design-member-protocol
Use for any non-leader agent in a structured design discussion.
Skill by buchananwill
Chalk Labs
Need help deploying design-member-protocol?
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/buchananwill-design-member-protocol
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: design, 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. Checked Oct 25, 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/design-member-protocol
What's inside
- Skill name
design-member-protocol- Description
- Use for any non-leader agent in a structured design discussion. Defines the complete arc from handshake through convergence voting to conclusion, as experienced by a team member.
- License
- MIT
- Instructions
- 52 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Design Member Protocol Complete protocol for a specialist team member in a structured design discussion. You are an advisor — you read, research, and contribute via the channel. You do not lead the discussion. ## Phase 1 — Handshake Post a short hello (1-2 sentences) confirming your role and that you have read the brief. Then **wait for the discussion leader to confirm everyone is present.** Do not launch into analysis until the leader opens the floor. ## Phase 2 — Self-Onboarding The leader will announce an onboarding window (up to 60 seconds). Use this time to research the discussion topic — read code, grep for patterns, build your mental model. You may launch background sub-agents to speed up research if the scope merits it. Post **"Ready."** when you are done. Wait for the leader to open the floor. ## Phase 3 — Core Discussion The leader will open the floor and direct questions at specific members. - When the leader directs a question at you, respond promptly — even if only to say you need a moment. - Between turns, do your own research. Read code, investigate questions raised in discussion, build evidence for your positions. Use your tools to ground every contribution. - If you need to do deep research mid-discussion, launch background sub-agents so you remain available for the read-and-reply loop. Do not go dark. - Drive the discussion forward with unique, high-quality contributions. Do not repeat what you or others have already said. If a point is settled, move to the next issue. ## Phase 4 — Convergence Voting The leader will announce that a convergence vote is imminent. **Step 1 — Ready check.** Finish any in-flight message, then reply with **"Ready."** and wait. Do not send any other messages until the vote is opened. **Step 2 — Vote.** The leader will post **"Submit convergence votes."** Respond with exactly **one message**: - **Consent** — if you are satisfied that all points on your agenda have been addressed. - **Dissent** — if you have unraised points or need more discussion. State your reasons concisely. Do not submit more than one message per vote. **If the vote fails:** the discussion re-enters Phase 3. The floor is yielded to dissenting members — if you dissented, this is your opportunity to raise the points you held back on. **If all votes are exhausted** (the leader will inform you): the discussion concludes with divergence recorded. This is a valid outcome — not every discussion converges. ## Phase 5 — Conclusion The leader will invite you to make a **final statement** (one message). This is your last opportunity to register a position. After all final statements, the leader drafts the deliverable and signals **"DISCUSSION CONCLUDED."** ## Exit Condition The ONLY exit signal is the discussion leader posting a message containing the exact phrase **"DISCUSSION CONCLUDED"**. Do not exit for any other reason. Do not exit because you feel your work is done, because the conversation has gone quiet, or because you have said everything you want to say. The leader decides when the session ends. ## Workspace - You cannot edit existing project files. You may create scratch files in your workspace for your own notes. - Other team members cannot see files you create. Never rely on file-based handoffs.
From buchananwill/ue-claude-scaffold, MIT.
More from buchananwill/ue-claude-scaffold
- 0.507score
action-boundary
buchananwill
Use when an agent must enforce strict role boundaries — what actions are valid, what is out of scope.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
arbitration-protocol
buchananwill
Use when an agent is the FSM arbitrator on a durable task.
SkillCFreshness: C★ 2Claude Code +9 - 0.443score
browser-web-hygiene
buchananwill
React-agnostic web safety checklist for any code that renders in a browser.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
audit-matrix-schema
buchananwill
Use when an audit deliverable must cross-reference two project axes as a bipartite graph.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
audit-protocol
buchananwill
Use when an agent must audit a codebase area and produce documentation.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
commit-discipline
buchananwill
Use for any agent with write access inside a Docker container.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
content-catalogue-dashboard-system-wiring
buchananwill
Agent resolution table, working-scope declaration, and review mandates for the content-catalogue-dashboard orchestrator running inside a Docker container…
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
debrief-protocol
buchananwill
Use for any agent that writes code and must produce a work audit before building.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
design-leader-protocol
buchananwill
Use for any agent that leads a multi-agent design or cleanup session.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
chat-etiquette
buchananwill
Use for any agent that communicates with other agents or the user via a chat channel.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
cleanup-session-protocol
buchananwill
Use for the cleanup session leader.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
container-build-routing
buchananwill
Use for any agent running inside a Docker container that needs to trigger Unreal Engine builds or tests.
SkillDFreshness: D★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 1, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from buchananwill
- 0.507score
arbitration-protocol
buchananwill
Use when an agent is the FSM arbitrator on a durable task.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
action-boundary
buchananwill
Use when an agent must enforce strict role boundaries — what actions are valid, what is out of scope.
SkillCFreshness: C★ 2Claude Code +9 - 0.443score
browser-web-hygiene
buchananwill
React-agnostic web safety checklist for any code that renders in a browser.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
audit-protocol
buchananwill
Use when an agent must audit a codebase area and produce documentation.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
audit-matrix-schema
buchananwill
Use when an audit deliverable must cross-reference two project axes as a bipartite graph.
SkillDFreshness: D★ 2Claude Code +9 - 0.440score
chat-etiquette
buchananwill
Use for any agent that communicates with other agents or the user via a chat channel.
SkillDFreshness: D★ 2Claude 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 design-member-protocol 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
design-member-protocol skill. Agent Mart. https://agentmart.dev/skills/buchananwill-design-member-protocol (last updated 2026-10-24)