AgentSkillsCN

unstuck-scaling

当 AI 智能体频繁遭遇瓶颈,当可靠性成为制约实用化规模的关键因素,或当通用模型的改进始终无法破解特定的阻塞难题时,此技能将大显身手。

SKILL.md
--- frontmatter
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

The Unstuck Scaling Framework

Overview

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.

The Cycle

code
┌─────────────────────────────────────────────────────────────────┐
│                                                                  │
│     ┌───────────────────┐                                       │
│     │  IDENTIFY         │                                       │
│     │  'Stuck' Points   │                                       │
│     │  (auth, payments) │                                       │
│     └─────────┬─────────┘                                       │
│               │                                                  │
│               ▼                                                  │
│     ┌───────────────────┐                                       │
│     │  ADDRESS          │                                       │
│     │  Specific         │                                       │
│     │  Bottlenecks      │                                       │
│     └─────────┬─────────┘                                       │
│               │                                                  │
│               ▼                                                  │
│     ┌───────────────────┐                                       │
│     │  QUANTITATIVELY   │                                       │
│     │  Tune System      │                                       │
│     │  (pass/fail rate) │                                       │
│     └─────────┬─────────┘                                       │
│               │                                                  │
│               ▼                                                  │
│     ┌───────────────────┐                                       │
│     │  FAST FEEDBACK    │─────────────────────────┐             │
│     │  Loop             │                         │             │
│     └───────────────────┘                         │             │
│               ▲                                   │             │
│               └───────────────────────────────────┘             │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

Key Principles

PrincipleDescription
Specific blockersIdentify exact points where AI fails
Quantitative tuningMeasure stuck rates, not vibes
Fast feedbackRapid iteration on fixes
Bottleneck focusSpecific roadblocks > general intelligence

Common Mistakes

  • Focusing on general model improvements
  • Failing to measure "stuck" rates quantitatively
  • Slow feedback loops preventing rapid iteration

Source: Anton Osika (Lovable, GPT Engineer) via Lenny's Podcast