菜单
Visualize an agent's perceive→think→act loop. Inspects tool calls, latency per step, decision branches, retry patterns. Surfaces bottlenecks. Triggers on "trace agent", "why is agent slow", "agent loop analysis", "what did the agent do".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Compute context window budget for a prompt/agent — sums system prompt, tool descriptions, examples, conversation history; flags overruns; suggests cuts. Triggers on "context budget", "how much context", "will this fit", "budget my prompt".
Treat dataset / eval JSONL as code — lint, validate schema, detect duplicates, leakage between train/eval, label imbalance, PII. Karpathy "Software 2.0" lens. Triggers on "audit dataset", "lint jsonl", "check for leakage", "validate eval data".
Enforce "evals over vibes" — before any prompt, agent, or model change, require an eval set with success criteria and baseline measurement. Blocks vibe-only changes. Triggers on "tune prompt", "improve agent", "change model" without prior eval set.
Build a 10-30 case eval dataset from a PRD, skill, or prompt — covering golden path, edge cases, and adversarial inputs. Output as JSONL with input/expected/category. Triggers on "build eval set", "create evals", "generate test cases for prompt".
Break down any ML/AI concept to first principles — strip jargon, derive from basics, build physical/mathematical analogy. Karpathy intuition-building style. Triggers on "first principles", "explain like I'm 5", "derive from scratch", "why does X actually work".
Generate minimal, runnable from-scratch implementation of LLM concepts (attention, BPE tokenizer, backprop, RoPE, KV-cache, MoE, LoRA, RLHF). Karpathy-style pedagogy — code first, theory in comments. Triggers on "explain X from scratch", "minimal X implementation", "show me how X works in code", "build X from zero".
| name | agent-loop-trace |
| description | Visualize an agent's perceive→think→act loop. Inspects tool calls, latency per step, decision branches, retry patterns. Surfaces bottlenecks. Triggers on "trace agent", "why is agent slow", "agent loop analysis", "what did the agent do". |
Run: agent_xyz (total 47s, $0.18, 23 steps)
Step | t(s)| Tokens | Action
1 | 0.4 | 220/80 | perceive: user prompt
2 | 2.1 | 280/40 | think: plan 3 steps
3 | 8.2 | 120/0 | tool: search ✓
4 | 1.1 | 140/60 | think: refine
5 | 7.8 | 110/0 | tool: search ✗ (same query) ← REDUNDANT
6 | ...
Anti-patterns detected:
• Same search query twice (steps 3, 5)
• Long think gap with no progress (steps 11-14)
• Final answer not grounded in tool results
"How I use LLMs" / "Deep Dive into LLMs" Karpathy talks