Agent-Rules Pack: Conventional Commits + 6-Persona PR Review + 5 Whys Root-Cause Analysis
Curates three core project-rules from steipete/agent-rules into a single rule pack usable directly as a slash command: semantic commits (12 types plus emoji, with automatic splitting into atomic commits), a 6-persona professional PR review, and 5 Whys root-cause analysis.
# Agent Rule Pack — pick ONE mode per invocation
# Works as a Claude Code / Cursor slash command. Set {{MODE}} to: commit | pr-review | five-whys
MODE: {{MODE}}
CONTEXT: {{CONTEXT}} # e.g. the diff, the PR link, or the problem statement
=== MODE: commit ===
Create well-formatted, ATOMIC commits.
1. Run `git status`. If nothing is staged, review changes and stage the relevant ones.
2. Run pre-commit checks if the project has them (lint, build, type-check). Fix failures before committing.
3. If the staged changes cover unrelated concerns, SPLIT them into multiple commits — one concern each.
4. Pick the type and emoji, then write `type(scope): description` (imperative, lowercase, no trailing period). Add a body explaining WHY for non-trivial changes.
✨ feat | 🐛 fix | 📝 docs | ♻️ refactor | 🎨 style | ⚡️ perf | ✅ test | 🧑💻 chore | 🚧 wip | 🔥 remove | 🚑 hotfix | 🔒 security
=== MODE: pr-review ===
Review the change through SIX personas, each with its own checklist. Report findings per persona.
1. Product Manager — does it deliver the intended business value and meet requirements?
2. Developer — maintainability, standards, performance, scalability.
3. Quality Engineer — test coverage, edge cases, regression risk.
4. Security Engineer — vulnerabilities, authn/authz, input validation, data protection.
5. DevOps — CI/CD, config, monitoring, rollback safety.
6. UI/UX Designer — visual consistency, usability, accessibility, responsiveness.
RULE: anything you'd "fix later" must be raised NOW. End with: APPROVE or REQUEST CHANGES + the blocking items.
=== MODE: five-whys ===
Find the ROOT cause, not the symptom. Focus on process, not people.
1. State the problem/symptom precisely.
2. Ask "why" five times in a chain; each answer feeds the next question (Why 1 → Why 5).
3. Validate the chain: would fixing the final cause actually prevent recurrence?
4. Propose solutions that target the ROOT cause, plus a preventive measure so it can't return.
Output: the numbered Why-chain, a one-line root-cause statement, then the fix + prevention.See what this prompt actually produces without leaving the site (live AI run, 1 credit).
Don't just copy-paste — download and drop it at ~/.claude/skills/steipete-agent-rules-commit-pr-fivewhys-pack/SKILL.md and every future session can use it automatically.
mkdir -p ~/.claude/skills/steipete-agent-rules-commit-pr-fivewhys-pack && mv ~/Downloads/SKILL.md ~/.claude/skills/steipete-agent-rules-commit-pr-fivewhys-pack/SKILL.mdNew-Item -ItemType Directory -Force "$env:USERPROFILE\.claude\skills\steipete-agent-rules-commit-pr-fivewhys-pack" | Out-Null; Move-Item "$env:USERPROFILE\Downloads\SKILL.md" "$env:USERPROFILE\.claude\skills\steipete-agent-rules-commit-pr-fivewhys-pack\SKILL.md"## What This Is / What Problem It Solves Three problems that happen every day and get tolerated every day: commit messages written carelessly (making git log unreadable later), PR reviews that depend on the reviewer's mood at the moment (missing security issues or test gaps), and bugs that get patched on the surface only to recur (because the real cause was never found). steipete/agent-rules turns these into 'rule files' so an AI assistant applies the same standard every time. This piece curates the three most useful rules into one pack with switchable modes. ## Why This Source Is Worth Using The source is agent-rules by Peter Steinberger (steipete, a well-known iOS open-source author and founder of PSPDFKit), MIT-licensed and commercially usable. These rules were originally `.mdc` rule files he refined while using Cursor — and a `.mdc` rule is essentially usable as a Claude Code slash command as-is (just copy it into `.claude/commands/`), so the same rule set works across both Cursor and Claude Code. The three rules are all substantial: - **commit**: 12 Conventional Commit types paired with emoji (✨ feat / 🐛 fix / 📝 docs / ♻️ refactor, etc.), runs