Oobo

Context beyond the diff - captures AI sessions, tokens, code attribution, semantic code search, and engineering memory via MCP. Use when the user asks about commit history with AI context, session history, code attribution, token usage, code search, or engineering memory.

43 stars 9 forksAI, LLMs & Agents

Install

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

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

From the SKILL.md

# Oobo - Context beyond the diff

Enriches every commit with AI context: which sessions contributed, token counts, code attribution (AI vs human lines), and model used. Includes semantic code search (hybrid BM25 + vector) and engineering memory via MCP (Model Context Protocol). Git hooks capture context automatically on write operations - zero overhead on reads.

If `oobo` is not installed, direct the user to https://github.com/ooboai/oobo/releases.

Oobo is open-source ([Apache-2.0/MIT](https://github.com/ooboai/oobo)), local-first, no telemetry.

> **Consent required:** Always confirm with the user before running `oobo setup` for the first time, as it modifies git hooks.

## Output Modes

Three mutually exclusive modes:

- Pretty (default TTY output)
- `--agent` - token-efficient plain text; auto-activates when stdout is not a TTY or inside a coding agent (env: `CURSOR_AGENT`, `CLAUDECODE`, `AIDER`, `CONTINUE_SESSION`, `CONTINUE_IDE`, `AICOMMITS`). **Use this by default when you are an agent.**
- `--json` - full structured JSON. Use only when you need the object graph.

## Quick Reference

| Task | Command |
|------|---------|
| Recent commits with attribution | `oobo -n 10` |
| Drill into one commit | `oobo anchor show <sha>` |
| Anchors in the last 24h | `oobo --since 24h` |
| Filter by tool | `oobo --tool cursor` |
| Per-line AI blame | `oobo blame src/main.rs` |
| Semantic code search | `oobo search "query"` |
| Search sessions + anchors | `oobo recall "query"` |
Read the full skill on GitHub

Details

Skill name
oobo
Repository
ooboai/oobo
Path
skills/core/SKILL.md
License
Apache-2.0
Repo updated
8 July 2026

FAQ

What does the Oobo skill do?

Context beyond the diff - captures AI sessions, tokens, code attribution, semantic code search, and engineering memory via MCP. Use when the user asks about commit history with AI context, session history, code attribution, token usage, code search, or engineering memory.

How do I install the Oobo skill?

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

Is Oobo popular?

It lives in ooboai/oobo, which has 43 GitHub stars and 9 forks.

Related skills

Agent Media

43

yuvalsuede/agent-media-skill

AI UGC video production from the terminal using the `agent-media` CLI.

AI, LLMs & Agents

Lengyi Shotlist

43

woyin2024/lengyi-shotlist

设计电影级分镜视频提示词。输入一段文本(小说片段、一句剧情或几个主题词),拆分或扩写成一段 8-15s 视频的顺序镜头脚本,自动确定分镜数(4/6/9/12/16)与每镜时长,逐镜给出可直接复制到可灵/海螺/seedance 2.0/veo 的提示词——含镜号、场景、风格、主体、动作过程、镜头运动、剧情内容,并附"参考主体生图提示词"以锁定主体一致性。当用户要做视频分镜、分镜脚本、镜头脚本、shotlist、顺序分镜、文生视频/图生视频、AI视频镜头脚本时使用。

AI, LLMs & Agents

Capafy Publisher

49

Capafy/Capafy-skills

Creator-side Capafy workflow for publishing, updating, packaging, uploading, re-shipping, or managing an Agent/Skill. Also handles creator earnings, payouts, statistics, refunds, certification/KYC, review links, Agent continuation, and publisher-account switching. Generic buyer login, balance, orders, purchases, subscriptions, and instances belong to capafy-user.

AI, LLMs & Agents10

Gtm Pipeline:signal Search

77

keinsaasforever/gtm-pipeline-skills

Find buying intent signals for target companies and score them for purchase intent. Runs a Python script (signal_search.py) that orchestrates Parallel web search (always on), Firecrawl crawl (opt-in), Parallel structured enrichment (opt-in), and a Signal Assessment LLM that scores 1-100. Universal templates live in the script; client-specific prompts come from the working directory's context/ files. Runs standalone or in either pipeline workflow — does NOT require ICP scoring as input. Also triggers on "signal search", "find signals for", "buying intent".

AI, LLMs & Agents

Claude Slim

44

iops-leo/claude-slim

Analyze and reduce Claude Code token overhead. Scans skills, plugins, memory files, and CLAUDE.md for bloat — then cleans up with user approval. Use when: /claude-slim, token optimization, reduce tokens, slim down, cleanup skills, token diet, save tokens, context diet

AI, LLMs & Agents

AI Ds Composer

73

cris-achiardi/claude-skills

Strategic guide for consuming design system metadata to compose components intelligently. Use when generating or modifying UI components and layouts to ensure component reuse, proper variant selection, and adherence to design system patterns. Helps Claude understand project structure, read hierarchical metadata indexes, apply anti-pattern rules, and flag when existing components don't fit a requirement.

AI, LLMs & Agents

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