What is preparar-conversa?

A preparation guide for important workplace conversations, such as one-to-ones and discussions with colleagues or stakeholders. It uses existing notes and recent signals to create a conversation agenda.

Use it to prepare one-to-ones, stakeholder meetings, alignment discussions, and other conversations where you need questions and follow-ups ready.

It helps turn scattered notes, past follow-ups, and recent events into a focused agenda. This reduces the risk of entering a conversation without the relevant context.

preparar-conversa — Skill for Claude Code by pe-menezes

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add pe-menezes/pm-chief-of-staff --skill preparar-conversa

Clone the repo

git clone --depth 1 https://github.com/pe-menezes/pm-chief-of-staff

Made for: Claude Code.

Or install pm-chief-of-staff, the plugin that ships this one along with the rest of its 10 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/preparar-conversa/github.svg)](https://agentmods.dev/skills/pe-menezes/pm-chief-of-staff/preparar-conversa)

Your own site

<a href="https://agentmods.dev/skills/pe-menezes/pm-chief-of-staff/preparar-conversa"><img src="https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/preparar-conversa/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pe-menezes/pm-chief-of-staff/preparar-conversa"><img src="https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/preparar-conversa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 983 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00106	$0.00983
Opus 5	$0.00053	$0.00491
Sonnet 5	$0.00021	$0.00197
Haiku 4.5	$0.00011	$0.00098

Measured 12d ago against content hash e93870d32a1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

preparar-conversa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

seeds/preparar-conversa/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preparar uma conversa

Semente do pm-chief-of-staff. Este arquivo é SEU: peça pro agente mudar o formato da pauta ("quero que sempre tenha uma seção de X") e ele edita esta skill na hora.

Escrita: siga o cânone do CLAUDE.md desta pasta. Na ausência dele: sem travessão (use vírgula, parênteses ou dois pontos), frases curtas e densas, 1 linha por item.

Pauta boa nasce do que já está escrito, não da memória. O fluxo: levantar candidatos → validar com a pessoa → escrever a pauta só com o validado.

Passo 1: levantar candidatos

Ler o hub da pessoa em pessoas/, começando pela cabeça: a seção Fatos (datados, com fonte) e a Leitura vigente (a mais recente, sem marca de superada) são a base da preparação; leitura marcada como superada é ignorada. Sinais recentes e Histórico entram como complemento.
Ler as 2 a 3 últimas notas de conversa com ela em reunioes/: o que ficou de follow-up (dos dois lados), o que foi combinado "pra próxima".
Grep do nome no diário e no memory/ das últimas 2 semanas: o que apareceu sobre ela ou sobre os temas dela.
Todo item da seção "Sinais recentes" do hub é candidato. Sinal parado há mais de 3 semanas entra com a pergunta: cobra de novo ou caiu?
Se existir .claude/skills/_shared/capacidades.md com provider e como chamar em mensagens ou tickets, puxar por ali o que apareceu nas últimas 2 semanas sobre a pessoa e os temas dela (a mesma janela do item 3), como candidato igual aos outros. Sem o módulo, com a linha vazia ou pela metade, ou se a busca falhar, o passo 1 fica nos arquivos, que é o default.

Passo 2: validar com a pessoa

Apresentar os candidatos numerados, agrupados (follow-ups abertos / sinais / tópicos novos), e perguntar o que entra: levar / hoje não / descartar / editar. Não censurar candidato por conta própria; a pessoa decide.

Passo 3: escrever a pauta

Arquivo em reunioes/{nome}/YYYY-MM-DD pauta.md, mira de 15 linhas no máximo, tom factual. Seção sem conteúdo é omitida.

**Contexto:** {1 linha: momento da pessoa + o que está quente}

Abrir ouvindo: "o que você me traz?"

## Follow-ups abertos
- {item + prazo + pergunta, 1 linha cada; pendência SUA que impacta a pessoa entra com transparência}

## Decisões a tomar
- {1 linha por decisão que precisa sair da conversa}

## Tópicos
- {o que entrar do passo 2}

Read the full file on GitHub · 54 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 54 lines · 106 tokens per session scan A e93870d32a1b

Subscribe to this mod's changes

preparar-conversa is a skill published in the GitHub repository pe-menezes/pm-chief-of-staff (2 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 983 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Planning Productivity chief-of-staff claude-code-plugin product-management second-brain

Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".

agenticnotetaking/arscontexta · 50 tokens

preparar-conversa

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Preparar uma conversa

Passo 1: levantar candidatos

Passo 2: validar com a pessoa

Passo 3: escrever a pauta

What this file has done since we first saw it

Other skills, from other repositories

next

create-slide-deck

pm-setup

opportunity-assessment

competitive-intel

experiment-review