TypingMindTypingMindThe best frontend for AI
Frontend Design Improvements Loop logo

Frontend Design Improvements Loop

Community
Waishnav
frontend-design-improvements-loop

Run repeatable single-track frontend-design benchmark loops for this repo. Use this when creating sequential experiment versions, tuning frontend-design SKILL.md instructions, running Codex from inside `experiments/version-X/` with the shared `prompt.md`, capturing full-page `/1.. /5` screenshots, and scoring outputs against Opus-with-skill reference sets.

Overview

PublisherWaishnav
Repositoryself-improvement-frontend-design-skill-loop-for-codex
Skill namefrontend-design-improvements-loop
Stars
13
Forks
0
Bundled files
23
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 23 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Waishnav on GitHub. Read the source before you install it.

Installation

Install the Frontend Design Improvements Loop AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Waishnav/self-improvement-frontend-design-skill-loop-for-codex/tree/main/.agents/skills/frontend-design-improvements-loop
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Waishnav/self-improvement-frontend-design-skill-loop-for-codex.git /tmp/self-improvement-frontend-design-skill-loop-for-codex
mkdir -p .claude/skills
cp -r /tmp/self-improvement-frontend-design-skill-loop-for-codex/.agents/skills/frontend-design-improvements-loop .claude/skills/frontend-design-improvements-loop
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Frontend Design Improvements Loop in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Frontend Design Improvements Loop on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Frontend Design Improvements Loop is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Frontend Design Improvements Loop

Use this skill to run end-to-end benchmark iterations that improve frontend-design behavior through instruction tuning, not model weight tuning.

Scope

  • Repository: improved-frontend-skills-for-gpt
  • Canonical prompt: repo root prompt.md (same prompt for every version)
  • Active version workspace: experiments/version-X/
  • Preferred raw baseline skill seed: global $frontend-design at /home/waishnav/.agents/skills/frontend-design/SKILL.md
  • Primary references:
    • research/targetted-designs/
    • research/theo-screenshots-2k-clean/opus45_with_skill/
    • research/theo-screenshots-2k-clean/opus_iterations/

Read references/opus_targets.md, references/mutation_axes.md, and references/experiment_topologies.md before drafting a new version.

Non-Negotiables

  1. Never modify prompt.md unless explicitly asked.
  2. Always run Codex in the target version folder (-C experiments/version-X/...).
  3. Keep one mutation hypothesis per version.
  4. Keep each version self-contained (SKILL.md, t4-canvas/, README.md, CRITQUES.md, screenshots/).
  5. Do not delete previous versions.
  6. New versions must be isolated by default: do not inherit prior t4-canvas implementation unless explicitly requested.
  7. Run one active experiment at a time (strict sequential loop; no parallel sibling branches).
  8. Carry forward only one prioritized critique into the next mutation.
  9. Keep SKILL.md portable: no experiment/version labels or repo-specific benchmarking terms.

Workflow

1) Choose baseline and one mutation hypothesis

  • Baseline is the latest completed experiments/version-*.
  • Pick one mutation axis only (see references/mutation_axes.md).
  • Read the previous version CRITQUES.md and pick exactly one highest-impact issue to target.
  • Write the hypothesis in the new version README before implementation.

2) Create the next version

  • For true raw start (no version baseline), use:
    • scripts/new_fresh_version.sh <new-version-dir>
  • Use scripts/new_version_from_previous.sh <previous-version-dir> <new-version-dir>.
  • Default behavior is isolated: copy prior SKILL.md, create fresh empty t4-canvas/.
  • Legacy mode only when explicitly requested: --copy-app.
  • For raw baseline seeding from global frontend skill: use --skill-source global.

2b) Keep the loop sequential

  • Do not create sibling versions in the same iteration.
  • Do not run multiple mutation theses in parallel.
  • Complete critique and keep/drop decision for the current version before creating the next version.

3) Tune frontend-design skill instructions

  • Edit only experiments/version-X/.agents/skills/frontend-design/SKILL.md.
  • Keep constraints auditable and measurable.
  • Avoid vague language; use explicit guards and pass/fail criteria.
  • Apply one mutation change set only for this version.
  • Translate critique findings into generic rules; do not write benchmark- or version-specific wording inside SKILL.md.

4) Run Codex headlessly with canonical prompt

  • Use scripts/run_headless_iteration.sh <version-dir> <repo-root>/prompt.md [run-label].
  • Optional reliability args: [max-attempts] [retry-delay-sec].
  • This forces codex exec to run with cwd inside version folder and logs artifacts.
  • Prefer short, restartable runs over one giant run.

