Agent skill

Hicks Law Defaults

by hashgraph-online in hashgraph-online/awesome-codex-plugins

A skill your agent uses when the question is what to pre-select in a list of options — radio groups, dropdowns, configuration UIs, plan pickers, sign-up flows, settings.

Apache-2.0Auto-check passed

Install Hicks Law Defaults

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill hicks-law-defaults -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins hicks-law-defaults --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/hicks-law-defaults .claude/skills/hicks-law-defaults && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hicks-law-defaults
GitHub stars
1.3k
Token cost
~2.8k tokens
SKILL.md length
1,232 words
Files
2 (incl. references)
Skills in repo
716
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when the question is what to pre-select in a list of options — radio groups, dropdowns, configuration UIs, plan pickers, sign-up flows, settings.

  • Works in 3 steps: The acceptance-rate test. Periodically… → The "who does this serve?" check. For… → The "describe in one sentence" test. Can…
  • The question is what to pre-select in a list of options — radio groups
  • SKILL.md covers When to invest in a default, Levels of default, Strategies for choosing the… and When not to default, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hicks Law Defaults is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill when the question is what to pre-select in a list of options — radio groups, dropdowns, configuration UIs, plan pickers, sign-up flows, settings. A strong default is the highest-leverage Hick's Law mitigation: most users accept the default, paying almost no decision cost. Trigger when picking what's selected on first load, when stakeholders argue "shouldn't we let the user choose?", when designing wizards or onboarding, or when a UI has many options but most users want the same one. Sub-aspect of…

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/defaults-research.md`).

The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.

When your agent uses it

  • The question is what to pre-select in a list of options — radio groups
  • Configuration UIs
  • Picking whats selected on first load
  • Stakeholders argue shouldnt we let the user choose?

Example prompts

  • “s selected on first load, when stakeholders argue”
  • “t we let the user choose?”
  • “/hicks-law-defaults”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. The acceptance-rate test. Periodically measure: of users who land on this default, what percent accept it? If <50%, the default is wrong…
  2. The "who does this serve?" check. For each default, ask: does this default primarily serve the user, or the business? If it's the…
  3. The "describe in one sentence" test. Can you describe what the default is and why in one plain sentence? If yes, it's defensible. If you…

What it can do on your machine

Read from SKILL.md and the folder at commit 3e1456a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are html and javascript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hicks Law Defaults loads about 2.8k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 148 tokens; SKILL.md has 1,232 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~148
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 3e1456a, republished under its Apache-2.0 licence (© hashgraph-online). 1,232 words, ~2,758 tokens.

Download SKILL.mdSave it as .claude/skills/hicks-law-defaults/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
hicks-law-defaults
description
Use this skill when the question is what to *pre-select* in a list of options — radio groups, dropdowns, configuration UIs, plan pickers, sign-up flows, settings. A strong default is the highest-leverage Hick's Law mitigation: most users accept the default, paying almost no decision cost. Trigger when picking what's selected on first load, when stakeholders argue "shouldn't we let the user choose?", when designing wizards or onboarding, or when a UI has many options but most users want the same one. Sub-aspect of `hicks-law`; read that first if you haven't already.

Hick's Law: defaults as the primary mitigation

Strong defaults are the highest-leverage way to reduce Hick's Law cost. When the system pre-selects the most likely option, the user faces a much smaller decision: "accept the default" or "look at the alternatives." Most users accept; the decision is effectively zero cost. The minority who don't accept now do face the original Hick's Law cost — but only when their preferences differ from the default.

When to invest in a default

A good default is worth the design effort when:

  • One option is significantly more likely than the others. If 60–80%+ of users want option X, defaulting to X serves most of them at no cost.
  • The cost of "wrong" is recoverable. Users can change the default after the fact without losing work.
  • You can predict the right default from context. User's locale, previous behavior, role, or the immediate task often disclose the right answer.
  • The decision is low-stakes. Financial commitments, irreversible actions, and privacy-affecting choices should not be defaulted; they should be deliberate.

A bad default appears when:

  • Options are roughly equiprobable. Picking any one biases the user without serving them.
  • The cost of accepting the wrong default is high or hidden.
  • The default is set to serve the business (auto-checked "share my data with partners") rather than the user.

Levels of default

Defaults vary in strength and cognitive cost:

Level 1: pre-selection (no commitment)

The default option is highlighted/selected, but the user must explicitly confirm to proceed.

html
<form>
  <fieldset>
    <legend>Email digest</legend>
    <label><input type="radio" name="digest" value="off" /> Off</label>
    <label><input type="radio" name="digest" value="daily" checked /> Daily (recommended)</label>
    <label><input type="radio" name="digest" value="weekly" /> Weekly</label>
  </fieldset>
  <button>Continue</button>
</form>

The user sees "Daily" pre-selected. They can change it; they must press Continue regardless. Low-pressure, ethical, effective.

Level 2: implicit acceptance

The default is set silently; if the user doesn't change it, it takes effect when they continue.

This is appropriate for non-consequential settings (sort order, theme preference). Less appropriate for material commitments.

Level 3: opt-out (the user must take action to escape the default)

The default takes effect unless the user actively unchecks or selects another option. Common in privacy and notification settings.

This crosses an ethical line in many contexts. Reserve it for choices where the default genuinely serves the user (e.g., critical security notifications on by default).

Level 4: forced default with disclosure

A choice is made for the user with explicit disclosure — "We've set this for you based on your role; you can change it in settings."

Useful when defaults are derived from earlier signals and the user might wonder why the system "knows" their preference.

