Analyze Logs — Data skill for Claude Code
Analyze GPU monitoring data (monitor.csv) and training metrics from a completed compass-app-jasper experiment.
How to install Analyze Logs
Installs to ~/.claude/commands/peiranfeng-my-claude-code-analyze-logs.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/PeiranFeng/my-claude-code/HEAD/.claude/commands/analyze-logs.md -o ~/.claude/commands/peiranfeng-my-claude-code-analyze-logs.md Restart Claude Code, or start a new session, for it to be picked up.
What Analyze Logs does
name: analyze-logs description: Analyze GPU monitoring data (monitor.csv) and training metrics from a completed compass-app-jasper experiment. Use when the user wants a GPU utilization report or training metrics summary from an experiment directory. disable-model-invocation: false allowed-tools: Bash Read Glob Grep
Analyze Experiment Logs
Step 1 — 确认实验目录
确认目标实验目录(用户提供,或从对话上下文推断):
ls /
Step 2 — 确认可用的日志文件
**先检查文件是否存在、格式是什么,再做任何分析。不要假设某个字段存在。**
检查以下文件(如存在)
Alternatives in Data
- Claude Code Usage Monitor — by Maciek-roboblog - A real-time terminal-based tool for monitoring Claude Code token usage 7k ★
- Osint Employees — Gather employee names + email patterns for password spray prep 4.5k ★
- Trading Signal — Monitor on-chain Smart Money buy/sell signals with price, max gain, and exit rate data on Solana and BSC 483 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Lecture To Notes
Lecture recordings → structured grounded notes + a synced HTML viewer: video, timestamped transcript and curat
Cc Analytics
Use when user asks for Claude Code usage stats, weekly analytics, project activity summary, or wants to see wh
Generate More Training Data
This command analyzes patterns in existing data files (CSV, JSONL) and generates additional synthetic training
Page Monitoring
Monitor web pages for changes
Write Stakeholder Brief
Translate technical data work into a 1-page business summary with impact metrics
Stats
Pipeline metrics from logs — task count, rejection rates, skill usage, iterations. Answers "is the plugin actu
Related Agents
Incident Investigator
Investigates an LLM-serving incident (vLLM or SGLang) in an isolated context. Reads long runtime logs, runs th
Container Monitoring
Monitor Kubernetes and containerized environments including Docker, pods, deployments, and cluster health metr
Monitor UI
Use this agent proactively whenever:\n- The user mentions monitoring, dashboards, metrics, or real-time data v