Skip to main content
command CX Codex

create-command · eugeniughelbur — Claude Code command: what it does, how to install

create-command scaffolds a new slash command for Obsidian through an interactive interview, removing the need to write Markdown or frontmatter by hand.

MIT ★ 5,412 updated 2026-10-24

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add eugeniughelbur/obsidian-second-brain
/plugin install obsidian-second-brain@obsidian-second-brain
Open on GitHub

What create-command does

This command automates drafting new workflows for obsidian-second-brain. Rather than copying existing files or filling out templates manually, it collects requirements one step at a time via AskUserQuestion. When given a rich task description right away, it switches to a fast path that creates a spec draft and requests a single confirmation.

The routine validates the target kebab-case name against ^[a-z][a-z0-9-]*$, assigns a category (vault, thinking, research, or meta), collects triggers, and structures a 3-5 step plan. If the new command writes to the vault, it appends the AI-first rules from references/ai-first-rules.md. For external integrations like Perplexity Sonar or xAI Grok, it references keys from ~/.config/obsidian-second-brain/.env. Without the AskUserQuestion tool available, the interactive interview cannot run.

What it helps with

  • Scaffold a new slash command file without manual Markdown editing
  • Define trigger phrases and command categories interactively
  • Validate command naming conventions to prevent file overwrites
  • Enforce AI-first rules for commands that write notes to the vault

Example prompts for the agent

  • /create-command
  • /create-command summarize notion pages and save to vault as AI-first notes

How to install create-command

1Plugin marketplace

/plugin marketplace add eugeniughelbur/obsidian-second-brain
/plugin install obsidian-second-brain@obsidian-second-brain

2Manually: put the files in place

.claude/commands/create-command.md

Call it with /create-command. For all projects use ~/.claude/commands/

Questions about create-command

How to install create-command in Claude Code?

Register the marketplace repository with /plugin marketplace add eugeniughelbur/obsidian-second-brain, then run /plugin install obsidian-second-brain@obsidian-second-brain.

What does create-command do?

It interviews you in the session and outputs a structured Markdown command inside commands/ ready for the build pipeline.

How does the fast path trigger?

Supplying a detailed prompt with intent, name, and category skips the full interview, presenting a draft for one-click confirmation.

Source text

create-command.md · MIT
---
description: Create a new obsidian-second-brain command via interview - zero markdown editing required
category: meta
triggers_en: ["create command", "new command", "add a command", "scaffold a command"]
triggers_de: ["erstelle einen Befehl", "neuer Befehl", "Befehl hinzufügen", "Befehl-Gerüst erstellen"]
triggers_es: ["crea un comando", "nuevo comando", "añade un comando", "hazme un comando nuevo", "arma un comando"]
triggers_pt: ["crie um comando", "novo comando", "adicione um comando", "gere um comando"]
triggers_zh: ["创建一个新命令", "新增 Obsidian 命令", "帮我写个命令", "生成命令模板"]
---

Use the obsidian-second-brain skill. Execute `/create-command $ARGUMENTS`:

This command runs a short interview, then writes a new `commands/<name>.md` file that the build pipeline picks up automatically. The user never touches frontmatter, never edits a template, and never copies an existing command file.

**Hard rule:** You MUST use the AskUserQuestion tool for every question in this flow. ONE question per call. Wait for the answer before the next question. Do not batch.

The optional argument is a free-text seed describing what the command should do (e.g., `summarize my notion pages and save to vault`). If given, use it to pre-fill suggestions in the interview. If empty, the first question opens with "what problem do you want to solve?".

### Fast path (skip the interview when the seed already answers it)

If the seed argument is detailed enough to fill every field yourself - the intent is clear AND you can confidently derive a name, category, trigger phrases, the step outline, and whether it writes to the vault - do NOT run the six-question interview. Instead:

1. Draft the complete spec (name, category, triggers, 3-5 steps, vault-write yes/no) from the seed.
2. Present it in ONE AskUserQuestion tool call as a single confirm-or-adjust gate: option A "Create it as specced" (show the name + one-line behaviour), option B "Let me adjust" (falls back to the full interview). Include the proposed name in the option label so the user sees it.
3. On "Create it as specced", validate the name (Phase 2 checks: regex `^[a-z][a-z0-9-]*$`, and `commands/<name>.md` does not already exist), then jump straight to Phase 8 (generate the file) and Phase 9 (confirm).

