coding-plus
by Roy Yuen
Upgrade your AI agent with a senior-level engineering SOP focused on inspection, minimal diffs, and hard verification.
About This Skill
Elite Engineering Discipline for AI Agents
Coding Plus transforms generic AI chat into a rigorous Senior Software Engineer's workflow. The primary challenge with AI coding is "hallucination-led development"—where models make assumptions about codebase state without looking at the files. This skill enforces an Inspect-First methodology that prioritizes verification over guesswork.
What it does
The skill embeds a Model-Agnostic Standard Operating Procedure (SOP) into your agent, ensuring every task follows a consistent lifecycle: deep inspection, contract definition, minimal diff implementation, and hard verification. It forces the agent to categorize every claim under specific Verified, Inferred, and Unknown headings, eliminating the ambiguity that leads to broken builds.
Why use this skill?
- Consistent Quality: Get senior-level output regardless of whether you are using GPT-4, Claude, or local models.
- Reduced Technical Debt: Focuses on minimal diffs and preserving existing patterns rather than rewriting entire files.
- Explicit Risk Reporting: The agent must admit what it hasn't tested, allowing you to focus your review on high-risk areas.
- Universal Compatibility: Works across any language or framework (Node.js, Python, Go, etc.) by focusing on engineering logic rather than syntax.
The Output
Expect structured responses that include clear engineering success criteria and a dedicated "Residual Risk" report. No more "trust me" responses; you get actionable proof of what was run, what was fixed, and what remains to be seen.
How to Install
unzip coding-plus.zip -d ~/.claude/skills/$5
One-time purchase • Own forever
Security Scanned
Passed automated security review
Permissions
File Scopes
Tags
Frequently Asked Questions
Learn More About AI Agent Skills
Similar Skills
env-doctor
Diagnoses why your project will not start. Checks runtime versions, dependencies, environment variables, databases, ports, and build artifacts systematically.
diagnosing-rag-failure-modes
RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.
benchmarking-ai-agents-beyond-models
Published AI benchmarks measure brains in jars. They test models in isolation or within a single reference harness — and then attribute all performance to the model. This skill teaches you to decompose agent performance into its two actual components: model capability and harness multiplier. The result is evaluations that predict real-world behavior instead of benchmark theater.
code-reviewer
Reviews your code for bugs, security vulnerabilities, logic errors, performance issues, and style violations. Organizes findings by severity and suggests fixes with code examples.