pre-commit checks first, emphasizes atomic commits, and proactively splits unrelated changes into separate commits. - **pr-review**: Reviews using 6 professional personas (PM / Engineering / QA / Security / DevOps / UI-UX), each with its own checklist, plus one hard rule: 'if you're planning to fix it later, fix it now.' - **five (5 Whys)**: Define the problem → ask 'why' five times in a row → verify the causal chain → propose a fix and preventive measure targeting the root cause, with an emphasis on addressing the issue, not the person. ## How to Use It (Steps) 1. Save the full_prompt above as a Claude Code slash command (`.claude/commands/agent-rule.md`), or paste it directly into a conversation. 2. Set `{{MODE}}` to `commit`, `pr-review`, or `five-whys`, and supply the relevant material in `{{CONTEXT}}` (a diff, a PR link, or a problem description). 3. The AI will follow that mode's fixed process and produce output. If you want the full, unmodified rule set, just clone the repo and drop `project-rules/*.mdc` straight into your tooling. ## When to Use It - You want to standardize your team's commit style and PR review quality. - A production incident or a recurring bug needs a structured root-cause dig instead of a quick patch. - You use both Cursor and Claude Code and want one rule set that works for both. 📎 Source: steipete/agent-rules (project-rules, by Peter Steinberger, MIT License) — this piece is a Traditional Chinese adaptation combining the three rules into a mode-switchable version; see the link above for the original individual `.mdc` rule files.
[MODE]要執行的模式：commit（語意化提交）/ pr-review（6 視角審查）/ five-whys（根因分析）
[CONTEXT]對應模式的輸入材料：commit 給變更、pr-review 給 diff 或 PR 連結、five-whys 給問題描述
填下面的欄位，上方 prompt 會即時替換 [方括號] 內容。填好後按「複製組好的 prompt」直接丟進工具。
# Agent Rule Pack — pick ONE mode per invocation
# Works as a Claude Code / Cursor slash command. Set {{MODE}} to: commit | pr-review | five-whys
MODE: {{MODE}}
CONTEXT: {{CONTEXT}} # e.g. the diff, the PR link, or the problem statement
=== MODE: commit ===
Create well-formatted, ATOMIC commits.
1. Run `git status`. If nothing is staged, review changes and stage the relevant ones.
2. Run pre-commit checks if the project has them (lint, build, type-check). Fix failures before committing.
3. If the staged changes cover unrelated concerns, SPLIT them into multiple commits — one concern each.
4. Pick the type and emoji, then write `type(scope): description` (imperative, lowercase, no trailing period). Add a body explaining WHY for non-trivial changes.
✨ feat | 🐛 fix | 📝 docs | ♻️ refactor | 🎨 style | ⚡️ perf | ✅ test | 🧑💻 chore | 🚧 wip | 🔥 remove | 🚑 hotfix | 🔒 security
=== MODE: pr-review ===
Review the change through SIX personas, each with its own checklist. Report findings per persona.
1. Product Manager — does it deliver the intended business value and meet requirements?
2. Developer — maintainability, standards, performance, scalability.
3. Quality Engineer — test coverage, edge cases, regression risk.
4. Security Engineer — vulnerabilities, authn/authz, input validation, data protection.
5. DevOps — CI/CD, config, monitoring, rollback safety.
6. UI/UX Designer — visual consistency, usability, accessibility, responsiveness.
RULE: anything you'd "fix later" must be raised NOW. End with: APPROVE or REQUEST CHANGES + the blocking items.
=== MODE: five-whys ===
Find the ROOT cause, not the symptom. Focus on process, not people.
1. State the problem/symptom precisely.
2. Ask "why" five times in a chain; each answer feeds the next question (Why 1 → Why 5).
3. Validate the chain: would fixing the final cause actually prevent recurrence?
4. Propose solutions that target the ROOT cause, plus a preventive measure so it can't return.
Output: the numbered Why-chain, a one-line root-cause statement, then the fix + prevention.Suno Engineer's Mindset: 4 Steps to a Song That Doesn't Sound Like AI
A studio engineer's breakdown of Suno's fatal weaknesses (fried vocals, high-frequency artifacts), plus a 4-step DAW workflow and a Suno Studio cleanup prompt.
5 Claude Weekly Workflows That Stuck After 6 Months
Proposal generator / meeting processor / content repurposer / Friday review / shutdown reset — out of 40 I tried, only these 5 survived, each saving 30+ minutes per run.