Run any Skill in Manus with one click

swarm-onboard

Stars0

Forks0

UpdatedJuly 15, 2026 at 16:17

Set up a new project on Swarm — create its channel and seed it with intelligence records. Use when connecting a repository to Swarm for the first time, or when the user asks to onboard, initialize, or set up a project on Swarm.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

builtbyberry

builtbyberry/swarm-platform-claude-plugin

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	swarm-onboard
description	Set up a new project on Swarm — create its channel and seed it with intelligence records. Use when connecting a repository to Swarm for the first time, or when the user asks to onboard, initialize, or set up a project on Swarm.

Onboard a project to Swarm

Onboarding creates ONE new channel and seeds it from the repository in front of you. It never reads from, adopts, or inherits the workspace of another channel.

The onboarding ritual is:

Take the user's intent literally. If they named the channel and/or workspace, use those verbatim — do not rename, fuzzy-match, or substitute a similar existing channel.
Call list_channels only to guard against an exact duplicate: a channel whose key is the slug of this channel's name in the same target workspace. A similar or shorter name (e.g. acme vs acme-billing) is a different project — ignore it. Never call get_context_for_injection on another channel during onboarding, and never inherit its workspace.
Distill the repository into atomic, typed intelligence records.
Pick the target workspace: use the one the user named; otherwise, if they belong to more than one, ask — never guess or borrow another channel's workspace.
Call the onboard_project tool to create the channel and seed it with those records.
Bind this project to the channel so future conversations pick it up automatically: add a  line to the project's own instructions file (CLAUDE.md, AGENTS.md, a .cursor/rules/*.mdc file — whichever this client uses; create one if none exists). This is a hard step, not optional.

If you are unsure about the channel name or the workspace, ask the user before calling onboard_project rather than assuming and continuing.

If your client surfaces MCP prompts, the onboard-project prompt walks this same ritual interactively and is the canonical, server-rendered source — prefer it when it is available. Some clients do not expose MCP prompts; when the prompt is not available, follow the steps above directly (they call the same onboard_project tool).

After onboarding, treat the channel as the project's shared memory: load it at the start of each task with get_context_for_injection, and checkpoint at the end per the channel's capture mode.

More from this repository

same repository

swarm-checkpoint

builtbyberry/swarm-platform-claude-plugin

Checkpoint the current conversation back to its Swarm channel. Use ONLY when the user explicitly asks to checkpoint, share, or save their work to Swarm — never invoke automatically, because sharing is gated on the channel's capture mode and the user's intent.

2026-07-180

swarm-context-bus

builtbyberry/swarm-platform-claude-plugin

Use when working in a project connected to Swarm, a shared context bus over MCP. At the start of a task, load shared context with get_context_for_injection; at meaningful checkpoints, share back per the channel's capture mode. Triggers whenever the Swarm MCP tools (get_context_for_injection, capture_context, share_session, list_channels) are available.

2026-07-160

swarm-curate

builtbyberry/swarm-platform-claude-plugin

Turn working context into durable channel canon — promote or create records, link them, and supersede replaced ones. Use when the user asks to curate, record, promote, or save findings as Swarm records, or to relate or supersede existing records.

2026-07-150

swarm-load

builtbyberry/swarm-platform-claude-plugin

Load shared Swarm context for the active channel. Use at the start of a task in a Swarm-connected project, or whenever the user asks to load or refresh Swarm context.

2026-07-150

swarm-project

builtbyberry/swarm-platform-claude-plugin

Work the produce-loop on a Swarm Project. Use when the user asks you to work on their Swarm project, address or review the change requests (recommendations) on a Swarm Project, or produce the changes a human has recommended — you author the edits to the Project's Artifacts and open a review gate for a human to approve. Scoped to a Swarm Project (channel + slug), not any local project folder.

2026-07-130

swarm-handoff

builtbyberry/swarm-platform-claude-plugin

Hand off curated context to another person or agent with a Swarm handoff bundle. Use when the user asks to hand off, transfer, or package context for a teammate or successor, or to inspect or acknowledge a handoff bundle.

2026-07-010

name	swarm-onboard
description	Set up a new project on Swarm — create its channel and seed it with intelligence records. Use when connecting a repository to Swarm for the first time, or when the user asks to onboard, initialize, or set up a project on Swarm.

Onboard a project to Swarm

Onboarding creates ONE new channel and seeds it from the repository in front of you. It never reads from, adopts, or inherits the workspace of another channel.

The onboarding ritual is:

Take the user's intent literally. If they named the channel and/or workspace, use those verbatim — do not rename, fuzzy-match, or substitute a similar existing channel.
Call list_channels only to guard against an exact duplicate: a channel whose key is the slug of this channel's name in the same target workspace. A similar or shorter name (e.g. acme vs acme-billing) is a different project — ignore it. Never call get_context_for_injection on another channel during onboarding, and never inherit its workspace.
Distill the repository into atomic, typed intelligence records.
Pick the target workspace: use the one the user named; otherwise, if they belong to more than one, ask — never guess or borrow another channel's workspace.
Call the onboard_project tool to create the channel and seed it with those records.
Bind this project to the channel so future conversations pick it up automatically: add a  line to the project's own instructions file (CLAUDE.md, AGENTS.md, a .cursor/rules/*.mdc file — whichever this client uses; create one if none exists). This is a hard step, not optional.

If you are unsure about the channel name or the workspace, ask the user before calling onboard_project rather than assuming and continuing.

After onboarding, treat the channel as the project's shared memory: load it at the start of each task with get_context_for_injection, and checkpoint at the end per the channel's capture mode.