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.
git clone --depth 1 https://github.com/lucasgaravelli/pm-skills-claude-codeWrote 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.
[](https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/interview-synthesis)<a href="https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/interview-synthesis"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/interview-synthesis/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.
<a href="https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/interview-synthesis"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/interview-synthesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.02169 |
| Opus 5 | $0.00000 | $0.01085 |
| Sonnet 5 | $0.00000 | $0.00434 |
| Haiku 4.5 | $0.00000 | $0.00217 |
Grade A, and why
interview-synthesis 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 9d 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.
This is a copy
100% identical to interview-synthesis — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/interview-synthesis
O que essa skill faz
Sintetiza transcrições de entrevistas em JTBD, padrões comportamentais, problemas frequentes e recomendações acionáveis.
Saída: Síntese de entrevistas com insights estruturados para informar descoberta ou PRD.
Quando usar
- Rodou entrevistas e tem transcricao/notas
- Quer extrair padrões em vez de ler tudo manualmente
- Precisa priorizar problemas descobertos
- Vai referir insights em sync com stakeholders
Input esperado
Mínimo:
- Transcrições ou resumos de 3+ entrevistas
- Contexto: Quem foi entrevistado (persona, rol), qual era a pergunta principal
Opcional:
- Dados de sessão (tempo gasto, features usadas)
- Feedback NPS ou CSAT
- Context sobre competidores mencionados
Processo
- Extração de JTBD — Identifica jobs, pains, gains para cada entrevistado
- Padrões — Agrupa temas comuns em 3-5 clusters
- Problemas principais — Ranking por frequência e severidade
- Recomendações — Ações específicas (PRD, experimento, suporte)
- Evidência — Quotes diretos das entrevistas para validar
Output
# Síntese de Entrevistas: [Tema]
## Respondentes
- 5 clientes de [segmento], usando produto há [X meses]
- Contexto: Entrevistados sobre [pergunta principal]
## Jobs to Be Done (JTBD)
### JTBD 1: [Job principal]
- **Contexto**: Quando [situação]
- **Job**: Eu quero [ação]
- **Outcome esperado**: Para que [resultado]
- **Frequência**: [X/5 entrevistados mencionaram]
### JTBD 2: [Job secundário]
- **Contexto**: [...]
- **Job**: [...]
- **Outcome esperado**: [...]
- **Frequência**: [X/5]
## Padrões comportamentais
### Padrão 1: [Behavior] (4/5 entrevistados)
- Descrição: O que observamos
- Contexto: Quando acontece
- Impacto: Consequência para produto
- Quote: "Frase direto de entrevistado"
### Padrão 2: [Behavior] (3/5 entrevistados)
- Descrição: [...]
- Contexto: [...]
- Impacto: [...]
- Quote: [...]
## Problemas descobertos (ranking por severidade)
| Problema | Severidade | Frequência | Impacto | Esforço para fix |
|----------|-----------|-----------|--------|-----------------|
| [P1] | Alta | 5/5 | [Churn, NPS, CAC] | [Estimado] |
| [P2] | Alta | 4/5 | [Impact] | [Estimado] |
| [P3] | Média | 3/5 | [Impact] | [Estimado] |
| [P4] | Baixa | 2/5 | [Impact] | [Estimado] |
## Recomendações
1. **Quick win** — [Problema P3]: Fazer [ação] em [timeline curta]
- Evidência: [X/5 mencionou]
- Impacto estimado: [X% melhoria em métrica]
2. **Medium priority** — [Problema P1]: Especificar [feature] para [PRD]
- Evidência: [X/5 + JTBD: ...]
- Impacto estimado: [X% redução em churn]
- Próximo passo: Validar com mais dados (experimento ou entrevista com 10 clientes)
3. **Research needed** — [Problema P2]: Investigar [gap]
- Evidência: [X/5 mencionou, mas não está claro]
- Próximo passo: Session replay de [X usuários] ou entrevista focada
## Anexo: Quotes por tema
### "Falta de onboarding"
> "I spent 30 mins figuring out how to connect Salesforce. No guide, no tooltip." — Cliente A
> "Primeira coisa que fiz foi abrir um ticket com suporte porque não sabia por onde começar." — Cliente B
### "Performance em dados grandes"
> "Quando tenho > 10k leads, o sistema fica lento." — Cliente C
> "Report leva 5 minutos para carregar. Salesforce carrega em 1 segundo." — Cliente D
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.
- 9d ago First seen · 218 lines · 0 tokens per session scan A 176e0a041b0b
interview-synthesis is a command published in the GitHub repository lucasgaravelli/pm-skills-claude-code (20 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,169 tokens. A static security scan graded it A with 0 findings. It is 100% identical to interview-synthesis, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.