Prompts de voz gratuitos · Claude

Prompts úteis para Claude, prontos para a sua voz.

Comece com uma estrutura testada, dite os detalhes do seu jeito e entregue ao Claude uma tarefa com contexto, limites e resultado claro.

Claude · message composer

Feito para message composer

Abra message composer, diga o gatilho e continue descrevendo a tarefa. O Clavio organiza a fala na estrutura escolhida e insere tudo no Claude.

A decisão final continua sua

A voz acelera um briefing longo. Revise caminhos, negações, comandos, deploys e ações destrutivas antes de enviar.

01 · Claude

Oito modelos para trabalho real no Claude

Cada modelo resolve uma tarefa recorrente. É específico o bastante para revisar e flexível para o seu repositório, produto e restrições.

Depurar

Corrigir um bug

01

Corrigir um bug · Claude

Diga start debug brief
Target application: Claude
Target input: message composer

Task: Fix the bug described in my dictation.

Problem:
- Summarize the observed behavior precisely.

Expected behavior:
- State what should happen instead.

Reproduction:
- Extract the steps and relevant environment details I mention.

Constraints:
- Preserve existing behavior outside the fix.
- Do not invent missing requirements.

Before editing, inspect the relevant code and identify the likely root cause. Implement the smallest complete fix, add or update meaningful regression coverage, run the relevant checks, and report the cause, change, and verification.

Application-specific guidance:
- Give Claude the observed behavior, relevant code and reproduction conditions; require assumptions to stay explicit.
Criar

Criar um recurso

02

Criar um recurso · Claude

Diga start feature brief
Target application: Claude
Target input: message composer

Goal:
- Turn my description into one clear product outcome.

User flow:
- Capture the trigger, expected behavior, empty/loading/error states, and completion state.

Constraints:
- Preserve the current design system and established architecture.
- Reuse existing components and services where appropriate.
- Do not invent scope I did not request.

Inspect the current implementation first. Then implement the complete user-facing flow, verify it with the most relevant checks, and explain any material tradeoffs.

Application-specific guidance:
- Describe the user outcome, states and boundaries before asking Claude to draft an implementation.
Melhorar

Refatorar com segurança

03

Refatorar com segurança · Claude

Diga start refactor brief
Target application: Claude
Target input: message composer

Refactor target:
- Identify the code and problem described in my dictation.

Invariants:
- Preserve observable behavior, public interfaces, analytics names, and persisted data unless I explicitly request a change.

Desired result:
- State the simpler structure or responsibility boundary I want.

Inspect callers and tests before editing. Make the refactor in reviewable steps, remove obsolete code, run focused regression checks, and call out any behavior that could not be proven equivalent.

Application-specific guidance:
- State invariants and affected interfaces, then check the proposal against callers Claude has not been shown.
Criar

Escrever testes úteis

04

Escrever testes úteis · Claude

Diga start test brief
Target application: Claude
Target input: message composer

Behavior under test:
- Extract the contract and failure modes from my dictation.

Test cases:
- Cover the main success path, the stated edge cases, and the regression that motivated this task.

Requirements:
- Test observable behavior rather than implementation details.
- Reuse the repository's existing test style and fixtures.
- Avoid tests that merely repeat the production code.

Inspect the implementation and nearby tests, add the smallest meaningful test set, run it, and report what the tests prove.

Application-specific guidance:
- Provide the contract and nearby test examples so the result follows the repository's conventions.
Revisar

Revisar alterações no código

05

Revisar alterações no código · Claude

Diga start code review
Target application: Claude
Target input: message composer

Review the changes I describe or provide.

Focus on:
- User-visible regressions and incorrect behavior.
- Data loss, security, privacy, concurrency, and migration risks.
- Missing validation for behavior that materially changed.

Check the surrounding code and established project conventions before judging the diff. Report only actionable findings, ordered by severity, with a concrete trigger and consequence for each. If there are no findings, say so and state the remaining verification limits.

Application-specific guidance:
- Share the actual diff with surrounding context and ask for actionable findings ordered by consequence.
Depurar

Investigar desempenho

06

Investigar desempenho · Claude

Diga start performance investigation
Target application: Claude
Target input: message composer

Performance problem:
- Capture where the slowdown occurs, how often, and what the user experiences.

Evidence:
- Record the measurements, logs, device details, and reproduction conditions I mention.

Investigate before optimizing. Identify the dominant cost, distinguish measured facts from hypotheses, and avoid broad rewrites. Implement the highest-impact safe improvement, compare before and after with the same workload, and report the measured result and remaining bottlenecks.

Application-specific guidance:
- Provide repeatable measurements and keep hypotheses distinct from verified bottlenecks.
Criar

Planejar uma implementação

07

Planejar uma implementação · Claude

Diga start implementation plan
Target application: Claude
Target input: message composer

Objective:
- Restate the outcome from my dictation.

Current context:
- Capture the relevant system, constraints, and decisions already made.

Produce a concrete implementation plan based on the actual codebase. Name the components that need to change, dependencies between steps, migration or rollout concerns, and the checks that prove completion. Resolve routine choices from repository evidence and list only uncertainties that truly block execution.

Application-specific guidance:
- Include architecture and constraints, then ask Claude for ordered steps with validation and rollout concerns.
Melhorar

Refinar uma interface

08

Refinar uma interface · Claude

Diga start interface polish
Target application: Claude
Target input: message composer

Screen or flow:
- Identify the interface and user goal from my dictation.

Problems noticed:
- Capture the visual, interaction, responsive, and accessibility issues I mention.

Preserve the product's existing visual language. Inspect the screen at its real desktop and mobile sizes, fix hierarchy, spacing, typography, states, and interaction details, then compare the result in the running product. Avoid decorative changes that do not improve comprehension or use.

Application-specific guidance:
- Provide the current UI and design rules, then validate the recommendation in the running product.

Modelo pronto para o agente · EN · Claude

02

Prompts para outros apps

CursorAgentClaude Codeterminal promptCodextask composerWindsurfCascadeGitHub CopilotCopilot ChatChatGPTmessage composerGeminiprompt boxReplit AgentAgent chatLovablechat composer

Como usar modelos com Claude

Preciso do Clavio para usar os modelos?

Não. Todos podem ser copiados. O Clavio acrescenta o fluxo sem as mãos: instale uma vez, diga o gatilho e dite os detalhes.

Posso falar no meu idioma?

Sim. Fale no idioma que você usa. O modelo preserva a estrutura e seus detalhes definem o idioma de trabalho e o contexto.

O Clavio envia o prompt automaticamente?

Somente se você ativar essa ação para o app. Mantenha a revisão manual para código, comandos, deploys, permissões e exclusões.