EO MicroSaaS OS Guide v2 — master orchestrator for the 6-phase MicroSaaS journey. Creates workspace, detects progress, guides students phase-by-phase, handles language pr — from…
Extract learning from completed work to improve future cycles. Use when: (1) After VERIFY phase shows feature complete, (2) End of development iteration, (3) User asks for…
[74] CLOSE. Quick checkpoint during active work when context is running low. Use multiple times per development cycle to preserve progress and lessons.
Use for insight, reframing, contradiction, impasse, and anomaly-driven problem solving when execution effort no longer helps.
Use when when you have a neural network or machine learning model with multiple tunable hyperparameters (layer size, regularization strength, dropout) or design choices (e.
HOAI-Praxis: erstellt Abschlussbericht, Gewährleistungsplan und Lessons Learned; für Architekten, Ingenieure, Bauleiter, Bauunternehmen, Anwälte, Sachverständige und Bauherren im…
Adaptive Cross-session Experience (ACE) playbook manager. Handles lesson extraction, playbook updates, and confidence tracking.
Audit this repo against the AI Codebase Maturity Model (ACMM) — canonical 6-level rubric with 85 criteria from 4 source frameworks (ACMM, Fullsend, AEF, Reflect).
Tutor a student through the A.CRE Accelerator Core — the 18-course flagship program that teaches CRE pros to build institutional-quality models from scratch.
Reusable prompts for labs and sections: predict, justify, compare, teach-back, and peer instruction.
Эксперт active learning. Используй для ML с участием человека, uncertainty sampling, annotation workflows и labeling optimization.
Generiere eine Hinweisfolge für einen Problemtyp, die progressive Offenlegung zeigt ohne die Antwort zu geben.
Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.
TLCL müfredatına yeni bir ders/görev ekler. js/course.js içindeki courseData dizisine kitapla hizalı bir ders nesnesi ekler, gerekli komutları açar ve en/ aynasını çevirir.
Capture a durable lesson, correction, or convention from this session as a reusable adept skill, then sync it to every harness.
Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation.
Use when providing educational legal structure guidance for entrepreneurs. Covers business entity selection, liability considerations, IP protection, and professional referral…
Client advisory communication with fiduciary tone, compliance-friendly language, and plain-language financial education
Complete strategic thinking & mental models toolkit. 50+ decision frameworks organized by situation type — business strategy, investing, hiring, pricing, risk, negotiations,…
Structured post-goal reflection that extracts lessons, evaluates quality, and feeds the self-improvement loop
AG-Vorbereitung und Cold-Call-Prep für Jurastudium: Anwendungsfall Student wird im naechsten Seminar oder Arbeitsgemeinschaft aufgerufen und muss konkrete Faelle vorberei — from…
AG-Vorbereitung und Cold-Call-Prep für Jurastudium: Anwendungsfall Student wird im naechsten Seminar oder Arbeitsgemeinschaft aufgerufen und muss konkrete Faelle vorberei — from…
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more.
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more.
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more.
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more.
Train AI agents using AgentDB's 9 reinforcement learning algorithms including Q-Learning, DQN, PPO, and Actor-Critic.
17-lesson 2026-current supplement to the AI Model Factory by Herman Carter course. Each lesson fills a specific gap in Herman's 2025-vintage stack with the May 2026…
Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/agent, set up an eval harness, define quality metrics for an…
Help users create and run AI evaluations. Use when someone is building evals for LLM products, measuring model quality, creating test cases, designing rubrics, or trying to…
Design AI-supported collaborative tasks that structure group interaction and address participation problems. Use when students struggle to collaborate effectively on group tasks.
Expert in applying AI to education - AI tutors, personalized learning paths, content generation, automated assessments, and adaptive learning systems.
Daily digest of content that helps AI agents improve their own capabilities. Use when setting up learning routines for AI agents, building self-improving systems, or curating…
Use when the user works with AI-Shifu (AI师傅) courses in any capacity of creating, writing, editing, rewriting, optimizing, reordering, deploying, publishing, previewing, or…
AI 관련 자료(YouTube URL, 블로그 URL 등)를 받아 내용을 분석하고 정리하여 Obsidian vault에 마크다운 노트로 저장한 뒤 GitHub에 자동으로 푸시하는 스킬.
Assess and report on AI tool subscriptions, usage patterns, and cost-effectiveness. Use for reviewing AI subscriptions, analyzing tool usage, optimizing AI spend.
Use when a new user arrives and needs assessment. Gathers background, experience level, and learning goals through a warm conversational flow (max 3 questions).
Use whenever you work in the Akashic Aurora repo (E:\AI-Setup) — at session start, after ANY fix that first failed, whenever the user corrects you, and at session end.
Prüft Akteneinsicht in Prüfungsakte und Bewertungsunterlagen im Prüfungsrecht Hochschule.
Prüft Umfang der Akteneinsicht, Bewertungsvermerke, Musterlösung, Protokolle und Kopien im Prüfungsrecht Hochschule.
Navigate through plant intelligence and living forest consciousness. Deploy ONLY when nature consciousness, ecological wisdom, or plant medicine context emerges naturally.
Score composed artifacts against blueprint rubric. Evaluates hook density, singability, rhyme tightness, section completeness, and profanity compliance.
Evaluates ML applications in investment with feature engineering, model selection, and implementation considerations for alpha generation.
Prüft Anerkennung und Anrechnung von Prüfungsleistungen im Prüfungsrecht Hochschule.
Supervisoren-Prüfwarteschlange — studentische Arbeitsergebnisse warten hier auf die Supervisoren-Freigabe, bevor sie an Mandanten oder Gerichte gehen.
Comprehensive annual content review — total output, revenue, growth, top performers, lessons learned, and next-year strategy. The year-end report that shows how far you've come.
Prüft Matrikelnummer, Namensoffenlegung, Gleichbehandlung und Korrekturfehler im Prüfungsrecht Hochschule.
Document technical debt, anti-patterns, and patterns to avoid from analyzed frameworks. Use when (1) creating a "Do Not Repeat" list from framework analysis, (2) categorizing…
Prüft Anwesenheitspflichten als Prüfungsvoraussetzung im Prüfungsrecht Hochschule.
Prüft Anwesenheitspflichten, Fehlzeiten, Satzungsgrundlage und Prüfungszulassung im Prüfungsrecht Hochschule.
Design a bounded local eval suite, prompt set, report, or validator plan after selection finds no adequate existing surface, using deterministic checks first and trace or rubric…
Turn raw technical material into a shareable public-safe artifact while keeping the raw source separate, placing the sanitized result in the canonical sharing surface, and…
Apprenticeship pedagogy for the trades — how craft is actually taught, which is almost nothing like how classroom subjects are taught.
Karpathy-style consolidation: compila observações brutas em páginas markdown no fim da sessão e registra lessons duráveis.
Generate certification exams for chapters or parts. Extracts concepts first, then generates scenario-based questions. Use "ch X" for chapter, "part X" for part.
Creates comprehensive assessment tools, rubrics, and evaluation materials for student work. Use when the user asks to create rubrics, build assessments, evaluate student learning,…
Formative vs summative, rubric design, authentic assessment, competency-based evaluation, and feedback
Routes between five assessment pathways — formative, rubric/criteria, authentic/performance, peer/self, and diagnostic — with validity and equity checks.
Create valid, reliable assessment items across formats (multiple choice, constructed response, performance tasks) following psychometric best practices
Triages an external LLM assessment against the codebase and FOUNDATIONS.md, writes draft specs for accepted proposals, and updates IMPLEMENTATION-ORDER.md.