Is the AI Development Guide skill free?

Yes. The skill itself is free from shinpr/claude-code-workflows. SkillProof publishes the install command and an independent test verdict at no cost.

What is the AI Development Guide SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install AI Development Guide?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use AI Development Guide with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

AI Development Guide

Backend code-review criteria: anti-patterns, fail-fast errors, Rule of Three, quality gates

by shinpr · shinpr/claude-code-workflows

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · e8c1b27

⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 21, 2026; it's queued for a re-test.

Fetched via GitHub API; found 5 byte-identical copies of SKILL.md (top-level skills/ and four dev-workflows* plugin dirs) — used the top-level one. Frontmatter parses with name+description; body is pure prose with zero script/file references, no hardcoded paths, no security smells. Installed cleanly into a temp HOME. Trigger test: 3 review/debug/completeness phrasings loaded it, 2 adjacent ones (build a React dropdown; write an API blog post) correctly did not — 5/5. Output test: reviewed a 3-function Python sample with silent except-returns-default fallbacks and a user/admin near-duplicate. Baseline review recommended "extract a shared helper to remove the duplication"; the skill-following review gave the opposite, traceable recommendation — "Do NOT extract a shared helper yet" per the Rule-of-Three table (2nd occurrence = consider only) plus the users-vs-admins-may-diverge caveat — and reframed the discount fallback as unacceptable absent a defined recovery contract rather than baseline's "just log it."

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What AI Development Guide does

A prose guide that gives Claude language-agnostic and backend technical decision criteria: an anti-pattern catalog, fail-fast error-masking detection, Rule-of-Three duplication rules, impact analysis, and a universal quality-check workflow. Triggers when reviewing backend/general implementation choices, code smells, failure chains, or judging implementation completeness. Pure guidance, no scripts or external dependencies.

How to install AI Development Guide

git clone --depth 1 https://github.com/shinpr/claude-code-workflows.git /tmp/ai-development-guide-src
mkdir -p ~/.claude/skills
cp -R /tmp/ai-development-guide-src/skills/ai-development-guide ~/.claude/skills/ai-development-guide
# Pure-prose SKILL.md (~293 lines), no scripts, no external deps, no API keys.
# Repo ships 5 identical copies (top-level skills/ + four dev-workflows* plugin dirs);
# the top-level skills/ copy above is the clean standalone install.
# Plugin-marketplace alternative: install the `dev-workflows` plugin from this repo
# to get the full recipe workflow (/recipe-implement, /recipe-design, etc.).

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger AI Development Guide

/ai-development-guide Backend code-review criteria: anti-patterns, fail-fast errors, Rule of Three, quality gates

It also activates on plain-language prompts like these:

Check this code for common anti-patterns
Help me decide between these two architecture options
Run a quality check workflow on this feature

Frequently asked questions

Is the AI Development Guide skill free?: Yes. The skill itself is free from shinpr/claude-code-workflows. SkillProof publishes the install command and an independent test verdict at no cost.
Does AI Development Guide work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched via GitHub API; found 5 byte-identical copies of SKILL.md (top-level skills/ and four dev-workflows* plugin dirs) — used the top-level one. Frontmatter parses with name+description; body is pure prose with zero script/file references, no hardcoded paths, no security smells. Installed cleanly into a temp HOME. Trigger test: 3 review/debug/completeness phrasings loaded it, 2 adjacent ones (build a React dropdown; write an API blog post) correctly did not — 5/5. Output test: reviewed a 3-function Python sample with silent except-returns-default fallbacks and a user/admin near-duplicate. Baseline review recommended "extract a shared helper to remove the duplication"; the skill-following review gave the opposite, traceable recommendation — "Do NOT extract a shared helper yet" per the Rule-of-Three table (2nd occurrence = consider only) plus the users-vs-admins-may-diverge caveat — and reframed the discount fallback as unacceptable absent a defined recovery contract rather than baseline's "just log it."
What is the AI Development Guide SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install AI Development Guide?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use AI Development Guide with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.