Slash Command83 repo starsupdated 9d ago

write

The /write slash command launches a coordinated agent team optimized for writing projects. Use this when you need multiple specialized agents working together on content creation, with options to configure the team tier (Ultra for reliability or Balanced for cost), set writing outcomes through guided questions, and optionally enable research capabilities. The command streamlines setup by offering preset configurations or step-by-step customization before deploying the agent team.

View source Repository: swarms

Install in Claude Code

Copy

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/DheerG/swarms/HEAD/commands/write.md -o ~/.claude/commands/write.md

Then start a new Claude Code session; the slash command loads automatically.

Definition

write.md

# /swarm:write

Read `${CLAUDE_PLUGIN_ROOT}/commands/launch.md` for Step 0 (pre-flight), Step 1 (hard rules), and Step 8 (launch). This command replaces Steps 2–7.

**No lead research unless enabled.** Unless the user explicitly enables lead research, do not read codebase files, spawn subagents, or perform research. Delegate all research to teammates.

## Settings

- **Mode:** Writing
- **Outcomes question:** "What are you writing?"
- **Defaults:** suggest-members (Writing mode), tier picked at setup (Ultra recommended), no lead research

## User-Provided Context

$ARGUMENTS

## Workflow

1. **Setup.** AskUserQuestion — "How would you like to set up the team?" Options: "Defaults — Ultra (Recommended)" (auto-configure mode/team/research; full team on the stronger model — reliable rule-following) / "Defaults — Balanced" (same auto-config; cheaper model for members — lower cost, less reliable rule-following) / "Configure each step" (choose mode, team, tier, research individually).
2. **Outcomes.** If User-Provided Context is non-empty, use as outcomes. Otherwise ask the outcomes question (plain text, not AskUserQuestion). Do NOT echo the outcomes back verbatim — run the outcome reflection instead: You MUST use the **Skill** tool to invoke `swarm:reflect-outcome` with the user's exact words as `args`, and do not author its wording yourself. If it returns `NO FORK` (the common case), show nothing — no echo, no confirmation beat — and carry the outcome forward to the Step 7 team-plan summary, where it is restated (that is where the user sees their words carried forward). If it returns a ready-to-render fork, present it with AskUserQuestion exactly as returned (transport it, do not reword the question or labels) and resolve the user's pick per the skill — Option A keeps their wording, Option B re-authors into a new verbatim. Store no separate supplement. The user's verbatim words are still captured for the Step 8 briefs (launch.md verbatim-capture rule); the user can still adjust at Step 7.
3. **Team configuration.** Defaults path (either Defaults option): apply the defaults above with the tier set to the option picked (Ultra or Balanced), and immediately proceed to step 4 in the same response — do not pause for user input. Configure path: follow launch.md Steps 4–6, then step 4.
4. **Confirmation.** Follow launch.md Step 7. Mode is Writing.
5. **Launch.** Follow launch.md Step 8.