levnikolaevich avatar

Ln 002 Session Analyzer

This is a post-mortem tool for your Claude sessions. Run it after completing a task or when something feels off, and it analyzes the conversation or recent JSONL logs across ten dimensions: tool errors, wasted reads, process loops, communication bloat, scope drift, and more. It distinguishes between things that broke (NOOP_EDIT, permission failures), things that wasted tokens (reading the same file three times), and patterns you can improve (dead ends before pivoting, trial and error). The output is actionable: which SKILL.md needs path anchors, which scripts belong in references instead of being written ad hoc each run, where hooks are blocking unnecessarily. Think of it as a linter for your agent's behavior rather than its code.

skills.sh installs
172
GitHub stars
591
last updated
Aug 21, 2026

Install

$ npx -y skills add levnikolaevich/claude-code-skills --skill ln-002-session-analyzer --agent claude-code

Installs into .claude/skills of the current project.

Files

This is a post-mortem tool for your Claude sessions. Run it after completing a task or when something feels off, and it analyzes the conversation or recent JSONL logs across ten dimensions: tool errors, wasted reads, process loops, communication bloat, scope drift, and more. It distinguishes between things that broke (NOOP_EDIT, permission failures), things that wasted tokens (reading the same file three times), and patterns you can improve (dead ends before pivoting, trial and error). The output is actionable: which SKILL.md needs path anchors, which scripts belong in references instead of being written ad hoc each run, where hooks are blocking unnecessarily. Think of it as a linter for your agent's behavior rather than its code.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/levnikolaevich/claude-code-skills
Category
Frontend Development
First seen
Jun 3, 2026

More from levnikolaevich/claude-code-skills

All 128
1bowenliang123 avatarmarkdown-exporterbowenliang123/markdown-exporterConvert Markdown text to DOCX, PPTX, XLSX, PDF, HTML, IPYNB, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc fil167skills.sh installs
2rohitg00 avatarauto-setuprohitg00/pro-workflowAuto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.165skills.sh installs
3mindgames avataragent-browser-relaymindgames/agent-browser-relayRead metadata, DOM, screenshots, and structured page payloads from an attached Chrome or Chromium tab through the local Agent Browser Relay extension. Use when 164skills.sh installs
4levnikolaevich avatarln-012-mcp-configuratorlevnikolaevich/claude-code-skillsUse when installing MCP packages and configuring Claude-side MCP registration, hooks, permissions, IDE extension mode, and migrations.162skills.sh installs
5liangdabiao avatardata-exploration-visualizationliangdabiao/claude-data-analysis-ultra-main自动化数据探索和可视化工具,提供从数据加载到专业报告生成的完整EDA解决方案。支持多种图表类型、智能数据诊断、建模评估和HTML报告生成。适用于医疗、金融、电商等领域的数据分析项目。160skills.sh installs
6rohitg00 avatarllm-gaterohitg00/pro-workflowLLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set u158skills.sh installs