Claude Skills by giuice

Produce the smallest user-facing report that preserves every material fact about a task outcome, by classifying the terminal state, comparing it against the contract, filtering activity out, and checking that no material fact was lost to compression. Use this skill at a task boundary — when work is complete, partial, blocked, or failed — whenever the user asks what the outcome was or for a summary of what was accomplished, and whenever an execution run ends and its result must be communicated...

Execute a PLAN.md task by task as an orchestrator, dispatching each task, verifying its postcondition against observable state, recording outcomes in a semantic ledger, and triggering replanning when reality diverges from the plan. Use this skill whenever the user asks to execute, run, carry out, work through, or implement a plan, whenever work should proceed task by task with evidence and state tracking, or whenever resuming a partially executed plan. Requires a PLAN.md produced by plan-from...

Fluxo de trabalho com IA em 3 fases — Explorar (brainstorm guiado), Planejar (plano com tarefas atômicas) e Executar (passo a passo). Ative esta skill sempre que o usuário digitar `/explorar`, `/planejar` ou `/executar`, ou quando tiver qualquer objetivo que envolva planejamento, criação ou dúvida aberta. Serve tanto para tarefas de código quanto para tarefas do mundo real (escrever, pesquisar, contatar, montar). Idioma pt-BR.

Turn a SPEC, PRD, or any stated goal into a high-level executable PLAN of outcome-shaped tasks, and regenerate that plan when execution reveals it is wrong. Use this skill whenever the user asks to plan, break down, decompose, sequence, or roadmap work from a spec/requirements document or a goal, and whenever an executor's replan gate fires because a task's postcondition failed, expected state does not exist, a planned task is impossible, or new information invalidates a later task. Runs in t...

Create a complete SPEC from scratch through an exhaustive requirements interview before any planning or implementation. Use this skill whenever the user asks to create, define, clarify, scope, or write a spec/SPEC/PRD/requirements document from an idea, especially when they want to avoid assumptions, start at "step zero," or prepare input for later planning workflows. This skill must question goals, requirements, constraints, edge cases, business rules, and acceptance criteria before drafting...

Route a piece of work through the full long-horizon loop — specify, plan, execute, replan, report — by deciding whether the work warrants the loop, detecting which stage it is already in, and handing off to the right skill. Use this skill whenever the user asks to take something from idea to done, to handle a goal end to end, to run the full workflow, to work on something properly with a plan and evidence, or to resume, continue, or check where a previous run of this workflow stopped.