Chalk Labs
Need help deploying mc-staff?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lokkrish-mc-staff
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/mc-staff
What's inside
- Skill name
mc-staff- Description
- Set up or change the madcompany team. Choose roles, domain expertise and models for this app, write .madcompany/team.yaml, and generate one Claude Code subagent per member.
- License
- MIT
- Instructions
- 11 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Staff the team 1. Read the BMad architecture and PRD (usually in `_bmad-output/planning-artifacts/`) and the current `.madcompany/team.yaml`. 2. Propose a team in **one short table**: id, `type` (a role from the catalogue: product-manager, ux-designer, ui-designer, architect, web-developer, mobile-developer, backend-developer, database-engineer, data-engineer, qa-engineer, security-engineer, devops-engineer, tech-writer), main domain (specific to this app, e.g. "Expo screens, offline sync", not just "frontend"), secondary domain, model. Always include one lead (the human's main session), and usually a QA reviewer. Suggest `max_parallel` (3 is a good start on a Claude plan). 3. Ask the human to confirm or change it. The human decides the headcount. If they'd rather start from a template, run `npx madcompany staff --template small|medium|large` (5, 10 or 20 people) and then tailor each member's `domain` to this app. 4. Write `.madcompany/team.yaml`. Keep the project `key`, `checks` (the repo's real typecheck/lint/test commands) and `ports`. Use a stronger model for the lead and architecture-heavy roles, and a cheaper one for QA and routine work. 5. **Tools.** Call `mc_tools` (as: "lead"). Tell the human in one line which MCP servers and plugins the team will use and who gets which (e.g. "QA uses Playwright; designers use Figma"). If a server that would clearly help is missing (HQ → Tools lists suggestions), offer to file it as Human help; adding a server is theirs to do. Put any assignment the defaults don't cover under `tools.assign` in `team.yaml`. 6. Run `npx madcompany staff`. It writes `.claude/agents/mc-<id>.md` for every member except the lead, plus their identity and memory files, and removes agents that left the team. 7. Tell the human: restart Claude Code once so the new agents load, then `/mc-plan-epic`. They can change any agent's model, hire or remove agents later in HQ → Team, and change the lead's model with `/model`. To bring teammates or a client into HQ, see `npx madcompany people add` and `npx madcompany hq --share`.
From lokkrish/madcompany, MIT.
More from lokkrish/madcompany
- 0.587score
mc-plan-release
lokkrish
Plan the next madcompany release (R1, R2…) in UI-driven, MVP-driven, UI-MVP or brownfield mode.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
mc-plan-epic
lokkrish
Spec-driven mode.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
mc-scan
lokkrish
Onboard madcompany onto an existing codebase (brownfield mode).
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
mc-start
lokkrish
Start the madcompany workday.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
mc-minutes
lokkrish
Write the minutes of this conversation into madcompany HQ, with its key points, decisions, action items, open questions and links.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
mc-ui-sprint
lokkrish
Run the UI sprint for a release or epic with the human, the one session they sit in.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
mc-end-day
lokkrish
End the madcompany workday.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
mc-setup
lokkrish
Install madcompany in this project after adding it as a BMad module or Claude Code plugin.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
mc-stop
lokkrish
Stop every madcompany agent now.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 25, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/lokkrish/madcompany
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lokkrish
- 0.587score
mc-plan-epic
lokkrish
Spec-driven mode.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
mc-plan-release
lokkrish
Plan the next madcompany release (R1, R2…) in UI-driven, MVP-driven, UI-MVP or brownfield mode.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
mc-scan
lokkrish
Onboard madcompany onto an existing codebase (brownfield mode).
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
mc-minutes
lokkrish
Write the minutes of this conversation into madcompany HQ, with its key points, decisions, action items, open questions and links.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
mc-ui-sprint
lokkrish
Run the UI sprint for a release or epic with the human, the one session they sit in.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
mc-start
lokkrish
Start the madcompany workday.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get mc-staff running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
mc-staff skill. Agent Mart. https://agentmart.dev/skills/lokkrish-mc-staff (last updated 2026-10-24)