reviews generated or changed production code against Clean Code, SOLID, DRY, KISS, YAGNI and LLM-specific failure modes before it ships, in any language.

    1.3k GitHub starsUsed in 2 repos~4.3k tokens
    DevelopmentAuto-check passed

  • Maintainable Code for iPolloWork

    Devin-AXIS/iPolloWork

    A code-change gate for the iPolloWork repository: search and reuse first, keep one source of truth, justify every new file or dependency, and audit the change.

    6.8k GitHub stars~2.7k tokensUpdated today
    DevelopmentAuto-check passed

  • Solid

    ramziddin/solid-skills

    A skill your agent uses when writing code, implementing features, refactoring, planning architecture, designing systems, reviewing code, or debugging.

    609 GitHub stars~2.7k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from sickn33/agentic-awesome-skills

All 1,497 skills in this repo

  • Liuguang Banlan UI

    sickn33/agentic-awesome-skills

    Implements an interface in one of two named color modes, iridescent white or colorful black, from a parameterized starter that reports measured color intensity.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed

  • User Thoughts Memory

    sickn33/agentic-awesome-skills

    Saves a user's project decisions, rules and preferences into a project-local mdbase so later sessions and other agents can recover the intent.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed

  • Using LWC Memory and Graphs

    sickn33/agentic-awesome-skills

    Keeps project decisions, research and verified results available across coding-agent sessions through LWC memory, a document Wiki graph and a CodeGraph code index.

    47k GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed

  • Find Complementary Founders

    sickn33/agentic-awesome-skills

    Guides an agent through assessing its own owner for cofounder fit, publishing an approved profile, and ranking complementary profiles other agents published for their owners.

    47k GitHub starsUsed in 1 repo~4.8k tokens
    Auto-check passed

  • Whatsapp Cloud API

    sickn33/agentic-awesome-skills

    Integracao com WhatsApp Business Cloud API (Meta). An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~4.5k tokens
    Auto-check passed

  • Cline Pilot

    sickn33/agentic-awesome-skills

    Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

    47k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed

Categories

Questions about Uncle Bob Craft

What does Uncle Bob Craft do?

A skill your agent uses when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter. Uncle Bob Craft is an agent skill from sickn33/agentic-awesome-skills. Use when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.

When should I use Uncle Bob Craft?

Uncle Bob Craft fits situations like: performing code review; refactoring code; discussing architecture; complements clean-code and does not replace project linter/formatter.

How do I install Uncle Bob Craft in Claude Code?

Run `npx skills add sickn33/agentic-awesome-skills --skill uncle-bob-craft -a claude-code`. Or copy the skill folder (skills/uncle-bob-craft in sickn33/agentic-awesome-skills) into .claude/skills/uncle-bob-craft in your project. Claude Code loads it when a task matches its description.

How do I install Uncle Bob Craft in Codex?

Run `npx skills add sickn33/agentic-awesome-skills --skill uncle-bob-craft -a codex`. Or copy the skill folder (skills/uncle-bob-craft in sickn33/agentic-awesome-skills) into .agents/skills/uncle-bob-craft in your project. Codex loads it when a task matches its description.

Can I use Uncle Bob Craft in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sickn33/agentic-awesome-skills --skill uncle-bob-craft -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/uncle-bob-craft, .gemini/skills/uncle-bob-craft, .github/skills/uncle-bob-craft and .opencode/skills/uncle-bob-craft in your project.

What does Uncle Bob Craft need to run?

SKILL.md names no scripts, command-line tools or credentials: Uncle Bob Craft is instructions for the agent only. Our summary lists: Python 3.

Does Uncle Bob Craft access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Uncle Bob Craft safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Uncle Bob Craft use?

Uncle Bob Craft is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Uncle Bob Craft use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.8k tokens, read only when the agent opens those files.

What are the alternatives to Uncle Bob Craft?

Skills that share tags, products or a category with Uncle Bob Craft: Brooks Review (hyhmrright/brooks-lint, 1.5k stars), Expert Code Reviewer (GulajavaMinistudio/Mayukai-Theme, 139 stars), Dignified Python Standards (docling-project/docling, 69k stars) and Clean Code Guard (amElnagdy/guard-skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Uncle Bob Craft?

sickn33 (a GitHub user) maintains it in sickn33/agentic-awesome-skills, which has 47,405 GitHub stars. The repository holds 1,497 skills in this directory. The repository was last updated on October 9, 2026.

Source: sickn33/agentic-awesome-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.