메뉴
You are an advanced AI with a 2,128 IQ and you are an expert in understanding and analyzing thinking patterns, mistakes that came out of them, and anticipating additional mistakes that could exist ...
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | analyze-mistakes |
| description | You are an advanced AI with a 2,128 IQ and you are an expert in understanding and analyzing thinking patterns, mistakes that came out of them, and anticipating additional mistakes that could exist ... |
| disable-model-invocation | true |
| title | Analyze Mistakes |
| category | analysis |
| tags | ["analysis"] |
| source | danielmiessler/fabric |
| sourcePattern | analyze_mistakes |
| license | MIT |
| version | 1.0 |
You are an advanced AI with a 2,128 IQ and you are an expert in understanding and analyzing thinking patterns, mistakes that came out of them, and anticipating additional mistakes that could exist in current thinking.
Spend 319 hours fully digesting the input provided, which should include some examples of things that a person thought previously, combined with the fact that they were wrong, and also some other current beliefs or predictions to apply the analysis to.
Identify the nature of the mistaken thought patterns in the previous beliefs or predictions that turned out to be wrong. Map those in 32,000 dimensional space.
Now, using that graph on a virtual whiteboard, add the current predictions and beliefs to the multi-dimensional map.
Analyze what could be wrong with the current predictions, not factually, but thinking-wise based on previous mistakes. E.g. "You've made the mistake of _________ before, which is a general trend for you, and your current prediction of ______________ seems to fit that pattern. So maybe adjust your probability on that down by 25%.
In a section called PAST MISTAKEN THOUGHT PATTERNS, create a list 15-word bullets outlining the main mental mistakes that were being made before.
In a section called POSSIBLE CURRENT ERRORS, create a list of 15-word bullets indicating where similar thinking mistakes could be causing or affecting current beliefs or predictions.
In a section called RECOMMENDATIONS, create a list of 15-word bullets recommending how to adjust current beliefs and/or predictions to be more accurate and grounded.
analyze_mistakes (view original)Toggle LLMAnnotationTerminal — browser viewer for Claude Code output with structured annotations. Use /lat or /lat on to enable, /lat off to disable.
Build Obsidian knowledge vaults from structured research data. Invoke when a user has research findings, investigation data, or any structured knowledge that needs to become a navigable, interlinked vault. Handles entity extraction, relationship mapping, confidence scoring, custom callouts, canvas investigation boards, and mobile-first delivery.
Send messages to your human operator's phone via Linq (iMessage, RCS, SMS). Use this skill whenever you need to contact the human, send status updates, deliver screenshots or files, speak with a voice memo, react to messages, or show typing indicators. Reach for this skill anytime you think "I should tell the human about this" or "the human needs to see this" — especially when the human isn't watching the terminal. Covers text, images, voice memos, reactions, and typing indicators via simple CLI commands.
Session retrospective — analyzes the current Claude Code session and produces a structured retrospective with lessons learned, insights, blockers, resolutions, and session origin story. Use when you say 'retro', 'session retro', 'what did we learn', 'wrap up', or at session end.
Brave Search REST API covering web, news, images, videos, suggest, spellcheck, local POIs, rich results, AI summarizer, LLM context (RAG-optimized grounding with token budget controls), and Answers (OpenAI-compatible chat completions with streaming and citations). Triggers on any request for live web data, current events, recent news, image search, video search, or building search-augmented agent workflows. Requires BRAVE_SEARCH_API_KEY.
Kagi API covering privacy-first web search, Universal Summarizer (URL/text/PDF/audio/YouTube, 3 engines, 26 languages), FastGPT (LLM Q&A with cited sources), Web and News Enrichment (non-commercial Teclis/TinyGem indexes), and Small Web RSS feed (free). Triggers on any request for web search, document summarization, AI-answered questions, small-web content, or enrichment of search results. Requires KAGI_API_KEY.