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/opportunity-tree)<a href="https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/opportunity-tree"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/opportunity-tree/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/opportunity-tree"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/opportunity-tree.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 | $0.04296 |
| Opus 5 | $0.00000 | $0.02148 |
| Sonnet 5 | $0.00000 | $0.00859 |
| Haiku 4.5 | $0.00000 | $0.00430 |
Grade A, and why
opportunity-tree 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 10d 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 opportunity-tree — 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/opportunity-tree
O que essa skill faz
Gera uma Opportunity Solution Tree (OST) completa seguindo o framework de Teresa Torres (Continuous Discovery Habits). Estrutura o pensamento de discovery em 4 níveis: Outcome → Opportunities → Solutions → Experiments.
Saída: Árvore de oportunidades com scores, soluções comparadas e experimentos desenhados — pronta para alinhar o Product Trio.
Quando usar
- Tem um outcome claro mas não sabe por onde começar
- Quer priorizar oportunidades com base em dados, não intuição
- Precisa gerar múltiplas soluções antes de se comprometer com uma
- Quer alinhar PM, Designer e Tech Lead sobre o que explorar primeiro
- Está preso no modo "feature factory" e quer voltar para discovery
Input esperado
Mínimo:
- Desired Outcome: Métrica específica que quer mover (ex: "Aumentar retenção de 7 dias de 30% para 50%")
- Contexto do produto: O que é o produto, quem usa
- Dados disponíveis: Que pesquisas, entrevistas ou analytics existem
Opcional:
- Trechos de entrevistas com usuários
- Dados de analytics (funil, retenção, comportamento)
- Oportunidades já identificadas
- Constraints (budget, timeline, capacidade do time)
- Personas definidas
Processo
-
Definir UM outcome — Escolher uma única métrica mensurável com baseline e target. Não tente resolver tudo ao mesmo tempo. Ex: "Aumentar 7-day retention de 30% para 50%." Se o input tiver múltiplos outcomes, pedir para priorizar.
-
Identificar 4-6 oportunidades — Extrair de pesquisa com usuários (entrevistas, surveys, analytics). Cada oportunidade deve ser um problema ou necessidade do cliente, NUNCA uma feature. Usar framing centrado no usuário: "Eu luto para..." ou "Eu gostaria de poder...". Se não houver dados, marcar como hipótese.
-
Scorer oportunidades — Para cada oportunidade, avaliar:
- Importância (1-5): Quanto isso importa para o usuário?
- Satisfação (1-5): Quão bem resolvido está hoje?
- Score = Importância × (1 − Satisfação/5)
- Priorizar as 2-3 com maior score.
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.
- 10d ago First seen · 341 lines · 0 tokens per session scan A 90c62f221f16
opportunity-tree 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 4,296 tokens. A static security scan graded it A with 0 findings. It is 100% identical to opportunity-tree, 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.