メニュー
Use when AI agents frequently hit dead ends, when reliability is the main constraint on scaling utility, or when general model improvements don't solve specific blockers
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when designing AI agent products, defining roadmaps for agentic workflows, or evaluating how to evolve AI from passive tool to proactive partner in software development
Shift from rigid roles (PM, Designer, Engineer) towards a model where individuals use AI to bridge skill gaps, enabling smaller and flatter teams. Use in early-stage startups or innovation units where speed is critical.
Use when designing AI agents or chatbots, when raw model outputs feel like a black box, or when building natural language interfaces that need structure and trust
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for agentic workflows
View yourself as an entity with infinite dimensions rather than a single good/bad identity. Strengths and weaknesses are often the same trait in different contexts. Use during performance reviews or when receiving tough feedback.
Review your calendar, color-code activities by energy impact (Green/Red), and systematically delegate draining tasks to maximize time in your Zone of Genius.
| name | unstuck-scaling |
| description | Use when AI agents frequently hit dead ends, when reliability is the main constraint on scaling utility, or when general model improvements don't solve specific blockers |
A systematic approach to improving AI reliability by treating "getting stuck" as the primary bottleneck. Instead of broad improvements, painstakingly identify specific failure modes and create tight feedback loops.
Core principle: Address specific bottlenecks, not general intelligence.
┌─────────────────────────────────────────────────────────────────┐
│ │
│ ┌───────────────────┐ │
│ │ IDENTIFY │ │
│ │ 'Stuck' Points │ │
│ │ (auth, payments) │ │
│ └─────────┬─────────┘ │
│ │ │
│ ▼ │
│ ┌───────────────────┐ │
│ │ ADDRESS │ │
│ │ Specific │ │
│ │ Bottlenecks │ │
│ └─────────┬─────────┘ │
│ │ │
│ ▼ │
│ ┌───────────────────┐ │
│ │ QUANTITATIVELY │ │
│ │ Tune System │ │
│ │ (pass/fail rate) │ │
│ └─────────┬─────────┘ │
│ │ │
│ ▼ │
│ ┌───────────────────┐ │
│ │ FAST FEEDBACK │─────────────────────────┐ │
│ │ Loop │ │ │
│ └───────────────────┘ │ │
│ ▲ │ │
│ └───────────────────────────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────┘
| Principle | Description |
|---|---|
| Specific blockers | Identify exact points where AI fails |
| Quantitative tuning | Measure stuck rates, not vibes |
| Fast feedback | Rapid iteration on fixes |
| Bottleneck focus | Specific roadblocks > general intelligence |
Source: Anton Osika (Lovable, GPT Engineer) via Lenny's Podcast