skills/general-coding-guidelines/SKILL.md
General coding rules across all file types to maintain code quality, consistency, and prevent common errors. Make sure to use this skill whenever the user asks you to write code, refactor code, review code, or suggest architectural changes.
npx skillsauth add hrdtbs/agent-skills general-coding-guidelinesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill provides general coding rules to maintain code quality, consistency, and prevent common errors. These rules apply across all file types and languages.
Always verify information before presenting it. Do not make assumptions or speculate without clear evidence. Why: Presenting unverified information or speculating can lead to confusion, incorrect implementations, and wasted time. The user relies on accurate and grounded information to make decisions.
When suggesting or implementing changes across multiple files, present the changes file by file. Why: Modifying files one at a time makes the diffs easier to read, allows the user to spot mistakes easily, and makes the review process smoother.
Never use apologies in your communication. Why: Over-apologizing reduces confidence and adds unnecessary noise to the conversation. Focus on correcting the issue and moving forward constructively.
Avoid giving feedback about your understanding in code comments or documentation. Why: Code comments should be reserved for explaining why the code does what it does, not for conversational feedback or meta-commentary about the task itself. This keeps the codebase clean and concise.
Don't suggest or make arbitrary whitespace changes unless specifically requested (e.g., when running a formatter). Why: Unnecessary whitespace changes pollute diffs, making it harder to see the actual logical changes in the code.
Provide all edits for a single file in a single chunk instead of multiple-step instructions or explanations for the same file. Why: Providing a single comprehensive chunk for a file makes it easier for the user or the automated system to apply the changes without having to manually stitch together multiple snippets.
testing
Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.
testing
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
development
Evaluate and score user-written LLM prompts on a 100-point scale across 5 axes (Clarity, Structure, Information Content, Specificity, Context), providing specific improvement suggestions and a revised prompt. Make sure to use this skill whenever the user asks to evaluate, review, score, or improve a prompt, or when they say things like 'このプロンプトどう?', 'プロンプトを評価して', 'rate my prompt', 'review this prompt', or 'is this prompt good enough?'. This skill focuses on scoring existing prompts, not writing new ones from scratch.
testing
Apply prompt engineering best practices to write, refine, and optimize system prompts, user prompts, and agent instructions. Use this skill whenever the user wants to write a prompt, optimize an existing prompt for better results, fix a prompt that is hallucinating or underperforming, or structure prompts for Large Language Models (LLMs). Even if the user just says "help me write instructions for my agent", trigger this skill.