Add karpathy-guidelines skill 🤖🤖🤖

docs/README.skills.md

@@ -207,6 +207,7 @@ See [CONTRIBUTING.md](../CONTRIBUTING.md#adding-skills) for guidelines on how to
 | [java-springboot](../skills/java-springboot/SKILL.md)<br />`gh skills install github/awesome-copilot java-springboot` | Get best practices for developing applications with Spring Boot. | None |
 | [javascript-typescript-jest](../skills/javascript-typescript-jest/SKILL.md)<br />`gh skills install github/awesome-copilot javascript-typescript-jest` | Best practices for writing JavaScript/TypeScript tests using Jest, including mocking strategies, test structure, and common patterns. | None |
 | [javax-to-jakarta-migration](../skills/javax-to-jakarta-migration/SKILL.md)<br />`gh skills install github/awesome-copilot javax-to-jakarta-migration` | Migrate Java code from javax.* to jakarta.* namespace. Use when upgrading to Tomcat 11, Jakarta EE 10, or when javax imports are detected in the codebase. | None |
+| [karpathy-guidelines](../skills/karpathy-guidelines/SKILL.md)<br />`gh skills install github/awesome-copilot karpathy-guidelines` | Behavioral coding-agent guidelines that reduce common LLM coding mistakes by favoring simple, surgical, assumption-aware, and verifiable changes. | None |
 | [kotlin-mcp-server-generator](../skills/kotlin-mcp-server-generator/SKILL.md)<br />`gh skills install github/awesome-copilot kotlin-mcp-server-generator` | Generate a complete Kotlin MCP server project with proper structure, dependencies, and implementation using the official io.modelcontextprotocol:kotlin-sdk library. | None |
 | [kotlin-springboot](../skills/kotlin-springboot/SKILL.md)<br />`gh skills install github/awesome-copilot kotlin-springboot` | Get best practices for developing applications with Spring Boot and Kotlin. | None |
 | [legacy-circuit-mockups](../skills/legacy-circuit-mockups/SKILL.md)<br />`gh skills install github/awesome-copilot legacy-circuit-mockups` | Generate breadboard circuit mockups and visual diagrams using HTML5 Canvas drawing techniques. Use when asked to create circuit layouts, visualize electronic component placements, draw breadboard diagrams, mockup 6502 builds, generate retro computer schematics, or design vintage electronics projects. Supports 555 timers, W65C02S microprocessors, 28C256 EEPROMs, W65C22 VIA chips, 7400-series logic gates, LEDs, resistors, capacitors, switches, buttons, crystals, and wires. | `references/28256-eeprom.md`<br />`references/555.md`<br />`references/6502.md`<br />`references/6522.md`<br />`references/6C62256.md`<br />`references/7400-series.md`<br />`references/assembly-compiler.md`<br />`references/assembly-language.md`<br />`references/basic-electronic-components.md`<br />`references/breadboard.md`<br />`references/common-breadboard-components.md`<br />`references/connecting-electronic-components.md`<br />`references/emulator-28256-eeprom.md`<br />`references/emulator-6502.md`<br />`references/emulator-6522.md`<br />`references/emulator-6C62256.md`<br />`references/emulator-lcd.md`<br />`references/lcd.md`<br />`references/minipro.md`<br />`references/t48eeprom-programmer.md` |

skills/karpathy-guidelines/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: karpathy-guidelines
+description: Behavioral coding-agent guidelines that reduce common LLM coding mistakes by favoring simple, surgical, assumption-aware, and verifiable changes.
+license: MIT
+compatibility: Works with GitHub Copilot agent skills and other SKILL.md-compatible coding agents. No external dependencies.
+metadata:
+  author: SwarmClaw AI
+  source: https://github.com/swarmclawai/andrej-karpathy-skills
+  inspired-by: https://x.com/karpathy/status/2015883857489522876
+---
+
+# Karpathy Guidelines
+
+Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.
+
+Use this skill when writing, reviewing, or refactoring code and the main risk is overcomplication, hidden assumptions, broad edits, or weak verification.
+
+## Agent Behavior Rules
+
+1. **Think before coding.** State assumptions explicitly, surface tradeoffs, and ask when the request has multiple plausible interpretations.
+2. **Prefer simple implementations.** Do the minimum needed to solve the user request. Avoid speculative abstraction, configurability, and features that were not asked for.
+3. **Make surgical changes.** Touch only the files and lines required for the task. Match the surrounding style and avoid unrelated cleanup.
+4. **Define success criteria.** Convert vague work into verifiable outcomes before editing. For bugs, reproduce the failure first when practical.
+5. **Verify the result.** Run the smallest meaningful checks that cover the requested behavior. Report any checks that could not be run.
+
+## Before Editing
+
+- Identify the concrete user goal.
+- Name any assumptions that affect implementation.
+- Check the existing code shape before introducing new patterns.
+- Prefer local helpers, local conventions, and established tests over new infrastructure.
+
+## While Editing
+
+- Keep every changed line traceable to the goal.
+- Remove imports, variables, or functions that your change made unused.
+- Do not delete pre-existing dead code unless the user asked for cleanup.
+- If an implementation starts growing unexpectedly, pause and simplify.
+
+## Verification Pattern
+
+For multi-step work, use a short plan with checks:
+
+```text
+1. Implement the smallest change that addresses the goal.
+2. Run the focused test, build, or static check that exercises the changed behavior.
+3. Inspect the diff for unrelated churn.
+4. Report what changed and what was verified.
+```
+
+Strong success criteria let agents continue independently. Weak success criteria, such as "make it work", require clarification.