Pular para o conteúdo
TakoAPI
Voltar às skills

moltbot-best-practices

por nextfrontierbuilds

Moltbook
3.9kDownloads informados pelo clawskills.sh
20Estrelas
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

Best practices for AI agents.

Descrição

O que esta skill faz

A set of behavioral rules for AI coding agents derived from documented real-world failures. Covers confirmation loops, draft-before-publish flows, failure escalation, and stop-signal handling. Applies to agents running in Cursor, Claude Code, ChatGPT, and GitHub Copilot.

Instead of generic prompt-engineering advice, these rules map directly to failure modes observed in live agent sessions, making them easier to apply and validate.

Quando usá-la

  • Preventing an agent from publishing a social post without showing a draft first
  • Stopping an agent from retrying broken browser automation indefinitely
  • Getting an agent to ask whether a task should run in background or foreground
  • Enforcing that an agent reads all queued user messages before acting
  • Configuring session memory so an agent retains context across compaction

Exemplo de fluxo de trabalho

ENTRADA

User asks: Write a long form post about our product launch and publish it

AGENTE
  1. 1

    Reads all queued messages before acting to check for corrections or cancellations

  2. 2

    Asks clarifying question: 'Long form post — do you mean an X Article or a thread?'

  3. 3

    Confirms scope: 'You want an X Article about the product launch. I'll draft it and show you before posting. Correct?'

  4. 4

    Drafts the content and presents it to the user for review

  5. 5

    Waits for explicit approval before taking any publish action

SAÍDA

Draft delivered to user for review; no publish action taken until user confirms

Instalação

clawhub install nextfrontierbuilds/moltbot-best-practices

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links