Only the truly under-specified seeds need the full interview. A seed like "summarize my notion pages and save to vault as AI-first notes, call it obsidian-notion, research category" is enough to fast-path. When in doubt, run the interview - one confirmation is fine, but never invent behaviour the seed did not state (see the anti-fabrication rule).

---

## Phase 1 - Intent

Ask ONE question via the AskUserQuestion tool:

> "What problem do you want this new command to solve?" (free text)

Read the answer. Confirm understanding back in one sentence before proceeding.

---

## Phase 2 - Naming

From the intent, propose 3 candidate kebab-case names. Names should be lowercase, hyphenated, and start with `obsidian-` (vault-management commands) OR a topic prefix (research toolkit uses `research-*`, social uses `x-*`/`brand-*`) OR just a verb (`create-*`, `import-*`).

Use the AskUserQuestion tool (single-select) with 3 options plus "Other" implicit:

> "Which name should I use?"
> - `<candidate-1>`
> - `<candidate-2>`
> - `<candidate-3>`

After the user picks, validate:
1. Check that `commands/<name>.md` does NOT already exist (use Read; if it succeeds, the name is taken - go back and re-ask)
2. Confirm the name passes the regex `^[a-z][a-z0-9-]*$`

---

## Phase 3 - Category

Ask via the AskUserQuestion tool (single-select, 4 options):

> "Which category does this command belong to?"
> - `vault` - daily writing, capture, find (note creation, retrieval, kanban)
> - `thinking` - synthesis, decisions, learning, reviews
> - `research` - bring external sources into the vault
> - `meta` - vault setup, health, structure, tooling

---

## Phase 4 - Trigger phrases

Generate 3-5 natural-language trigger phrases the user might say to invoke this command (not slash-form). Examples from existing commands: `"save this"`, `"deep research"`, `"weekly review"`. Avoid duplicating triggers already used by other commands (read all `commands/*.md` frontmatter `triggers_en:` once and warn on collisions).

Ask via the AskUserQuestion tool (free text, default to your suggested set):

> "Trigger phrases the user might say to fire this command, comma-separated:"
> Default: `<suggestion-1>, <suggestion-2>, <suggestion-3>`

---

## Phase 5 - Behavior outline

Ask via the AskUserQuestion tool (free text):

> "Describe what the command does in 3-5 numbered steps. Plain English, no code."

Use the answer as the spine of the command body.

---

## Phase 6 - Vault writes? (AI-first compliance gate)

Ask via the AskUserQuestion tool (single-select):

> "Does this command write notes to the user's Obsidian vault?"
> - `yes` - output must apply the AI-first rule (frontmatter, preamble, wikilinks)
> - `no` - read-only, informational, or external-write only

If `yes`: the generated command body MUST end with the AI-first rule footer (see Phase 8).

---

## Phase 7 - External APIs?

Ask via the AskUserQuestion tool (multi-select):

> "Does this command call any external APIs?"
> - Perplexity Sonar (web research)
> - xAI Grok (X posts, x_search tool)
> - YouTube Data API
> - Other (free text)
> - None - purely operates on the vault and conversation

If any are selected, the generated body should include a setup line referencing `~/.config/obsidian-second-brain/.env` and the relevant key (e.g., `PERPLEXITY_API_KEY`).

---

## Phase 8 - Generate the file

Build the new command file. The exact format MUST be:

```
---
description: <one-line, sentence-case, ends without period>
category: <vault | thinking | research | meta>
triggers_en: ["<trigger 1>", "<trigger 2>", "<trigger 3>"]
triggers_es: ["<disparador 1>", "<disparador 2>"]
---

Use the obsidian-second-brain skill. Execute `/<name> $ARGUMENTS`:

<one-sentence framing tying the user's intent (Phase 1) to the action>

1. Read `_CLAUDE.md` first if it exists in the vault root
2. <step from Phase 5, step 1>
3. <step from Phase 5, step 2>
4. <step from Phase 5, step 3>
5. <step from Phase 5, step 4 if present>
6. <step from Phase 5, step 5 if present>

<closing one-liner explaining why this matters>

---

<AI-first footer ONLY if Phase 6 = yes>
**AI-first rule:** Every note created or updated by this command MUST follow `references/ai-first-rules.md` - `## For future agent` preamble, rich frontmatter (`type`, `date`, `tags`, `ai-first: true`, plus type-specific fields), recency markers per external claim, mandatory `[[wikilinks]]` for every person/project/concept referenced, sources preserved verbatim with URLs inline, and confidence levels where applicable. If that path does not resolve from your working directory, search upward for it; if you still cannot read it, say so before writing rather than producing a note that silently skips the rule. The vault is for future agent retrieval - not human reading.
```

