Insights Report

Generate a usage insights report from local Claude Code, Codex, pi, and omp session transcripts. Use when the user asks for an insights report, session analysis, usage review, "how do I work with agents", or runs /insights-report.

9 stars 1 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add lingengyuan/my-skills --skill insights-report
Manual install
git clone --depth 1 https://github.com/lingengyuan/my-skills.git /tmp/my-skills
mkdir -p ~/.claude/skills
cp -r /tmp/my-skills/.claude/skills/insights-report ~/.claude/skills/insights-report

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Insights Report

从本机 Claude Code、Codex、pi、omp 的会话记录生成 `/insights` 风格的 HTML 报告。采集和渲染由脚本完成,语义分析由当前 agent 完成。

## 支持的 agent

| agent | 数据来源 | 会话格式 |
|---|---|---|
| Claude Code | `~/.claude/projects/**/*.jsonl` | `user` / `assistant` 消息 + `tool_use` / `tool_result` 块 |
| Codex | `codex app-server` 的 `thread/list` + `thread/items/list`;旧版本回退到 `~/.codex/sessions/**/rollout-*.jsonl`、`~/.codex/archived_sessions/rollout-*.jsonl` | app-server 返回规范化 item;回退路径解析 `session_meta` + `response_item` + `event_msg` |
| pi | `~/.pi/agent/sessions/**/*.jsonl` | `session` + `message` + `toolCall` / `toolResult` |
| omp | `~/.omp/agent/sessions/**/*.jsonl` | 与 pi 相同的 JSONL 布局;未安装时自动跳过 |

路径可以用环境变量覆盖:`CLAUDE_CONFIG_DIR`、`CODEX_HOME`、`PI_HOME`、`OMP_HOME`。Codex 可执行文件可以用 `CODEX_BIN` 指定。

Codex 没有内置的 insights 报告命令。内置的会话入口是 `codex agents`、`codex resume --all`、`codex migrate-rollouts --json`,以及 app-server 的 `thread/*` 方法。脚本优先走 app-server;app-server 不可用时才解析 rollout 文件。

## 流程

### 1. 采集

```bash
python3 -I /Users/hughlin/.claude/skills/insights-report/scripts/collect.py --agent auto --days 30
```

默认输出到 `/Users/hughlin/.claude/usage-data/insights-skill/`:

- `stats.json`:聚合指标和会话列表。
- `digest.md`:给 agent 阅读的紧凑摘要。

参数:

- `--agent auto|all|claude,codex,omp,pi`:要扫描的 agent,可逗号分隔。`auto` 根据当前进程判断调用方 agent;判断不出时退回 `all`。默认 `auto`。
- `--days N`:只分析最近 N 天有更新的会话,`0` 表示全部。默认 30。
- `--max-sessions N`:最多分析多少个会话。默认 500。
- `--out DIR`:输出目录。
Read the full skill on GitHub

Details

Skill name
insights-report
Path
.claude/skills/insights-report/SKILL.md
License
MIT
Repo updated
14 November 2026

FAQ

What does the Insights Report skill do?

Generate a usage insights report from local Claude Code, Codex, pi, and omp session transcripts. Use when the user asks for an insights report, session analysis, usage review, "how do I work with agents", or runs /insights-report.

How do I install the Insights Report skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add lingengyuan/my-skills --skill insights-report. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Insights Report popular?

It lives in lingengyuan/my-skills, which has 9 GitHub stars and 1 forks.

Related skills

Brief Output

9

lingengyuan/my-skills

精简回答、技术说明与工程文档,删除冗余信息与 AI 味表达,只保留完成任务所需的必要事实与技术决策。适用于精简输出、压缩改写、去除 AI 腔调以及全文一致性修订。

AI, LLMs & Agents

Google Go Style

9

lingengyuan/my-skills

按 Google Go Style 编写、重构或审查 Go 代码。用于命名、注释、接口、错误处理、并发、包组织与可维护性决策。

Software Development

Insight Collector

9

lingengyuan/my-skills

Analyze URLs, source code, images, technical documents, or notes, and archive reusable insights, code snippets, and architecture patterns into a knowledge base. Use when collecting knowledge, archiving technical articles, saving reusable code, or recording insights (收录, 记录一下).

Software Development

Live Prompt

10

thatmike1/claude-skills

Write a copy-paste prompt that hands a task (usually a beads issue) to a fresh Claude instance the user will actively work with, in either collaborative (discuss-approach-first) or off-the-leash (implement-end-to-end) mode. Use when the user says "give me a prompt", "prompt for <task-id>", or wants to start a fresh instance on a task. For unattended runs (user going AFK), use the afk-prompt skill instead.

AI, LLMs & Agents

Gpt Pro

10

thatmike1/claude-skills

Hand a question to ChatGPT's Pro model or its image generator through the user's own chat window, off the Codex meter — the agent packs the prompt and context, the user pastes it and copies the answer back. Use when a plan or design wants a second opinion from another model family, for a large divergent idea run, for self-contained 3D or math-heavy code, for an image, or when the user says gpt-pro or asks to put something to ChatGPT.

AI, LLMs & Agents

Orchestrate

10

thatmike1/claude-skills

Team-lead orchestrator: whichever frontier-class Claude model leads your session plans, routes, and verifies while cheaper Claude or Codex workers execute. Use for: orchestrate, delegate, conductor mode, save tokens, multi-agent.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.