cbc
Drive a chatbotchat (CBC) cross-agent conversation well — open/join a room, exchange substantive messages, and wait via a background poll instead of…
Skill by Levezze
Chalk Labs
Need help deploying cbc?
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/levezze-cbc
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: 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/cbc
What's inside
- Skill name
cbc- Description
- Drive a chatbotchat (CBC) cross-agent conversation well — open/join a room, exchange substantive messages, and wait via a background poll instead of babysitting the loop. Enforces the discipline that makes CBC work — one identity across join/send/poll, re-ground from the room (not memory) before every reply, and interpose the user on decisions they own. Use when the user invokes `/cbc`, pastes a bare room id shaped like `slug-YYYYMMDD-HHMM`, or asks to talk to or coordinate with an agent in another repo or session.
- License
- unknown
- Instructions
- 293 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from Levezze/devkit
- 0.539score
pr-review
Levezze
Diligent end-of-cycle PR review gate.
SkillBFreshness: B★ 1Claude Code +9 - 0.531score
ask
Levezze
Answer questions without writing code to the codebase.
SkillBFreshness: B★ 1Claude Code +9 - 0.531score
document
Levezze
Create technical documentation using the documentation-scholar subagent.
SkillBFreshness: B★ 1Claude Code +9 - 0.492score
documentation-pass
Levezze
Holistic documentation audit.
SkillCFreshness: C★ 1Claude Code +9 - 0.492score
e2e-playwright-test
Levezze
LLM-piloted end-to-end smoke against a deployed app.
SkillCFreshness: C★ 1Claude Code +9 - 0.492score
ddd
Levezze
Design-Driven Development — visual checklist verification loop for UI work.
SkillCFreshness: C★ 1Claude Code +9 - 0.492score
design-system
Levezze
Bootstrap or audit a centralized design system (Tailwind v4 + shadcn).
SkillCFreshness: C★ 1Claude Code +9 - 0.492score
fix-pr-review
Levezze
Reconcile and apply fixes from my own /pr-review output plus any external PR reviews.
SkillCFreshness: C★ 1Claude Code +9 - 0.492score
handoff
Levezze
Generate a handoff document from the requesting side's perspective to another team, repo, or agent.
SkillCFreshness: C★ 1Claude Code +9 - 0.492score
handoff-reply
Levezze
Read new messages in a `/handoff-chat` file from other agents and prepare a reply — but before writing, surface anything that needs the user's judgment as a…
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
merge-pr
Levezze
Merge a PR to main with the full pre/post-merge gate (CI check, post-merge migrate+seed if needed, deploy wait, deployed smoke/e2e).
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
evaluate
Levezze
Post-implementation review — summarizes what was built, then quizzes you on design decisions and tradeoffs.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 17, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/Levezze/devkit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Levezze
- 0.539score
pr-review
Levezze
Diligent end-of-cycle PR review gate.
SkillBFreshness: B★ 1Claude Code +9 - 0.531score
ask
Levezze
Answer questions without writing code to the codebase.
SkillBFreshness: B★ 1Claude Code +9 - 0.531score
document
Levezze
Create technical documentation using the documentation-scholar subagent.
SkillBFreshness: B★ 1Claude Code +9 - 0.492score
design-system
Levezze
Bootstrap or audit a centralized design system (Tailwind v4 + shadcn).
SkillCFreshness: C★ 1Claude Code +9 - 0.492score
ddd
Levezze
Design-Driven Development — visual checklist verification loop for UI work.
SkillCFreshness: C★ 1Claude Code +9 - 0.492score
e2e-playwright-test
Levezze
LLM-piloted end-to-end smoke against a deployed app.
SkillCFreshness: C★ 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 cbc 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
cbc skill. Agent Mart. https://agentmart.dev/skills/levezze-cbc (last updated 2026-10-24)