Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

andrej-karpathy-skills

OpenClaw skill distilled from Andrej Karpathy-inspired coding guidelines. Encourages explicit assumptions, simplicity, surgical edits, and goal-driven execution.

Executar no Manus

Visão geral

OpenClaw skill distilled from Andrej Karpathy-inspired coding guidelines. Encourages explicit assumptions, simplicity, surgical edits, and goal-driven execution.

Comando de instalação

npx skills add https://github.com/dfpalhano/openclaw-workspace --skill andrej-karpathy-skills

Copie e cole este comando no Claude Code para instalar a skill

Fonte

dfpalhano/openclaw-workspace

Estrelas0

Forks0

Atualizado16 de abril de 2026 às 14:12

Explorador de arquivos

2 arquivos

SKILL.md

readonly

name	andrej-karpathy-skills
version	1.0.0
description	OpenClaw skill distilled from Andrej Karpathy-inspired coding guidelines. Encourages explicit assumptions, simplicity, surgical edits, and goal-driven execution.
author	forrestchang
repository	https://github.com/forrestchang/andrej-karpathy-skills

Andrej Karpathy Skills

Use these guidelines when coding in OpenClaw:

Think before coding, state assumptions, surface ambiguity
Keep it simple, avoid speculative abstractions
Make surgical changes only
Work toward explicit, verifiable success criteria

Practical rules

Ask when the task is unclear
Prefer the smallest change that solves the problem
Do not refactor unrelated code
Verify results before declaring success

Mais deste repositório

mesmo repositório

capability-evolver

dfpalhano/openclaw-workspace

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.

2026-04-080

capability-evolver

dfpalhano/openclaw-workspace

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.

2026-04-080

clawrouter

dfpalhano/openclaw-workspace

Smart LLM router — save 67% on inference costs. Routes every request to the cheapest capable model across 41 models from OpenAI, Anthropic, Google, DeepSeek, and xAI.

2026-04-060

cc-godmode

dfpalhano/openclaw-workspace

Self-orchestrating multi-agent development workflows. You say WHAT, the AI decides HOW.

2026-04-060

god-mode

dfpalhano/openclaw-workspace

Developer oversight and AI agent coaching. Use when viewing project status across repos, syncing GitHub data, or analyzing agents.md against commit patterns.

2026-04-060

obsidian

dfpalhano/openclaw-workspace

Work with Obsidian vaults as a knowledge base. Features: fuzzy/phonetic search across all notes, auto-folder detection for new notes, create/read/edit notes with frontmatter, manage tags and wikilinks. Use when: querying knowledge base, saving notes/documents, editing existing notes by user instructions.

2026-04-060

Fonte

dfpalhano

dfpalhano/openclaw-workspace

Abrir repositório GitHub Ver repositórios do creator

Comando de instalação

Download

Executar no Manus

Útil paraSOC

Desenvolvedores de softwareInformática e Matemática15-1252L4

name	andrej-karpathy-skills
version	1.0.0
description	OpenClaw skill distilled from Andrej Karpathy-inspired coding guidelines. Encourages explicit assumptions, simplicity, surgical edits, and goal-driven execution.
author	forrestchang
repository	https://github.com/forrestchang/andrej-karpathy-skills

Andrej Karpathy Skills

Use these guidelines when coding in OpenClaw:

Think before coding, state assumptions, surface ambiguity
Keep it simple, avoid speculative abstractions
Make surgical changes only
Work toward explicit, verifiable success criteria

Practical rules

Ask when the task is unclear
Prefer the smallest change that solves the problem
Do not refactor unrelated code
Verify results before declaring success