Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

doncheli-voice

Estrelas56

Forks10

Atualizado1 de abril de 2026 às 17:09

Convert voice dictation into structured specs, review comments, or brainstorming notes. Activate when user mentions "voice", "dictate", "speak", "voice mode", "I'll dictate", "voice input".

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

doncheli

doncheli/don-cheli-sdd

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

SKILL.md

readonly

name	doncheli-voice
description	Convert voice dictation into structured specs, review comments, or brainstorming notes. Activate when user mentions "voice", "dictate", "speak", "voice mode", "I'll dictate", "voice input".

Don Cheli: Voice Mode Integration

Instructions

Prompt the user to activate Claude Code Voice Mode if not already active
Accept transcribed voice input as raw text
Detect the intended mode from context or user flag:
- spec — convert to Gherkin Feature/Scenario format
- review — convert to numbered review comments with severity
- brainstorm — organize ideas into grouped bullet points
Clean the transcription: remove filler words, fix punctuation, resolve run-on sentences
Structure the output according to the detected mode
Mark genuinely ambiguous segments with [unclear: original text] — do not invent content
Present the structured output and ask for confirmation before saving
On confirmation, save to the appropriate location:
- spec → .dc/specs/<feature>.feature
- review → .dc/reviews/<date>-review.md
- brainstorm → .dc/notas/<date>-brainstorm.md
Suggest relevant follow-up commands: /dc:validar-spec, /dc:debate, /dc:clarificar

Quality Gate

Never save without user confirmation
If the transcription is shorter than 3 meaningful sentences, ask if the user wants to continue dictating
Preserve technical terms exactly as dictated — do not paraphrase class names, endpoints, or identifiers

Mais deste repositório

mesmo repositório

doncheli-prd

doncheli/don-cheli-sdd

Generate professional Product Requirement Documents (PRD) from multiple sources — Figma designs, briefs, user research, existing code. Includes risk analysis, RICE prioritization, Gherkin stories and launch plan. Activate when user mentions "PRD", "product requirements", "requirement document", "product spec", "figma to PRD", "generate PRD".

2026-04-0756

doncheli-audit-trail

doncheli/don-cheli-sdd

Record and query the decision log for a project. Activate when user mentions "audit", "trail", "log decisions", "decision history", "why was this decided", "ADR", "architecture decision".

2026-04-0156

doncheli-data-policy

doncheli/don-cheli-sdd

Audit and document what personal or sensitive data the project collects, processes, and stores. Activate when user mentions "privacy", "data policy", "what data", "GDPR", "personal data", "data retention", "PII".

2026-04-0156

doncheli-drift

doncheli/don-cheli-sdd

Detect and reconcile divergence between specs and implementation. Activate when user mentions "drift", "sync", "spec divergence", "out of sync", "spec doesn't match", "implementation differs".

2026-04-0156

doncheli-estimate

doncheli/don-cheli-sdd

Estimate effort, duration and cost using 4 complementary models (Function Points, Planning Poker AI, COCOMO, Historical). Activate when user mentions "estimate", "estimation", "effort", "how long", "cost", "story points", "sizing".

2026-04-0156

doncheli-spec-score

doncheli/don-cheli-sdd

Evaluate the quality of a spec and return a structured score with improvement recommendations. Activate when user mentions "spec quality", "score spec", "how good is my spec", "spec review", "validate spec quality".

2026-04-0156

name	doncheli-voice
description	Convert voice dictation into structured specs, review comments, or brainstorming notes. Activate when user mentions "voice", "dictate", "speak", "voice mode", "I'll dictate", "voice input".

Don Cheli: Voice Mode Integration

Instructions

Prompt the user to activate Claude Code Voice Mode if not already active
Accept transcribed voice input as raw text
Detect the intended mode from context or user flag:
- spec — convert to Gherkin Feature/Scenario format
- review — convert to numbered review comments with severity
- brainstorm — organize ideas into grouped bullet points
Clean the transcription: remove filler words, fix punctuation, resolve run-on sentences
Structure the output according to the detected mode
Mark genuinely ambiguous segments with [unclear: original text] — do not invent content
Present the structured output and ask for confirmation before saving
On confirmation, save to the appropriate location:
- spec → .dc/specs/<feature>.feature
- review → .dc/reviews/<date>-review.md
- brainstorm → .dc/notas/<date>-brainstorm.md
Suggest relevant follow-up commands: /dc:validar-spec, /dc:debate, /dc:clarificar

Quality Gate

Never save without user confirmation
If the transcription is shorter than 3 meaningful sentences, ask if the user wants to continue dictating
Preserve technical terms exactly as dictated — do not paraphrase class names, endpoints, or identifiers