grill-plano
A Socratic questioning tool that interrogates project plans to find flaws and risks.
Install
mkdir -p .claude/skills/grill-plano && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10309" && unzip -o skill.zip -d .claude/skills/grill-plano && rm skill.zipInstalls to .claude/skills/grill-plano
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Interrogatorio socratico do plano de implementacao: anda a arvore de decisoes e acha furos, premissas e riscos antes da aprovacaoKey capabilities
- →Vet implementation plans phase-by-phase
- →Identify hidden project risks
- →Validate decision trees
- →Audit implementation assumptions
- →Enforce structured interrogation gates
How it works
The skill conducts a Socratic interrogation of an implementation plan, following a strict phase-by-phase process where only one question is asked at a time.
Inputs & outputs
When to use grill-plano
- →Reviewing architecture designs
- →Validating implementation plans
- →Identifying hidden project risks
- →Auditing decision trees
About this skill
Siga TODO o processo descrito em ia/prompts/engenharia/grill-plano.md (na raiz deste repositorio), fase por
fase, na ordem em que esta escrito.
Regras de execucao:
- NAO achate fases interativas em checklist nem em despejo de perguntas — quando o prompt pedir uma pergunta por vez, faca UMA pergunta e espere a resposta.
- Respeite os gates: nao avance de fase sem cumprir o criterio de saida da anterior.
- As instructions deste repositorio (
.github/instructions/) continuam valendo.
When not to use it
- →When skipping phases or gates
Limitations
- →Must not flatten phases into a single checklist
- →Requires waiting for responses between questions
How it compares
It prevents plan approval until all gates are cleared, ensuring a thorough review rather than a quick checklist assessment.
Compared to similar skills
grill-plano side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| grill-plano (this skill) | 0 | 1mo | No flags | Intermediate |
| planning-with-files | 233 | 6mo | Review | Intermediate |
| ralph-plan | 14 | 6mo | No flags | Beginner |
| agent-planner | 3 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
planning-with-files
davila7
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
ralph-plan
mastra-ai
Interactive planning assistant that helps create focused, well-structured ralph-loop commands through collaborative conversation
agent-planner
ruvnet
Agent skill for planner - invoke with $agent-planner
llm-council
am-will
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.
agent-queen-coordinator
ruvnet
Agent skill for queen-coordinator - invoke with $agent-queen-coordinator
swarm-planner
am-will
[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.