Claude Code hook
Claude Adhd Skills
Claude Code skills and hooks for staying organized with AI agents.
Install
git clone https://github.com/ravila4/claude-adhd-skills.gitFrom the README
claude-adhd-skills
(No ADHD required!)
A set of Claude Code skills and hooks I use daily as scaffolding for staying organized while developing with AI agents. The key pieces are time awareness (so Claude knows when to tell me to stop), Obsidian integration (so I can store research and reconstruct what I was doing yesterday), and a nudge system (so promises to "wrap up in 30 minutes" actually stick).
Obsidian is central to the workflow. It's where daily logs, meeting notes, research and ideas land, and because agents can read and write to the vault, it becomes a shared memory between sessions. I can point a new Claude instance at yesterday's journal entry and ask the agent to catch up instead of re-explaining context. Ideas get dumped into notes, marinate, and only the ones that survive get built. obsidian-semantic closes the loop, letting agents search notes by meaning, not just filenames.
What's in the box
Skills
Hooks
CLAUDE.md
A starting point for your own CLAUDE.md. I have found that the following ADHD-specific patterns help me: break suggestions, pacing, focus tracking, and a working relationship that prioritizes asking over assuming.
Installation
1. Copy skills to your Claude Code config
2. Wire up the hooks
Copy the hook configuration into your Claude Code settings. The settings file is at ~/.claude/settings.json (global) or ~/.claude/settings.local.json (local/private).
See settings.json.example for the full config. The key hooks are:
- UserPromptSubmit: Runs on every prompt. Shows current time and any due nudges.
3. Set up your CLAUDE.md
Copy CLAUDE.md to ~/.claude/CLAUDE.md and fill in the {PLACEHOLDERS}:
Edit the file and replace:
- {YOUR_NAME}: your name
- {YOUR_ROLE}: your job title or role
- {WHAT_YOU_DO}: brief description of your work
-…How hooks work
- Hooks are shell commands Claude Code runs at fixed points: before or after a tool call, when you submit a prompt, when Claude stops, on notifications and at session start.
- They are set in the hooks section of ~/.claude/settings.json (or .claude/settings.json for a project), or come bundled in a plugin.
- A hook can block a tool call, add context, or run a formatter or test. Read the scripts before you install them: they run on your machine with your permissions.
Details
- Repository
- ravila4/claude-adhd-skills
- Type
- Hooks
- Language
- Python
- License
- MIT
- Last updated
- 1 March 2026
- Topics
- adhdclaude-codeobsidianproductivityskills
FAQ
What is Claude Adhd Skills?
Claude Code skills and hooks for staying organized with AI agents. It is a hook for Claude Code, from ravila4/claude-adhd-skills on GitHub.
How do I install Claude Adhd Skills?
Clone ravila4/claude-adhd-skills from GitHub and follow the setup steps in its README.
Is Claude Adhd Skills popular?
ravila4/claude-adhd-skills has 171 GitHub stars and 9 forks. It was last updated on 1 March 2026.
More hooks
agentjail
100LuD1161/agentjail
Policy guardrails that check every Claude Code, Codex or Cursor tool call against local rules.
Claude Memory Engine
134HelloRuru/claude-memory-engine
Claude Code 的記憶系統 | A memory system built with hooks + markdown. Zero dependencies.
Flonat Research
149flonat/flonat-research
Shareable Claude Code + Codex infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows
Agent Usage Guard
93rbartoli/agent-usage-guard
Hook mod that pauses subagent fan-out, heavy prompts and retry loops before they burn quota.
Clawd Conduit
174ssssssanjiu/clawd-conduit
Full-lifecycle wiring between Claude Code and the Clawd on Desk pet — all 15 hook events, with permission prompts answered straight from the desktop
Canny
132qkal/Canny
Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.
Browse the most popular Claude Code mods, all hooks, or the skills and MCP server directories.