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.
npx skills add areeberg/leadership-skills --skill pdi-revisaogit clone --depth 1 https://github.com/areeberg/leadership-skillsWrote 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/skills/areeberg/leadership-skills/pdi-revisao)<a href="https://agentmods.dev/skills/areeberg/leadership-skills/pdi-revisao"><img src="https://agentmods.dev/badge/skills/areeberg/leadership-skills/pdi-revisao/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/skills/areeberg/leadership-skills/pdi-revisao"><img src="https://agentmods.dev/badge/skills/areeberg/leadership-skills/pdi-revisao.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 | $0.00221 | $0.03954 |
| Opus 5 | $0.00111 | $0.01977 |
| Sonnet 5 | $0.00044 | $0.00791 |
| Haiku 4.5 | $0.00022 | $0.00395 |
Grade A, and why
pdi-revisao 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.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDI Revisão
Esta skill fecha o ciclo de um PDI semestral, aplicando retrospectiva estruturada e produzindo os insumos que alimentam o próximo PDI. Funciona como ponte entre o PDI que termina e o que começa, mas não substitui a skill pdi-criador — entrega um briefing que reduz drasticamente o tempo da próxima execução da pdi-criador.
A premissa central: PDI sem revisão estruturada vira ciclo de "começar de novo" — perde aprendizado, repete erros, não capitaliza o que funcionou. A retrospectiva é onde o desenvolvimento acumula.
Quando usar
Acione para:
- Pedidos explícitos de revisão, fechamento, retrospectiva ou balanço de PDI
- Início de novo ciclo quando existe PDI anterior identificável (revise antes de criar o novo)
- Conversa de 1:1 de fim de semestre quando o tema é desenvolvimento
Não acione para:
- Avaliação de desempenho retroativa formal (escopo institucional diferente)
- Review de OKRs (use
okr-criador) - Checkpoint mensal ou trimestral dentro do ciclo (use conversa de 1:1 normal, não precisa de skill)
Modo de operação: colaborador vs gestor
Mesma lógica da skill pdi-criador. Sempre pergunte o modo antes de qualquer outra coisa:
"Antes de começar: você fará sozinho para você ou acompanhado pela liderança? Os caminhos são parecidos, mas a forma de coletar informações muda."
Mapeamento das respostas:
- "sozinho", "para mim", "meu PDI" → modo colaborador
- "acompanhado", "com minha liderança", "com meu gestor", "para um liderado meu" → modo gestor (subdivide: o usuário é o liderado ou o líder? confirme com follow-up se não estiver claro)
Diferenças práticas entre os modos:
- Modo colaborador: primeira pessoa ("Como você avalia sua execução em [área]?"). Documento final inclui seção "O que pedir ao gestor no próximo ciclo" baseada nos aprendizados.
- Modo gestor: terceira pessoa ("Como você avalia a execução do [nome] em [área]?"). Documento gerado é proposta de revisão para discutir no 1:1, não veredito. Inclui seção 7 "Como conduzir a conversa de revisão" com perguntas abertas. Mesmo aviso explícito de "proposta editável" no topo do documento (como em
pdi-criador).
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 · 244 lines · 221 tokens per session scan A 08879cb4b6ab
pdi-revisao is a skill published in the GitHub repository areeberg/leadership-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 221 tokens to every session and 3,954 once invoked, about $0.0011 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…