AI Business Skills
tmusser/ai-business-skills
Transforma threads confusas em asks, decisões e follow-ups claros
Ver no GitHubConjunto 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-skills1 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
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 context | Clean output |
|---|---|
| A workplace thread with disagreement, legal uncertainty, support readiness risk, a soft deadline, and no named decision owner | Clean 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
| Input | State extracted | Output |
|---|---|---|
| Slack thread, email chain, meeting transcript, doc comment, or Jira/Confluence discussion | What changed, clean ask, decision, owner, deadline, blocker, source confidence, and tone risk | Reply draft, follow-up, status update, decision snapshot, or action list |
Workflows
| Workflow | User question | Skill |
|---|---|---|
| Catch up | What did I miss? | brief-me |
| Clarify | What are they actually asking? | clear-ask |
| Extract actions | What are the actions and open loops? | meeting-to-actions |
| Decide | What decision is needed? | decision-brief |
| Respond | What should I say back? | follow-up-draft |
| Broadcast | What 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.
| Mode | You control |
|---|---|
| Pasted-only mode | Use only text you pasted |
| Connected-context mode | Read approved tools like Gmail, Slack, Calendar, Docs, Jira, or Confluence |
| Draft-only mode | Produce messages, updates, or follow-ups without sending or publishing |
| Action mode | Mutate 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
- Messy thread to follow-up
- Gmail buried obligation
- Leadership status update
- Post-meeting follow-up
- Morning brief
- Decision with data
- Async Slack clear ask
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.