Skip to content
Agentmart
Submit a tool

grain-genome

Build or update Grain's interactive component genome.

Skill by ObneyAI

IndexedMIT★ 127
Write a review

Chalk Labs

Need help deploying grain-genome?

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.

Book a call

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/obneyai-grain-genome

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.

We use your email only for this newsletter. Privacy

About

Build or update Grain's interactive component genome. Use when regenerating scripts/genome/grain-genome.html, resolving genome coverage warnings after component or macro changes, editing the taste overlay, or visually verifying component placement. Keep repository facts deterministic and human placement/description decisions in genome-taste.edn.

Use cases: frontend, testing, writing

No 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/grain-genome

What's inside

Skill name
grain-genome
Description
Build or update Grain's interactive component genome. Use when regenerating scripts/genome/grain-genome.html, resolving genome coverage warnings after component or macro changes, editing the taste overlay, or visually verifying component placement. Keep repository facts deterministic and human placement/description decisions in genome-taste.edn.
License
MIT
Instructions
32 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • files: referenced but missing: scripts/genome/genome-taste.edn

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Grain Genome

`bb scripts/genome/genome.bb` combines deterministic repository facts with the
editorial overlay in `scripts/genome/genome-taste.edn`, then injects them into the
HTML/Scittle shell. Never hand-edit generated `grain-genome.html`.

## Loop

1. Run `bb scripts/genome/genome.bb` from the repository root.
2. Resolve every warning in `genome-taste.edn`:
   - Add missing current components with a unique `(col,row)`, cluster, short role,
     and description.
   - Remove entries for deleted or deprecated components.
   - Add missing macros to the proper catalog group using the real arglist and a
     one-line purpose.
3. Rebuild until the coverage report is clean.
4. Run `node scripts/genome/shoot.js`, inspect every screenshot, and adjust the
   overlay until traces and layers read clearly.

## Taste rules

Rows represent dependency layers: apps, entry/coordination, processors, event-log
spine, storage, foundation. Columns run write-left, log-center, read-right. Place
nodes near dependencies, avoid shared cells, and exploit shared columns for hubs.
Prefer service-area clusters when registered; otherwise classify components by
their architectural role.

Facts such as dependencies, LOC, protocols, macros, and deprecation belong only
in `genome.bb` extraction. Placement, clusters, roles, descriptions, and macro
presentation belong only in `genome-taste.edn`.

From ObneyAI/grain, MIT.

Signals

Stars
127
Forks
9
Open issues
4
Last commit (this folder)
Aug 7, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ObneyAI

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 grain-genome 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying grain-genome?

CallGet help
Cite this page

grain-genome skill. Agent Mart. https://agentmart.dev/skills/obneyai-grain-genome (last updated 2026-10-24)