feat(skills): add Karpathy Guidelines to skill catalog (#70)

Add the "Karpathy Guidelines" skill from multica-ai/andrej-karpathy-skills
(MIT licensed) to the built-in skill catalog. The skill provides behavioral
guidelines for LLM coding: think before coding, simplicity first, surgical
changes, and goal-driven execution.

Co-authored-by: 你的姓名 <you@example.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

src/skills/skillCatalog.ts

@@ -181,6 +181,78 @@ Provide:
 4. Remaining blockers and next recommended CLI command.
 `
 
+const KARPATHY_GUIDELINES_SKILL = `---
+name: karpathy-guidelines
+description: Behavioral guidelines to reduce common LLM coding mistakes. Use when you want disciplined, minimal, goal-driven code changes with explicit tradeoff reasoning.
+---
+
+# Karpathy Guidelines
+
+Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
+
+**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+## 1. Think Before Coding
+
+**Don't assume. Don't hide confusion. Surface tradeoffs.**
+
+Before implementing:
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them — don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, stop. Name what's confusing. Ask.
+
+## 2. Simplicity First
+
+**Minimum code that solves the problem. Nothing speculative.**
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite it.
+
+Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
+
+## 3. Surgical Changes
+
+**Touch only what you must. Clean up only your own mess.**
+
+When editing existing code:
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, mention it — don't delete it.
+
+When your changes create orphans:
+- Remove imports/variables/functions that YOUR changes made unused.
+- Don't remove pre-existing dead code unless asked.
+
+The test: Every changed line should trace directly to the user's request.
+
+## 4. Goal-Driven Execution
+
+**Define success criteria. Loop until verified.**
+
+Transform tasks into verifiable goals:
+- "Add validation" → "Write tests for invalid inputs, then make them pass"
+- "Fix the bug" → "Write a test that reproduces it, then make it pass"
+- "Refactor X" → "Ensure tests pass before and after"
+
+For multi-step tasks, state a brief plan:
+\`\`\`
+1. [Step] → verify: [check]
+2. [Step] → verify: [check]
+3. [Step] → verify: [check]
+\`\`\`
+
+Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
+
+---
+
+**These guidelines are working if:** fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.
+`
+
 import { SUPABASE_REFERENCE_FILES } from './supabaseReferences.js'
 import {
   REACT_BEST_PRACTICES_SKILL,
@@ -269,6 +341,15 @@ export const SKILL_CATALOG: CatalogSkill[] = [
     source: UPSTREAM,
     files: { 'SKILL.md': TEMPORAL_DEVELOPER_SKILL },
   },
+  {
+    name: 'karpathy-guidelines',
+    displayName: 'Karpathy Guidelines',
+    description:
+      'Behavioral guidelines to reduce common LLM coding mistakes: think before coding, simplicity first, surgical changes, goal-driven execution.',
+    category: 'Workflow',
+    source: 'multica-ai/andrej-karpathy-skills (MIT) — https://github.com/multica-ai/andrej-karpathy-skills',
+    files: { 'SKILL.md': KARPATHY_GUIDELINES_SKILL },
+  },
 ]
 
 /** Look up a catalog entry by its install name. */