AGENT SKILL

the-fool

Stress-test a pending decision, plan or claim with its rationale, alternatives and reversibility; expose concrete threats, fragile assumptions and evidenced biases. Use for advogado do diabo, challenge this, pre-mortem, red team or blind spots. Do NOT use to decide for the owner, implement the solution, or harvest lessons from finished work (learning-opportunities).

License 许可
CC-BY-4.0
最近更新
2026-11-14
Stars
★ 1
Forks
0

01 前言 Front Matter

name
the-fool
license
CC-BY-4.0
metadata
{ "author": "Tech Leads Club", "version": "1.1.0", "owner_agent": "codenavi-agent" }
description
Stress-test a pending decision, plan or claim with its rationale, alternatives and reversibility; expose concrete threats, fragile assumptions and evidenced biases. Use for advogado do diabo, challenge this, pre-mortem, red team or blind spots. Do NOT use to decide for the owner, implement the solution, or harvest lessons from finished work (learning-opportunities).

02 资源文件 24

03 SKILL.md 正文

the-fool

Governance: CodENavi Full Workspace v2. Skill of codenavi-agent; inherit AGENTS.md. Lifecycle: BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF.

Workflow

  1. Obtain the decision, rationale, discarded alternatives and reversibility from supplied evidence. If rationale/alternatives are absent, return REPENSAR for missing basis; never invent an argument to defeat it.
  2. Read decision lens. Steelman the actual choice; select only applicable internal modes from the retained references.
  3. Run pre-mortem, surface load-bearing assumptions and falsifiers, red-team the strongest opposite case, and identify evidenced confirmation/sunk-cost/groupthink/anchoring/optimism/overconfidence biases.
  4. Scale scrutiny to reversibility. Return SEGUIR / SEGUIR COM AJUSTE / REPENSAR with threats ordered by likelihood, assumptions, biases and evidence that would change the verdict.
  5. Leave the final choice with its owner. Critique only; no code changes or new identities. Sequential self-critique cannot promise independent blind context.

Input: pending decision packet. Output: specific challenge report in PT-BR, without praise or invented findings. Source: IMG_2768–IMG_2770; retained TLC modes remain available under this contract.

Examples and failure handling

Example: “challenge replacing this database” → rationale/alternatives/reversibility packet, premortem and specific verdict; a reversible style choice receives a short pass. Error: absent rationale → REPENSAR with missing basis, never an invented counterargument.

Retained resources

04 同仓库更多 Skills

paulosantanna
paulosantanna/ai-assistent-universal-coder

workspace-brain

Operate the CodENavi workspace brain MCP and CLI — cloud DeepSeek RAG, disk corpus at WORKSPACE_BRAIN_ROOT, Jev URL curation, and event logging for Cursor/Codex/OpenCode/Claude. Use when ingesting repo knowledge, asking the brain, mapping web seeds, or recording AI-driven file changes. Do NOT use for local Ollama RAG or storing API keys in git.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

workbench-profile-resolver

Provide enterprise-grade capability for `workbench-profile-resolver` inside AEOS v1.1. Use when the user requests workbench profile resolver or invokes workbench-profile-resolver. Do NOT use for unrelated tools or unapproved remote writes.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

wordpress-expert

Staff-level WordPress engineering super-skill for one-shot site mapping, clean-code AI-assisted project creation/modification, the complete installed plugin universe, governed remote wp-admin operations, themes/blocks/layout, third-party integrations and production-safe changes. Use when the user requests wordpress expert or invokes wordpress-expert. Do NOT use for unrelated languages, domains or production deployment.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

whatsapp-simulator

Generate synthetic WhatsApp-style conversation fixtures for testing conversational systems, support flows and automation. Use when the user requests whatsapp simulator or invokes whatsapp-simulator. Do NOT use for unrelated tools or unapproved remote writes.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

web-quality-audit

Assimilated TLC/web-quality multi-area audit. Review performance, accessibility, SEO and best practices in one pass. Triggers: audit my site, review web quality, check page quality, optimize my website across areas. Do not use for a single-area job (core-web-vitals, ai-seo, best-practices, perf-lighthouse).

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

voiceai

Provide an evidence-backed voice interface for AEOS. Activating this skill is treated as explicit current-session consent for `voiceai` to record user audio or transcribe audio from user-authorized audio/video media within the declared scope. The skill can: Use when the user requests voiceai or invokes voiceai. Do NOT use for unrelated tools or unapproved remote writes.

★ 1