Chalk Labs
Need help deploying team?
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/jjongguet-team
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: productivity, 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/team
What's inside
- Skill name
team- Description
- Orchestrate parallel tmux workers for a multi-agent team task.
- License
- MIT
- Instructions
- 37 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Team Skill (oh-my-product) Use this skill when the user wants to run a multi-worker team orchestration task. ## What it does Launches `omp team run` with the specified task and worker count, creating a tmux session with N parallel workers. Each worker receives the team context via GEMINI.md and executes the task, then writes a completion signal. ## Usage ``` omp team run --task "<task description>" --workers <N> ``` ## Examples - `omp team run --task "Review all PRs" --workers 3` - `omp team run --task "Run smoke tests" --workers 2` - `omp team run --task "Audit dependencies" --workers 4` ## Orchestration steps 1. Hook system writes team context to `.gemini/GEMINI.md` 2. tmux session is created with N worker panes 3. Each worker runs `omp worker run --team <name> --worker <id>` 4. Workers read context, execute task, write done signal to state 5. Orchestrator polls until all workers complete 6. Results aggregated and displayed ## Acceptance criteria - [ ] tmux session created with N panes - [ ] Each pane executes the worker run command - [ ] Each worker writes a done signal (`.omp/state/team/<name>/workers/<id>/done.json`) - [ ] `omp team status` reflects worker completion
From jjongguet/oh-my-product, MIT.
More from jjongguet/oh-my-product
- 0.519score
design-system
jjongguet
Activate when the user wants to extract, sync, or manage design system tokens.
SkillDFreshness: D★ 99Claude Code +9 - 0.519score
ux-critique
jjongguet
Activate when the user requests a UX review, usability critique, or accessibility audit of a page, component, or user flow.
SkillDFreshness: D★ 99Claude Code +9 - 0.519score
web-design
jjongguet
Activate when the user requests web/UI design work, design briefs, wireframe specs, or wants to create/update a DESIGN.md file.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
ralplan
jjongguet
Iterative planning with structured consensus — planner, architect, and critic converge on an approved plan.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
prd
jjongguet
Transform a request into a measurable PRD with acceptance criteria, non-goals, and constraints.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
review
jjongguet
Perform a structured evidence-based code review with severity ratings.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
handoff
jjongguet
Produce a structured handoff document summarizing completed work and next steps.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
deep-interview
jjongguet
Run a structured Socratic interview to turn ambiguity into an implementation-ready brief.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
context-optimize
jjongguet
Analyze and optimize context for signal-to-noise ratio — deduplicate, compress, prioritize, and prune.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
cost
jjongguet
Summarize token usage and cost-style session metrics across daily, weekly, or monthly windows.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
autopilot
jjongguet
Autonomously drive a feature from clarified objective through implementation and verification.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
cancel
jjongguet
Safely stop active work, note what was interrupted, and preserve resumable context.
SkillDFreshness: D★ 99Claude Code +9
Signals
- Stars
- 99
- Forks
- 22
- Open issues
- 1
- Last commit (this folder)
- Apr 8, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/jjongguet/oh-my-product
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from jjongguet
- 0.519score
web-design
jjongguet
Activate when the user requests web/UI design work, design briefs, wireframe specs, or wants to create/update a DESIGN.md file.
SkillDFreshness: D★ 99Claude Code +9 - 0.519score
ux-critique
jjongguet
Activate when the user requests a UX review, usability critique, or accessibility audit of a page, component, or user flow.
SkillDFreshness: D★ 99Claude Code +9 - 0.519score
design-system
jjongguet
Activate when the user wants to extract, sync, or manage design system tokens.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
cost
jjongguet
Summarize token usage and cost-style session metrics across daily, weekly, or monthly windows.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
autopilot
jjongguet
Autonomously drive a feature from clarified objective through implementation and verification.
SkillDFreshness: D★ 99Claude Code +9 - 0.513score
review
jjongguet
Perform a structured evidence-based code review with severity ratings.
SkillDFreshness: D★ 99Claude 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 team 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
team skill. Agent Mart. https://agentmart.dev/skills/jjongguet-team (last updated 2026-10-24)