From chief-of-staff-kit
Install and customise a team of AI agents (a chief-of-staff orchestrator that routes to division leads and specialists) into the user's own project or global config. Interviews the user about their business, departments, teams, products, or the people they manage — or reads their existing CLAUDE.md / AGENTS.md — then renders a tailored crew for Claude Code and/or Codex. Use when the user wants to "install the crew", "set up the agent team", "build my chief of staff", "scaffold agents for my business", or runs this kit for the first time.
How this skill is triggered — by the user, by Claude, or both
Slash command
/chief-of-staff-kit:install-crewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill turns a set of generic agent templates into a **customised team of agents
references/rendering-claude-code.mdreferences/rendering-codex.mdreferences/team-readme-template.mdtemplates/comms/email-writer.mdtemplates/comms/inbox-reader.mdtemplates/comms/memory-harvester.mdtemplates/comms/notes-archivist.mdtemplates/division-lead.mdtemplates/orchestrator.mdtemplates/specialists/code-auditor.mdtemplates/specialists/cto-architect.mdtemplates/specialists/growth-marketer.mdtemplates/specialists/ops-steward.mdtemplates/specialists/presentation-writer.mdtemplates/specialists/problem-solver.mdtemplates/specialists/product-designer.mdtemplates/specialists/program-manager.mdtemplates/specialists/voice-scriptwriter.mdThis skill turns a set of generic agent templates into a customised team of agents for the person installing it — wired to their org, their house style, their tools.
The team is one shape, instantiated to fit anyone:
chief-of-staff ← orchestrator: triages, routes, synthesises
┌───────────────┼───────────────┐
lead A lead B lead C ← one "lead" per division (see below)
└───────────────┼───────────────┘
(any lead pulls in any specialist)
architect · code-auditor · program-manager · problem-solver
presentation-writer · voice-scriptwriter · growth-marketer
product-designer · ops-steward ← shared specialists
inbox-reader · email-writer · notes-archivist · memory-harvester ← opt-in comms
A "division" is deliberately abstract. For the installing user it might be a business, a department, a team, a product line, a client portfolio, or a person they manage. The installer's job is to learn what their divisions are and generate one lead per division.
Your job when this skill runs: conduct a short interview (informed by anything already in their config), confirm a plan, then write the agent files. Never invent the user's business facts — ask, or leave a clean placeholder and say so.
templates/orchestrator.md — the chief-of-staff template.templates/division-lead.md — ONE lead template, instantiated once per division.templates/specialists/*.md — the 9 generic specialists.templates/comms/*.md — the 4 integration-dependent agents (opt-in).references/rendering-claude-code.md — how to write Claude Code subagents.references/rendering-codex.md — how to write Codex prompts + AGENTS.md.references/team-readme-template.md — the team README the installer writes for the user.Read the relevant rendering reference before you write files. Read each template before you fill it.
Ask which the user runs (offer both):
references/rendering-claude-code.md).AGENTS.md
(references/rendering-codex.md). Note honestly: Codex has no auto-orchestrating
subagent system, so in Codex the personas are invoked manually and AGENTS.md
documents the routing doctrine — the content ports, the auto-delegation does not.Look for context the user has already written, and use it to propose a draft org rather than interrogating them from scratch:
~/.claude/CLAUDE.md (and ~/.codex/AGENTS.md if present).CLAUDE.md and/or AGENTS.md.From whatever exists, extract candidate divisions (named businesses, departments, teams, products), the user's house style (language/spelling variant, emoji policy, versioning rules), a default tech stack if mentioned, and any filing conventions. Draft a proposed roster from this. If nothing is found, start clean.
"I read your config and it looks like you run A, B, and C — should each be its own lead? Anything missing?" beats twenty cold questions.
Work through these, conversationally, confirming what you inferred in Step 1. Prefer multiple-choice where you can. Keep it tight.
inbox-reader, email-writer,
notes-archivist, memory-harvester. Only install the ones the user wants, and
for each, capture what integration they'll wire (or note it's unwired).{{WORKSPACE_CONTEXT}}. Do not
assume a variant or an emoji rule — use what they tell you; if they say nothing,
render a neutral block.{{DEFAULT_STACK}}.{{FILING_MAP}}.<workspace>/.claude/agents/) or global
(~/.claude/agents/). See the non-git caveat in the rendering reference and pick
accordingly.Before writing anything, show the user:
Wait for a yes. This is the only gate — once confirmed, write everything.
Follow the rendering reference for each target tool. The mechanics:
templates/division-lead.md and fill its tokens
({{LEAD_NAME}}, {{LEAD_SLUG}}, {{DOMAIN}}, {{WHAT_IT_IS}}, {{OWNS}},
{{DOES_NOT_OWN}}, {{KEY_FACTS}}, {{HANDOFFS}}, {{LEAD_COLOR}}). Give each a
unique kebab-case name (e.g. lead-<slug>).{{DEFAULT_STACK}} (architect) and
{{FILING_MAP}} (ops-steward) where present.{{INTEGRATION_SETUP}}.{{WORKSPACE_CONTEXT}} block into every agent so
the whole crew behaves consistently.templates/orchestrator.md and regenerate {{LEADS_LIST}} and
{{SPECIALISTS_LIST}} from the roster you actually installed — not the full
catalogue.references/team-readme-template.md, filling
{{ROSTER_TABLE}} from the installed files.{{ — a surviving token is a bug; fix
it before finishing.Report what you wrote and where. Then:
@chief-of-staff for anything cross-cutting or
call any agent by name.AGENTS.md.{{WORKSPACE_CONTEXT}}, never in the
frontmatter description (that string is broadly visible).npx claudepluginhub skyremote/chief-of-staff-kit --plugin chief-of-staff-kitComposes and deploys Claude Code Agent Teams by analyzing requirements, auto-selecting skills/agents across scopes, generating task dependency graphs, and orchestrating lifecycle. Use for complex multi-agent tasks with parallel work.
Creates a multi-agent team composition file with purpose definition, member selection, coordination patterns, and registry integration. Use when formalizing recurring collaborative workflows.
Interactive agent selector for composing and dispatching parallel teams. Use when you have multiple agent roles and need to pick a subset for a task.