mc-ui-sprint
Run the UI sprint for a release or epic with the human, the one session they sit in.
Skill by lokkrish
Chalk Labs
Need help deploying mc-ui-sprint?
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-ui-sprint
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: documents, design, backend, data
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-ui-sprint
What's inside
- Skill name
mc-ui-sprint- Description
- Run the UI sprint for a release or epic with the human, the one session they sit in. Build clickable screens with fake data, iterate on their feedback, then lock the screens and derive the API contract from them.
- License
- MIT
- Instructions
- 20 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# UI sprint (with the human) This is the part of the process where the human is present. Keep every message short and visual: show screens, not paragraphs. 1. **Scope.** List the release's (or epic's) screens and the navigation between them in one short message, e.g. `Sign-up → Tasks (empty) → New task → Tasks (filled)`. Ask the human to confirm or adjust. This is the only planning question. Then record each screen with `mc_screen`: its route, the stories and UX requirements it implements, and its mockups, and name it in the refs of the UI tickets that build it (`SCR-n`). 2. **Build the prototype** (you, or the UX and frontend agents via `/mc-start`): - real screens in the app's stack, running locally, on hard-coded fake data and a mock API client - add the feedback widget in development only: `<script src="http://127.0.0.1:4317/widget.js" defer></script>` (Next.js: in the root layout behind `process.env.NODE_ENV === 'development'`; Expo web: in `app/+html.tsx`) - use the integration ports (`npx madcompany env integration`) so HQ's Preview shows it 3. **Show it.** Tell the human to open HQ → Preview (or the app URL, or Expo Go on their phone), or a mockup in HQ → Library. They click **Comment** on any element, click on a mockup image, or **Sketch** (capture the screen and draw on it). Each comment lands on its screen and is either sent now or added to their review. Comments sent now: classify each (`mc_map_change` with `level` element, ux or story, and for ux or story what it amends or extends) before it's fixed. A submitted review: `/mc-review-feedback`, one plan for all of it, approved by the human. Fix in rounds and take screenshots after each round (`mc_attach` to the feedback tickets). 4. **Sign-off.** When the human approves: - log it: `mc_decide` titled `UI signed off: <release or epic>`, with links to the screenshots - record the session: run `/mc-minutes` (kind `ui-sprint`), so what the human asked for is in HQ → Library → Meetings - write the API contract the screens need to `docs/design/<area>/api.md` (OpenAPI, or a table of endpoints with request and response shapes) with `mc_design_write`, listing the backend and frontend agents as consumers - update the tickets: UI tickets now wire the real contract; backend tickets implement it. In UI-MVP mode that wiring is the next release (R2): plan it with `/mc-plan-release` 5. Hand over to the team with `/mc-start`. From here the human is only asked about decisions that are theirs. For a release or epic **without UI** (MVP mode), don't run this. Build the thinnest end-to-end slice first, show it through an API explorer (Swagger UI) or a CLI run, and revise from the human's feedback.
From lokkrish/madcompany, MIT.
More from lokkrish/madcompany
- 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-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 - 0.579score
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 - 0.579score
mc-staff
lokkrish
Set up or change the madcompany team.
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-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 - 0.579score
mc-end-day
lokkrish
End 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-ui-sprint 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-ui-sprint skill. Agent Mart. https://agentmart.dev/skills/lokkrish-mc-ui-sprint (last updated 2026-10-24)