Skip to content
Agentmart
Submit a tool

design-iterate

Claude-Design-style visual iteration loop — render the running UI, screenshot at 375/768/1440, critique against docs/design/tokens.json and design principles…

Skill by bpmforge

IndexedApache-2.0★ 2
Write a review

Chalk Labs

Need help deploying design-iterate?

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/bpmforge-design-iterate-a99cd0

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

Claude-Design-style visual iteration loop — render the running UI, screenshot at 375/768/1440, critique against docs/design/tokens.json and design principles, apply fixes, re-capture until clean (cap 3 iterations). Also extracts a token baseline from an existing codebase (--sync) and audits real logged-in browsers (--real). NOT a one-pass review — use /ux --review for findings-only; NOT functional conformance — use /ui-verify.

Use cases: design

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 and code. Checked Nov 1, 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/design-iterate

What's inside

Skill name
design-iterate
Description
Claude-Design-style visual iteration loop — render the running UI, screenshot at 375/768/1440, critique against docs/design/tokens.json and design principles, apply fixes, re-capture until clean (cap 3 iterations). Also extracts a token baseline from an existing codebase (--sync) and audits real logged-in browsers (--real). NOT a one-pass review — use /ux --review for findings-only; NOT functional conformance — use /ui-verify.
License
Apache-2.0
Instructions
21 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • files: referenced but missing: references/real-browser-bridge.md, references/visual-design-loop.md, references/design-review-checklist.md

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Design Iterate

Load and follow the instructions in the `design-iterator` agent.

**Usage:**
- `/design-iterate "<url or screen>"` (no flag) — the full loop: ground in `docs/design/tokens.json` → render → capture mobile/tablet/desktop → deterministic token-lint + vision critique → apply smallest fixes → re-capture until no P0/P1 remains or the 3-iteration cap hits
- `/design-iterate --sync` — extract an observed token baseline from an existing codebase + running app into `docs/design/tokens.json` (`provenance: extracted-baseline`) + `docs/design/TOKEN_DRIFT.md`. Only when no tokens.json exists — authored systems from design-system-lead always win
- `/design-iterate --real "<url>"` — capture + critique a real logged-in browser session (findings only, no fixes) via the tiers in `references/real-browser-bridge.md`

**Code and pixels in one loop:** a fix is not done when the code is edited — it is done when a fresh screenshot shows it closed. Every finding is grounded: screenshot path + viewport + element + cited token/principle. No vibes.

**References:** `references/visual-design-loop.md` (the protocol), `references/real-browser-bridge.md` (logged-in/real-browser tiers), `references/design-review-checklist.md` (rubrics).

**Workflow:** Read protocol → Ground in tokens → Render dev server → Capture 3 viewports → Token-lint + critique → Fix P0/P1 → Re-capture → Log → Exit at clean or cap.

**Outputs:**
- default → `docs/design/ITERATION_LOG.md` + `docs/screenshots/design-iterate/iter-N/`
- `--sync` → `docs/design/tokens.json` + `docs/design/TOKEN_DRIFT.md`
- `--real` → `docs/design/DESIGN_AUDIT_LIVE.md`

From bpmforge/attest, Apache-2.0.

More from bpmforge/attest

Signals

Stars
2
Forks
1
Open issues
0
Last commit (this folder)
Aug 10, 2026 (2 months ago)
Last release
Oct 13, 2026 (19 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from bpmforge

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 design-iterate 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 design-iterate?

CallGet help
Cite this page

design-iterate skill. Agent Mart. https://agentmart.dev/skills/bpmforge-design-iterate-a99cd0 (last updated 2026-10-24)