Receber por email

Desenvolvimento

13.569 skills encontradas

Alerta por categoria

Receba novas skills de Desenvolvimento toda segunda

Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.

fresh-eyes-review

0

Use when about to commit, create a PR, or declare work complete — after verification-before-completion confirms tests pass but before code ships. Catches security vulnerabilities, logic errors, and business rule bugs that slip through despite passing tests.

Desenvolvimento #ai #test por michellepellon

reset

0

Soft-reset unpushed commits back into the working tree for re-committing

Desenvolvimento #git por AnotherSava

my-little-office-workers

0

Uma equipe de agentes de IA se torna sua funcionária, cuidando de planejamento, pesquisa, reuniões de equipe, tomada de decisões, produção de vídeos de relatórios e implementação de código. Você apenas senta e aprova como um chefe.

Desenvolvimento #ai por Museng17

ms-spec-update

0

Update the docs/architecture .md spec files after adding a new feature, without re-running the full ms-spec. Detects what changed via git diff, maps changes to the right spec sections, grills the developer for missing context, and patches only the affected .md files. Use when a feature is done and the user wants to keep AI agent context up to date, or says "update spec", "sync spec", "ms-spec-upda

Desenvolvimento #ai #git por lsscecilia

simplify

0

Use when a file or module has grown too complex — removes unnecessary abstractions, dead code, and over-engineering without changing behavior. Invoke after implementing a feature when the code feels over-engineered.

Desenvolvimento #ai #test por latuconsinafr

schema-guided-reasoning

0

Паттерн Schema-Guided Reasoning (SGR) для решения задач на базе LLM с использованием structured output, constrained decoding, Pydantic моделей. Используй когда нужно: структурированный вывод, JSON schema, воспроизводимость рассуждений, тестируемость промежуточных шагов, направленное рассуждение модели, response_format, parse().

Desenvolvimento #ai #llm por Bbar0n234

file-editor

0

Edição de arquivos segura e confiável com validação e depuração, ideal para código, configurações ou marcação (HTML, JSON, Python, JS). Previne erros comuns como nomes de parâmetros incorretos ou alterações não intencionais, incorporando validação, verificação de pesquisa e estratégias de reversão.

Desenvolvimento #python por Cat-tj

miki-review-loop

0

Miki's personal pre-self-review loop. Iteratively runs /review on the current PR and addresses obvious issues until only minor nits remain or 3 iterations have run. Surfaces judgment calls back to the user, makes atomic commits per project convention, pushes once at the end. Invoke when the user says "/miki-review-loop", "loop the review", "iterate on the review", or similar after a PR has been cr

Desenvolvimento #ai por mikiwiik

smart-git-sync

0

デフォルトブランチ(develop or main)にチェックアウトし、fetch/pull してマージ済みブランチを削除する。ユーザーが「同期して」「ブランチ整理」「/smart-git-sync」と言ったら起動する。

Desenvolvimento #ai #git por mjcreativelab

aerospace-macos-setup

0

Install, configure, and debug AeroSpace on macOS. Use when Codex needs to set up AeroSpace with Homebrew, create or repair ~/.aerospace.toml, configure window movement hotkeys for multi-monitor workflows, diagnose Accessibility or server/config problems, or automate binding tests with the AeroSpace CLI.

Desenvolvimento #ai #test por ArthurZakirov

acceptance-criteria

0

Write, review, or rewrite Acceptance Criteria for user stories. Use this skill whenever the user (or a subagent you spawn) is asked to draft, improve, refine, rewrite, or review acceptance criteria, turn a user story into AC, translate behavior specs into Given/When/Then, critique existing Gherkin scenarios, define the "definition of done" for a story, or expand on a story's expected behavior — ev

Desenvolvimento #git por Povaz

agent-lint

0

Lint a BDK agent file for best practices and portability. Use when reviewing, creating, or editing an agent (agents/*.md) to verify it meets BDK conventions. Trigger on phrases like "check this agent", "verify agent", "lint agent", or when about to commit a new agent.

Desenvolvimento por broneq