5) Capture screenshots for /1.. /5

  • Start the version app in t4-canvas/.
  • Use Playwright CLI to capture full-page screenshots for routes /1 to /5 in desktop/tablet/mobile profiles.
  • Preferred command:
    • scripts/capture_screenshots.sh <version-dir> [base-url]
  • Save under experiments/version-X/screenshots/<route>/{desktop,tablet,mobile}.png.

6) Critique and score

  • Score against rubric in references/scoring_rubric.md.
  • Compare against Opus reference sets (not generic web quality).
  • Write critique notes to experiments/version-X/CRITQUES.md after every run.
  • Record critique in a structured way:
    • issue
    • evidence
    • likely root-cause rule
    • proposed generic fix
  • Record:
    • wins
    • regressions
    • next mutation

7) Decide next action

  • If net gain: keep mutation and continue.
  • If mixed: keep only if rubric delta is positive on target dimensions.
  • If regression: revert mutation in next version and try a different axis.
  • In all cases, pick one next mutation only.

Reliability Pattern For Long Runs

  • Design for 3-7 minute chunks per run.
  • Do not require tmux by default; run direct codex exec with artifact checkpoints.
  • Persist outputs every run:
    • artifacts/<run-label>/events.jsonl
    • artifacts/<run-label>/stderr.log
    • artifacts/<run-label>/final.md
  • If interrupted, continue with codex exec resume --last and continue from latest checkpoint.

Deliverable Contract Per Version

Each version must include:

  • experiments/version-X/.agents/skills/frontend-design/SKILL.md (mutation applied)
  • experiments/version-X/README.md with:
    • hypothesis
    • exact mutation
    • rubric score delta
    • next step
  • experiments/version-X/CRITQUES.md with expected-vs-output critique notes
  • experiments/version-X/screenshots/1/{desktop,tablet,mobile}.png ... screenshots/5/{desktop,tablet,mobile}.png

Scripts

  • scripts/new_fresh_version.sh
  • scripts/new_version_from_previous.sh
  • scripts/run_headless_iteration.sh
  • scripts/capture_screenshots.sh

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Frontend Design Improvements Loop AI skill do?

Run repeatable single-track frontend-design benchmark loops for this repo. Use this when creating sequential experiment versions, tuning frontend-design SKILL.md instructions, running Codex from inside `experiments/version-X/` with the shared `prompt.md`, capturing full-page `/1.. /5` screenshots, and scoring outputs against Opus-with-skill reference sets.

Why use Frontend Design Improvements Loop on TypingMind?

Because you install it once and use it with any model. Frontend Design Improvements Loop is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Frontend Design Improvements Loop in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Waishnav/self-improvement-frontend-design-skill-loop-for-codex/tree/main/.agents/skills/frontend-design-improvements-loop. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Frontend Design Improvements Loop?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Frontend Design Improvements Loop?

As many as you like. As long as a model supports skills, you can use Frontend Design Improvements Loop with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Frontend Design Improvements Loop AI skill free?

It is published on GitHub by Waishnav. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
affaan-m logo

Eval Harness

affaan-m
CommunityPopular

Framework formal de evaluación para sesiones de Claude Code que implementa principios de desarrollo orientado a evals (EDD)

39.1K
261.1K
Instructions
View
affaan-m logo

Tdd Workflow

affaan-m
CommunityPopular

Usar este skill al escribir nuevas funcionalidades, corregir bugs o refactorizar código. Aplica el desarrollo guiado por pruebas con 80%+ de cobertura incluyendo pruebas unitarias, de integración y…

39.1K
261.1K
Instructions
View
affaan-m logo

Angular Developer

affaan-m
CommunityPopular

Angular コードを生成し、アーキテクチャ ガイダンスを提供します。プロジェクトの作成、コンポーネント、またはサービスを作成するとき、または反応性（シグナル、linkedSignal、リソース）、フォーム、依存性注入、ルーティング、SSR、アクセシビリティ（ARIA）、アニメーション、スタイリング（コンポーネント スタイル、Tailwind CSS）、テスト、または CLI ツール作成のベスト…

39.1K
261.1K
Instructions
View
NousResearch logo

Anatomy

NousResearch
OrganizationPopular

Explain an idea as an interactive isometric machine figure.

54.8K
252.8K
65 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