PUA says NO. YES says YES.
A Claude Code skill that makes AI safe, evidence-based, and thorough — with encouragement, not pressure.
別 PUA 你的 AI，YES 它。
Your CLAUDE.md has one layer. AI reads it, then chooses whether to follow it.
YES.md has six layers. AI has to get past all six to cut corners.
| Layer | What | How | Who Enforces |
|---|---|---|---|
| 1 | Format — AI actually understands your rules | AI.MD converts prose to structured-label format | Format |
| 2 | Trigger — activates at exactly the right moment | 20+ specific trigger conditions in SKILL.md description | Skill engine |
| 3 | Hooks — blocks dangerous commands, reminds checks | Scripts run automatically before/after AI actions | Machine |
| 4 | Anti-Slack — 7 lazy patterns caught and corrected | Deflecting, guessing, spinning, surface-fix, empty questions... | AI self-correction |
| 5 | Gates — no backup = no edit, no test = no "done" | Hard stop rules that halt progress until requirements are met | AI self-discipline |
| 6 | Memory — mistakes get recorded, never repeated | Error logs + knowledge base persist across sessions | External storage |
Layer 3 is the key. Everything else relies on AI self-discipline. Hooks are scripts that run automatically — the AI cannot bypass them even if it wants to.
Most tools give you Layer 4 or 5 alone. That's why they don't work. Six layers together is why YES.md works.
AI coding assistants have seven bad habits:
| Bad Habit | What Happens |
|---|---|
| 🎲 Guessing | "Probably a permissions issue" — without checking |
| 🙈 Deflecting | "Please check your environment manually" |
| 🩹 Surface fixing | Fixes one bug, ignores three related ones |
| 🔄 Blind retrying | Same command 3 times, then gives up |
| 🤷 Empty questions | "Can you confirm X?" — without investigating X |
| 💬 Advice, not action | "I suggest..." instead of actual code |
| 🛠️ Ignoring tools | Has WebSearch but guesses. Has Bash but doesn't run. |
PUA-style skills fix habit #4 (blind retry / giving up).
YES.md fixes all seven.
| Pillar | What It Does |
|---|---|
| Safety Gates | Backup before editing. Check blast radius. Verify after changes. Pre-flight before deploy. |
| Evidence Rules | No guessing. No "probably." Every claim needs data, line numbers, or tool output. |
| Ripple Awareness | After every fix: check same pattern elsewhere, check upstream/downstream, check edge cases. |
Rules rely on AI self-discipline. Hooks don't. They are scripts that run automatically before and after AI actions.
| Hook | When | What It Does |
|---|---|---|
pre-bash-guard.sh |
Before any Bash command | Blocks rm -rf, git reset --hard, DROP TABLE, and other destructive commands |
post-edit-check.sh |
After any Write/Edit | Reminds AI to run ripple-check before saying "done" |
post-deploy-health.sh |
After deploy commands | Reminds AI to verify containers, endpoints, and logs |
The AI cannot skip these. That's the point.
YES.md identifies 7 specific AI avoidance behaviors and forces self-correction — without waiting for the user to notice:
Deflecting to user → Do it yourself first
Unverified blame → Run the command, then speak
Spinning in circles → Full stop, fundamentally different approach
Surface-only fix → Ripple Check
Empty questions → Investigate first, then ask
Advice without action → Ship code, not suggestions
Tool neglect → Use the tool, not your memory
| Failures | Action |
|---|---|
| 2 | Switch: fundamentally different approach (not parameter tweaks) |
| 3 | Five-Step Audit: read error word-by-word → WebSearch → read 50 lines context → verify assumptions → invert hypothesis |
| 4 | Isolate: minimal reproduction |
| 5+ | Structured Handoff: verified facts, eliminated causes, narrowed scope, next steps |
Key difference from PUA: Level 3 forces a direction check BEFORE continuing. Persistence in the wrong direction is worse than stopping.
Before any root-cause claim, four mandatory questions:
- Data source? — log / DB / API / curl?
- Time range? — all data or just recent?
- Sample vs total? — how much did you see?
- Other possibilities? — what else could explain this?
Incomplete data = "
| Capability | YES.md | PUA |
|---|---|---|
| Debugging persistence | ✅ | ✅ |
| Debugging direction (accuracy) | ✅ | ❌ |
| Anti-slack behavior detection | ✅ | ✅ |
| Post-fix ripple check | ✅ | ⭕️ |
| Safety gates (backup, deploy) | ✅ | ❌ |
| Evidence-based diagnosis | ✅ | ❌ |
| Conclusion integrity checks | ✅ | ❌ |
| Bug closure protocol | ✅ | ❌ |
✅ = yes | ⭕️ = partial | ❌ = no
They complement each other. PUA keeps AI going. YES.md keeps AI correct. Use both for maximum effect.
# Marketplace
claude plugin marketplace add sstklen/yes.md
claude plugin install yes@sstklen
# Manual
git clone https://github.com/sstklen/yes.md.git ~/.claude/plugins/yesmkdir -p ~/.codex/skills/yes
curl -o ~/.codex/skills/yes/SKILL.md \
https://raw.githubusercontent.com/sstklen/yes.md/main/skills/yes/SKILL.mdmkdir -p .agents/skills/yes
curl -o .agents/skills/yes/SKILL.md \
https://raw.githubusercontent.com/sstklen/yes.md/main/skills/yes/SKILL.md| Language | Skill Directory | Command |
|---|---|---|
| English | skills/yes/ |
Default |
| 中文 | skills/yes-zh/ |
Replace yes with yes-zh in commands above |
| 日本語 | skills/yes-ja/ |
Replace yes with yes-ja in commands above |
Activates when AI:
- Guesses without evidence ("probably", "might be", "should be")
- Deflects to user ("please check...", "you should manually...")
- Fails 2+ times on the same task
- Makes a root-cause claim
- Completes a fix (triggers Ripple Check)
- Modifies config/env/deployment files (triggers Safety Gates)
Type /yes in any conversation.
- 5x-cto (
sstklen/5x-cto) — Full dev pipeline (requirements → spec → cards → build → review). YES.md governs, 5x-cto orchestrates. Together = safe + structured end-to-end. - PUA (
tanweai/pua) — PUA adds persistence pressure, YES.md adds accuracy structure - systematic-debugging — Method-level debugging, YES.md adds governance layer
Battle-tested over months of real production work — daily deployments, multi-service debugging, and hard lessons learned from things going wrong. Every rule in YES.md exists because something broke without it.
MIT
By sstklen — PUA says NO. YES says YES.