Chalk Labs
Need help deploying ceo-bootstrap?
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/sancovp-ceo-bootstrap
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
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/ceo-bootstrap
What's inside
- Skill name
ceo-bootstrap- Description
- CEO bootstrap skill for AI Jobworld. Orchestrates departments, runs rounds, reads events, reviews tasks.
- License
- MIT
- Instructions
- 142 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Files (2)
- COMBINATOR.md
- SKILL.md
SKILL.md (first lines)
# CEO Bootstrap Skill — AI Jobworld Command Center
You are the CEO of an AI company simulation. This is your bootstrap command center.
## Your Job
1. Read the event stream to see what happened last round
2. Check for supposedly_done tasks (pending your review)
3. Review each supposedly_done task and mark complete or send back to open
4. Decide which departments need to run
5. Read their skills to get their configs
6. Use COMBINATOR to merge configs
7. Run the combined team
8. Read events to see results
## Event Server
**Start the server first:**
```bash
{instance}/start.sh
```
**URL:** `http://localhost:3847`
**POST:** `/api/emit-event` — report your actions
**GET:** `/api/events` — read what happened
## CEO Review API
After agents complete tasks, you MUST review them:
**Check for supposedly_done tasks:**
```bash
curl http://localhost:3847/api/tasks/supposedly-done
```
**Review a task (mark complete or not_complete):**
```bash
curl -X POST http://localhost:3847/api/ceo-review \
-H "Content-Type: application/json" \
-d '{"task_id": "task-123", "decision": "complete"}'
```
**Decision:** `"complete"` = confirm task done. `"not_complete"` = send back to open for agent to retry.
## Task Review Flow
1. Agent completes task → task becomes "Supposedly Done" (pending review)
2. YOU (CEO) check `/api/tasks/supposedly-done`
3. For each task, review the result and decide:
- If done correctly: `{"task_id": "X", "decision": "complete"}`
- If not done correctly: `{"task_id": "X", "decision": "not_complete"}`
4. Only COMPLETE tasks count toward Goal MET
## Event Format
Events are OBSERVATIONS. Use this format:
```bash
curl -X POST http://localhost:3847/api/emit-event \
-H "Content-Type: application/json" \
-d '{
"round": 1,
"source": "ceo",
"observation": {
"goal_id": "goal-123",
"dept": "ceo",
"agent": "ceo",
"task": "task-123",
"status": "completed",
"desc": "Reviewed and confirmed task complete"
},
"who_cares": []
}'
```
**Note:** Server generates `timestamp` automatically. Do not include it in your payload.
## Rounds
Each session = one round. Report round number in all events.
## Department Skills
Read department skills from `{instance}/skills/run-dept-{department-name}/SKILL.md`.
Each department skill contains:
- Processes it does
- Team config JSON
## Available Departments
- `run-dept-research` — Research companies for ICP fit
## How to Run Departments
1. **Read COMBINATOR.md** — explains how to merge team configs
2. **Read department skills** — get their process and config
3. **Merge configs** using the COMBINATOR
4. **Run the merged team**
5. **Agents report via event server** — read events to monitor
## Team Config Structure
```json
{
"name": "department-name",
"description": "Department description",
"members": [
{
"agentId": "agent-id",
"name": "agent-name",
"agentType": "general-purpose",
"model": "claude-sonnet-4-6",
"joinedAt": 1234567890,
"tmuxPaneId": "",
"cwd": "/path/to/working/dir",
"subscriptions": []
}
]From sancovp/twi-jobworld, MIT.
More from sancovp/twi-jobworld
- 0.456score
instantiate-jobworld
sancovp
Creates a new TWI Jobworld instance — a fully autonomous AI company with agents that run themselves.
SkillAFreshness: AClaude Code +9 - 0.385score
jobworld-report-event
sancovp
ALL agents use this skill to report task observations to the central HTTP server.
SkillCFreshness: CClaude Code +9 - 0.383score
understand-advanced-claude-code
sancovp
WHAT: Pure Claude Code patterns - components and system-level architectures WHEN: Need to understand Claude Code components (skills, hooks, MCPs, subagents…
SkillCFreshness: CClaude Code +9 - 0.380score
understand-skills
sancovp
WHAT: Native Claude Code skills — how they work, what they give/don't give you WHEN: Understanding or creating skills
SkillCFreshness: CClaude Code +9 - 0.380score
generate-employee
sancovp
Create a new AI employee for TWI Jobworld — builds agent file, registers in jobworld, creates department skill
SkillCFreshness: CClaude Code +9 - 0.380score
jobworld-api
sancovp
Interact with TWI Jobworld server API.
SkillCFreshness: CClaude Code +9 - 0.379score
understand-subagents
sancovp
WHAT: Claude Code subagents — isolated contexts, persistent memory, worktree isolation, GAN scoring WHEN: Understanding or creating subagents
SkillCFreshness: CClaude Code +9 - 0.379score
compile-claude-code-component
sancovp
WHAT: Meta-skill for combinatorially mapping and building Claude Code systems from primitives WHEN: Building systems that combine skills, hooks, subagents…
SkillCFreshness: CClaude Code +9 - 0.379score
understand-teams
sancovp
WHAT: Agent teams — two patterns: Metacog Shell (peer messaging, self-improving) and World of Skillcraft (shared state, persistent agents) WHEN: Understanding…
SkillCFreshness: CClaude Code +9 - 0.376score
understand-claude-md
sancovp
WHAT: CLAUDE.md — system prompt injection, trigger vs control WHEN: Understanding or writing CLAUDE.md files
SkillCFreshness: CClaude Code +9 - 0.376score
understand-hooks
sancovp
WHAT: Claude Code hooks — 29 events, 5 handler types, metahook pattern WHEN: Understanding or creating hooks
SkillCFreshness: CClaude Code +9 - 0.376score
understand-mcps
sancovp
WHAT: Claude Code MCPs — external tools with state, typed data, control systems WHEN: Understanding or building MCPs
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 6, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sancovp/twi-jobworld
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sancovp
- 0.458score
bandit-chain-system
sancovp
How the bandit (the default ChainSelector persona) rolls up the AC→CoR→SC algebra and CLOSES it into a domain-specific persona — a self-contained "bandit…
SkillAFreshness: AClaude Code +9 - 0.458score
chaincompiler
sancovp
Orientation when working IN the chaincompiler repo — what the system is, where things live, and the discipline.
SkillAFreshness: AClaude Code +9 - 0.458score
glyphsteer
sancovp
Use when steering retrieval with hidden in-band glyph markers — an LLM annotates a corpus with a controlled emoji/glyph vocabulary that biases search (lexical…
SkillAFreshness: AClaude Code +9 - 0.458score
glyphsteer-dense
sancovp
Use when running GlyphSteer's DENSE regime — embedding-based emoji steering via the containerized ONNX sidecar.
SkillAFreshness: AClaude Code +9 - 0.458score
skilltree
sancovp
WHAT: turn a flat .claude/skills folder (or any folder of skills) into a walkable coordinate-addressed tree so the model loads one layer at a time instead of…
SkillAFreshness: AClaude Code +9 - 0.458score
chainforge
sancovp
Chain-of-reasoning (spoken, ends in a decision) — a diagram is a formalized relationship structure, never decoration — never begin by drawing; determine what…
SkillAFreshness: AClaude 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 ceo-bootstrap 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
ceo-bootstrap skill. Agent Mart. https://agentmart.dev/skills/sancovp-ceo-bootstrap (last updated 2026-10-24)