Index of every page on this site: llms.txt
All skills
Run it yourself

Set up, audit or open the viewer of a Claude Code "second brain" for any project or area of life - an app, a codebase, a business, research, a book, a job search, a course, a home renovation. Creates a short CLAUDE.md map (150 lines max), a focus file, a decision log, folder rules and grouped skills shaped around the person's own work, so Claude never needs the project re-explained. Use when the user asks to create, start, scaffold or set up a second brain, project memory or CLAUDE.md, or to check/audit/clean up an existing one, or to open, show, view or visualize their second brain (the interactive viewer).

  • 20 files
  • 23.2 KB
  • Updated 2 weeks ago
  • GitHub
Use this Skill: https://skilld.dev/gh/owlinthebarnai/second-brain-kit/second-brain

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

interview.md

≈746 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Interview

Ask all of these in ONE message, numbered, with the default in brackets so the person can answer only what they care about.

  1. What is it? The project or area, in one line. [required]
  2. What does success look like? A goal, a deadline, or "ongoing". [ongoing, no deadline]
  3. What will you keep? The 2-5 kinds of things you create, collect or track. Examples: features, clients, chapters, experiments, applications, recipes, papers, rooms, bugs. [ask again if empty; this is the shape]
  4. What do you do again and again? Tasks you repeat, like "log a work session", "prep for a client call", "review a pull request", "turn a paper into notes", "write the monthly report". [only session close and a review]
  5. How often do you work on it, and how often do you want to step back and review? Daily, weekly, monthly, or no fixed review. [a few sessions a week, review weekly]
  6. Who sees it? Just you, a team, or the public (blog, social media, newsletter)? Under your own name or a pseudonym? [just me]
  7. Money? Costs, budget or revenue to track? [no]
  8. Language and tone for notes and drafts. [English, concise and plain]
  9. Hard rules. Anything Claude must always or never do. [plan before building or spending; never invent data]
  10. Anything private Claude should know but never put in shared files? (It goes in CLAUDE.local.md, which git ignores.) [nothing]

From answers to shape

Answer Becomes
1, 2 CLAUDE.md "What this is" (one line plus goal). No dates if ongoing.
3: each kind of thing an area: a folder named in the person's words (plural, lowercase), with a _template.md for one item. If items of that kind have their own rules, add .claude/rules/<area>.md with paths: ["<area>/**"].
4: recurring tasks skill groups. Group related tasks (2-4 per group) under one entry skill named after the activity: clients, writing, code-review. Each task becomes a playbook. Session close and the review always live in the core rhythm group, so do not duplicate them.
5: review cadence the review playbook in rhythm, and a reviews/ folder named by period (2027-w03.md, 2027-03.md). None = drop reviews/ and the review playbook.
6: team "Always true": who else reads these files. Never put personal notes in shared files.
6: public the publishing module: drafts/ plus .claude/rules/publishing.md with the channels and post format.
6: pseudonym Add to "Always true": never include the owner's name, face, employer, location or personal details in anything public.
7: yes the money module: ledger.md, plus cost lines in session close.
8 CLAUDE.md "Always true": language and tone.
9 CLAUDE.md "Always true", one line each.
10 CLAUDE.local.md only. Never repeat it anywhere else.

Keep it small: 2-5 areas and 0-3 extra skill groups are enough to start. The brain grows through session close, not up front.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at f1b6162. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 2 weeks ago

README badge

README badge for owlinthebarnai/second-brain-kit/second-brain