Write the file to `commands/<name>.md` using the Write tool.

---

## Phase 9 - Confirm + next steps

Show the user the absolute path of the file you just wrote. Then surface the three follow-up actions:

1. **Build** - `bash scripts/build.sh` will recompile every platform (`dist/claude-code/commands/<name>.md`, plus the per-platform outputs: native Agent Skills + `AGENTS.md` trigger reference for Codex, routing tables in `GEMINI.md` / OpenCode's `AGENTS.md`)
2. **Install** - for Claude Code users who symlink, the new command appears automatically on next session. For other platforms, copy `dist/<platform>/` into the vault.
3. **Iterate** - open the file, refine steps, commit. Or rerun `/create-command` to add a sibling command.

If the new command writes to the vault and the user has the validate-ai-first hook installed, remind them that the validator will warn on missing preamble/frontmatter - that's expected; just follow the AI-first rule in the command's own logic.

---

**Why this matters:** Most "no-code" frameworks fail because they make the user fill out a form. This command treats the conversation itself as the form. Six questions, one file, zero markdown editing. Lowers the contribution bar so anyone can extend the skill - and every command added through this flow lands AI-first-compliant by construction.

---

**Note for future agent:** This is a command that creates commands. Do not run it recursively on itself. Do not rewrite this file when invoked - write a NEW `commands/<name>.md` based on the interview.

**Anti-fabrication:** Search exhaustively before claiming any note, person, or file is absent - false absence is the most common failure mode - and never invent facts, entities, or dates (mark unknowns as `TBD`). See the anti-fabrication and search-completeness hard rules in `references/ai-first-rules.md`.

© Eugeniu Ghelbur · MIT · eugeniughelbur/obsidian-second-brain

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

create-command by other authors comes first.

From the same set51

The whole set →
obsidian-distill obsidian-distill condenses a long note or article into key claims, each tagged with the exact source block it came from — paragraph, section, or timestamp. CX Codex +1 ★ 5,412repo stars obsidian-merge obsidian-merge merges near-duplicate Obsidian notes without deleting files. It preserves links, unions frontmatter, and converts the retired note into a redirect stub. CX Codex +1 ★ 5,412repo stars obsidian-checkin The obsidian-checkin command asks the vault owner to confirm aging facts in notes and records their replies. Use it to review details about people or projects that may have changed. CX Codex +1 ★ 5,412repo stars research-deep research-deep scans your Obsidian vault to map what you already know, identifies missing or stale information, fills gaps via Perplexity or Grok, synthesizes the findings, and updates your notes on people, projects, and ideas automatically. CX Codex +1 ★ 5,412repo stars obsidian-init obsidian-init scans an Obsidian vault and creates _CLAUDE.md, index.md, and a log pointer. Use it to prepare vault guidance and a note catalog for Claude. CX Codex +1 ★ 5,412repo stars obsidian-health obsidian-health scans your Obsidian vault for contradictions, concept gaps, stale claims, and structural issues. Reports findings grouped by severity and spins up specialized agents to triage each category. CX Codex +1 ★ 5,412repo stars obsidian-calendar obsidian-calendar connects an Obsidian vault to Google Calendar across four modes: agenda snapshots, task reconciliation, meeting notes, and event scheduling. CX Codex +1 ★ 5,412repo stars obsidian-ingest The obsidian-ingest command brings a source or folder batch into an Obsidian vault, updates entities, and reconciles conflicting concepts. Use it for research intake. CX Codex +1 ★ 5,412repo stars

Project sponsors

Companies that keep this analytics open