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
- 参考文档.skill-meta.json120 B
- 参考文档lenses/the-fool.md1.2 KB
- 参考文档PERMISSIONS.yaml227 B
- 参考文档POLICY.md106 B
- 参考文档references/cognitive-bias-inventory.md7.5 KB
- 参考文档references/dialectic-synthesis.md7.2 KB
- 参考文档references/evidence-audit.md9.2 KB
- 参考文档references/lenses/retained/legacy-contract.md225 B
- 参考文档references/mode-selection-guide.md5.8 KB
- 参考文档references/ORIGINAL_SKILL.md8.5 KB
- 参考文档references/package-notes.md143 B
- 参考文档references/pre-mortem-analysis.md8.8 KB
- 参考文档references/provenance.md938 B
- 参考文档references/red-team-adversarial.md9.6 KB
- 参考文档references/socratic-questioning.md7.2 KB
- 参考文档references/tlc/references/cognitive-bias-inventory.md7.5 KB
- 参考文档references/tlc/references/dialectic-synthesis.md7.2 KB
- 参考文档references/tlc/references/evidence-audit.md9.2 KB
- 参考文档references/tlc/references/mode-selection-guide.md5.8 KB
- 参考文档references/tlc/references/pre-mortem-analysis.md8.8 KB
- 参考文档references/tlc/references/red-team-adversarial.md9.6 KB
- 参考文档references/tlc/references/socratic-questioning.md7.2 KB
- 参考文档references/tlc/UPSTREAM.md8.5 KB
- 参考文档references/usage-and-verification.md1.3 KB
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
- 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.
- Read decision lens. Steelman the actual choice; select only applicable internal modes from the retained references.
- 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.
- Scale scrutiny to reversibility. Return SEGUIR / SEGUIR COM AJUSTE / REPENSAR with threats ordered by likelihood, assumptions, biases and evidence that would change the verdict.
- 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
- Read retained cognitive-bias-inventory only for its matching mode; this entry and root governance take precedence.
- Read retained dialectic-synthesis only for its matching mode; this entry and root governance take precedence.
- Read retained evidence-audit only for its matching mode; this entry and root governance take precedence.
- Read retained mode-selection-guide only for its matching mode; this entry and root governance take precedence.
- Read retained ORIGINAL_SKILL only for its matching mode; this entry and root governance take precedence.
- Read retained package-notes only for its matching mode; this entry and root governance take precedence.
- Read retained pre-mortem-analysis only for its matching mode; this entry and root governance take precedence.
- Read retained provenance only for its matching mode; this entry and root governance take precedence.
- Read retained red-team-adversarial only for its matching mode; this entry and root governance take precedence.
- Read retained socratic-questioning only for its matching mode; this entry and root governance take precedence.
- Read retained tlc only for its matching mode; this entry and root governance take precedence.
- Read retained usage-and-verification only for its matching mode; this entry and root governance take precedence.
04 同仓库更多 Skills
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.
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.
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.
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.
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).
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.