ravila4/claude-adhd-skills
73 stars · Last commit 2026-03-01
Claude Code skills and hooks for staying organized with AI agents.
README preview
# 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](https://obsidian.md/) 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](https://github.com/ravila4/obsidian-semantic-search) closes the loop, letting agents search notes by meaning, not just filenames. ## What's in the box ### Skills | Skill | What it does | |-------|-------------| | **daily-journal** | Conversational daily journaling. Asks you about your day instead of generating reports from commit logs. Writes to Obsidian. ([examples](examples/daily-log/)) | | **obsidian-vault** | Vault-aware note management: folder hierarchy, naming conventions, frontmatter, internal linking. | | **nudge** | Time-based reminders that fire on prompt submission. "Stop me at 11" or "remind me about standup in 30m". | | **test-driven-development** | Logic Gate + Iron Rule (based on obra's original Red/Green TDD skill): triage what needs tests, then strict test-first for anything with logic. (Just good general development practices, but mentioned in my CLAUDE.md) | ### Hooks