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/sethatwood-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
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
- Set up Belay for a team. Add the team's own skills to the map, mark the zones that always need a human co-sign, and set how many unaided runs earn a skill.
- License
- MIT
- Instructions
- 11 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
A senior is setting Belay up for their team's repo. Walk them through it in order, one question per turn, and write the result to the map. 1. If the repo has no `.belay/map.json`, ask which starter map fits, `typescript` or `python`, and call `belay_init` with it. If the map exists, call `belay_map` and show it as a plain list. 2. Ask which skills this codebase needs that the starter map does not name. For each one they give, ask for the one or two sentences a senior would say about it, which witness kinds count (test, build, types), which skills come before it, and one or two files that show it done well. Add it to `.belay/map.json` by editing the file: same shape as the others, id in kebab-case. 3. Ask which paths always need a human co-sign whatever the logbook says. Write them into `zones` as globs with `cosign: true`. Say plainly that version one records zones and does not enforce them yet; the CI check that enforces them is later. 4. Ask how many witnessed unaided runs should earn a skill here, and how many correct reviews in a row should master one. The defaults are three and five. Write `threshold` and `mastery`. 5. Show the finished map as a plain list and say what to commit: `.belay/map.json`, `.claude/settings.json`, and the `.gitignore` line. Say that each person's logbook is their own file under `.belay/logbook/`, committed with their work, and that what they struggled with never leaves their machine. Edit the map directly with the file tools; no step is open, so the gate is not in the way. Keep the JSON valid and two-space indented. Short turns.
From sethatwood/belay, MIT.
More from sethatwood/belay
- 0.521score
learn
sethatwood
Start learning.
SkillBFreshness: BClaude Code +9 - 0.516score
calibrate
sethatwood
Seed your map on the first session.
SkillBFreshness: BClaude Code +9 - 0.516score
logbook
sethatwood
Show your logbook, newest first.
SkillBFreshness: BClaude Code +9 - 0.516score
why
sethatwood
Ask why the code in front of you is the way it is.
SkillBFreshness: BClaude Code +9 - 0.278score
map
sethatwood
No description from the publisher yet.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 23, 2026 (1 month ago)
- Last release
- Sep 23, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sethatwood/belay
- Website
- belay.page
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sethatwood
- 0.521score
learn
sethatwood
Start learning.
SkillBFreshness: BClaude Code +9 - 0.516score
calibrate
sethatwood
Seed your map on the first session.
SkillBFreshness: BClaude Code +9 - 0.516score
logbook
sethatwood
Show your logbook, newest first.
SkillBFreshness: BClaude Code +9 - 0.516score
why
sethatwood
Ask why the code in front of you is the way it is.
SkillBFreshness: BClaude 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/sethatwood-team (last updated 2026-10-24)