convez.ai
SkillProdutividadeIniciante
tmusser

AI Business Skills

tmusser/ai-business-skills

Transforma threads confusas em asks, decisões e follow-ups claros

Ver no GitHub
InicialPluginScore · de 0 a 100

Conjunto de skills Claude para transformar contexto empresarial confuso em demandas claras, decisões, proprietários e próximas ações. Funciona com threads do Slack, correntes de email, transcrições de reuniões e discussões de projeto — paste e obtenha estrutura sem pretender que incertezas foram resolvidas.

Instalação

$npx convez-ai tmusser/ai-business-skills

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
3
Forks
1
Acompanhando
0
Saúde
42%
Último commit
há 2 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Sintetizar threads Slack com desacordo ou bloqueios de decisão
  • Estruturar reuniões e transcrições em ações nomeadas
  • Esclarecer demandas vagas e identificar gaps de proprietário
  • Rascunhar respostas contextuais e brief para stakeholders

Veredito

Skill direto e pragmático que resolve um problema real em fluxos de trabalho colaborativos: traduzir contexto messy em estrutura executável sem fake certainty. Baixa fricção (copy/paste), foco em factualidade e abertura de loops.

README

A tradução para o português deste README ainda está na fila.

ai-business-skills

Paste a messy thread or notes; get the clean ask, decision, owner, risk, and reply.

Use it when a Slack thread, email chain, meeting transcript, doc comment, Jira discussion, or project conversation contains signal, but not yet a clean ask, decision, owner, update, or follow-up.

What it does in 30 seconds

Messy contextClean output
A workplace thread with disagreement, legal uncertainty, support readiness risk, a soft deadline, and no named decision ownerClean ask, decision needed, owner gap, risk/tone note, and a reply draft you can paste

The promise is small: turn messy business context into the next clear move without pretending uncertainty is resolved.

Use It When...

  • A Slack thread, email chain, or meeting transcript needs a fast catch-up
  • Someone asked a vague question and you need to clarify the ask
  • A conversation has decisions, owners, deadlines, blockers, or open loops
  • You need to draft the next context-aware reply
  • You need to brief other people on what changed

Try This First

Paste messy notes, a transcript, or connected context into Claude/Cowork and ask:

Use brief-me. Catch me up on what changed, what needs my response, risks/blockers, and suggested follow-ups.

Tiny example:

Messy input:
Alex: "Can we still send the customer note today?"
Sam: "I'd rather not wait; support can catch up after."
Priya: "Support needs the enterprise wording before anything goes out."
Jordan: "Legal has not approved the banner copy yet."
Alex: "The send queue closes at 3pm. Who owns the call?"

Clean output:
Clean ask: decide whether to send today or wait for legal/support readiness.
Decision needed: send today vs. move to tomorrow.
Owner gap: no final decision owner is named.
Suggested reply: "Can we name the decision owner and confirm by 3pm whether legal/support readiness blocks today's send?"
Full version: [examples/messy-thread-to-follow-up.md](examples/messy-thread-to-follow-up.md)

Shareable one-pager: docs/one-pager.md

Works with pasted context

These are plain-text skills, so the lowest-friction mode is copy/paste: paste the thread, note, email, transcript, or doc excerpt into your AI tool and ask for the skill by name.

The tested path is Claude/Cowork-style skills. The underlying SKILL.md files can also be adapted as reusable prompts for ChatGPT, Gemini, Codex-style agents, or internal AI assistants. No connector is required for pasted-context mode.

Use these skills

No coding is required.

Each skill lives in skills/ as a folder with a SKILL.md file.

Copy the skill folders into the skills directory used by your AI tool, then paste context and ask for a skill by name. For example:

Use brief-me on this thread and tell me what needs my response.

These skills read and draft by default. They do not send, publish, create events, or update systems unless you explicitly ask.

Privacy and control

  • pasted-only mode uses only pasted text
  • connected-context mode reads only approved tools
  • draft-only mode does not send or publish
  • action mode mutates systems only when explicitly asked
  • Tone safety: helps avoid accidental escalation, fake certainty, overcommitment, and misreading stakeholder sensitivity

What This Is

This repo is for the work before the work:

  • understand what people said
  • identify what changed
  • separate facts from assumptions
  • clarify the ask
  • preserve open loops
  • draft the next context-aware response

What This Is Not

This is not a deck generator, project-management framework, or heavy artifact factory.

How it works

InputState extractedOutput
Slack thread, email chain, meeting transcript, doc comment, or Jira/Confluence discussionWhat changed, clean ask, decision, owner, deadline, blocker, source confidence, and tone riskReply draft, follow-up, status update, decision snapshot, or action list

Workflows

WorkflowUser questionSkill
Catch upWhat did I miss?brief-me
ClarifyWhat are they actually asking?clear-ask
Extract actionsWhat are the actions and open loops?meeting-to-actions
DecideWhat decision is needed?decision-brief
RespondWhat should I say back?follow-up-draft
BroadcastWhat should others know?status-update

Meeting without a meeting

Many workplace meetings do not happen in Zoom.

A Slack thread, Gmail chain, Google Doc comment thread, Jira discussion, or Confluence page can contain the same things a live meeting does:

  • decisions
  • objections
  • owner changes
  • implied deadlines
  • unresolved questions
  • stakeholder sensitivities
  • political or contextual tone

These skills process async conversations the same way you would process a meeting: extract state, identify open loops, and draft the next context-aware response.

Operating Modes

Choose the mode that gives you the right control.

ModeYou control
Pasted-only modeUse only text you pasted
Connected-context modeRead approved tools like Gmail, Slack, Calendar, Docs, Jira, or Confluence
Draft-only modeProduce messages, updates, or follow-ups without sending or publishing
Action modeMutate systems only when you explicitly ask

Supported Context

Use pasted notes, Zoom transcripts, Slack, Gmail, Calendar, Atlassian, and Hex or other data outputs as inputs.

By default, these skills read and draft. They do not send messages, create events, update tickets, or publish outputs unless you explicitly ask.

Shared guidance for mixed-source inputs lives in source-packet.md.

Examples

Keep It Practical

Every skill is designed to produce something you can send, decide from, or act on within 5 minutes.

Helpful supporting files:

How This Repo Was Built

This repo was built using ai-engineering-skills as the control layer.

Part of the suite

This repo is one piece of a small set of repos for making AI-assisted work clearer, more bounded, and more verifiable. See Suite map.

Ver o original no GitHub

Bom para

Relacionados