Strategies for choosing the right default

Use known data

If you know the user's locale, you know their currency, date format, language, timezone. Default to those.

html
<select name="currency">
  <option value="USD" selected>USD ($)</option>      <!-- defaulted from IP -->
  <option value="EUR">EUR (€)</option>
  <option value="GBP">GBP (£)</option>
  …
</select>

If you know the user's role, you know which features they're likely to use; default the dashboard view to those.

Run analytics. If 70% of teams pick "Standard" plan, default to Standard. If 80% of users want "All notifications," default to All.

This works until the popular choice is popular only because it was the default — a feedback loop. Periodically test by flipping the default to a different option and measuring the new acceptance rate; if it's still 70%+, the default is genuinely matching preferences.

Use the safer choice

When in doubt, default to the option that's hardest to recover from an "incorrect default." Defaulting to "private" is safer than "public" — public-by-mistake leaks; private-by-mistake just requires sharing later.

Use the recently-used choice

If the user picked an option last time, default to it this time. "Recently used templates," "last upload directory," "previous report filter."

Pair the default with an explicit signal that it's the recommended choice:

html
<RadioGroup defaultValue="pro">
  <Option value="starter">Starter</Option>
  <Option value="pro">
    Pro
    <Badge>Recommended</Badge>
  </Option>
  <Option value="enterprise">Enterprise</Option>
</RadioGroup>

This is honest — you're disclosing that you have a recommendation — and it tells users "if you don't have a strong opinion, this one's safe."

When not to default

There are cases where forcing the user to choose is the right move:

  • Account creation passwords. Don't pre-fill or suggest; the user must compose.
  • Payment amounts. Don't pre-fill values for charity donations or tip amounts beyond a small set of explicit options.
  • Permissions and visibility. Don't default to "public" or "share with team" without an active selection.
  • High-stakes irreversible actions. Don't pre-select "Delete" in a confirmation dialog. (Actually invert: pre-select "Cancel" so the destructive path requires deliberate effort.)
  • Where the system genuinely doesn't know. Asking the user is more honest than guessing.

For these cases, leave the choice unset and disable the proceed button until the user picks. The Hick's Law cost is real but justified.

Show full SKILL.md (491 more words)Show less

Worked examples

Example 1: a sign-up plan picker

Three plans, one is by far the most popular. Default to it; mark it as recommended.

html
<form>
  <fieldset class="plan-picker">
    <legend class="sr-only">Pick a plan</legend>
    <label class="plan">
      <input type="radio" name="plan" value="starter" />
      <strong>Starter</strong>
      <p>Free for 14 days. Single user.</p>
    </label>
    <label class="plan plan--recommended">
      <input type="radio" name="plan" value="pro" checked />
      <strong>Pro</strong>
      <span class="recommended-badge">Recommended</span>
      <p>$29/mo. Up to 5 users.</p>
    </label>
    <label class="plan">
      <input type="radio" name="plan" value="team" />
      <strong>Team</strong>
      <p>$99/mo. Up to 25 users.</p>
    </label>
  </fieldset>
  <button class="primary">Continue with Pro</button>
</form>

Note the button label reflects the default ("Continue with Pro"), so the user is reminded what they're committing to. If they change selection, the label updates.

Example 2: a notification settings panel

Most users want notifications on, but not at maximum frequency. Default to a sane middle.

html
<form>
  <fieldset>
    <legend>How often should we email you?</legend>
    <label><input type="radio" name="freq" value="instant" /> Real-time (may be a lot)</label>
    <label><input type="radio" name="freq" value="daily" checked /> Daily digest <span class="hint">(default)</span></label>
    <label><input type="radio" name="freq" value="weekly" /> Weekly digest</label>
    <label><input type="radio" name="freq" value="off" /> Off</label>
  </fieldset>
</form>

The explicit "(default)" annotation removes any guessing about why "Daily digest" is selected.

Example 3: a date range picker

For a "Reports" page, default to a sensible range based on context.

  • On first visit: "Last 30 days" (covers most curiosity).
  • On return visit: the range the user last selected (recency bias).
  • After clicking a "Compare to" toggle: pre-fill the comparison range as "Previous 30 days."
js
const lastUsedRange = localStorage.getItem('reports.range');
const defaultRange = lastUsedRange ?? 'last_30_days';
Example 4: a "Send to" picker in a messaging app

The user is most likely to message the same people they recently messaged. Surface those as a "Recent" group at the top of the picker; the default is to type to filter.

[Search recipient________________]
Recent
  ● Maria Mendoza
  ● Marketing team
  ● Lin Chen
All people
  ● …

Recents collapse Hick's Law nearly to zero for repeat tasks.

Anti-patterns

  • The pre-checked subscription. "Subscribe to our newsletter" pre-checked at sign-up. Conversion goes up; trust goes down. Don't.
  • The defaulted upsell. A higher-priced plan pre-selected when the user's stated needs match a cheaper plan. The user finds out at checkout; ill will follows.
  • The hidden default change. Changing the default in a software update without telling users. Users feel the system "did something" without their consent.
  • The opt-out for material consequences. Pre-checked "auto-renew at full price" with the opt-out hidden three pages deep. Regulators are paying attention.
  • The incoherent default set. Defaults across a settings page that contradict each other (notifications ON, but email digest OFF, but in-app quiet hours ON 24/7). Means the system can't actually deliver the user's intent.

Heuristics

  1. The acceptance-rate test. Periodically measure: of users who land on this default, what percent accept it? If <50%, the default is wrong; pick a different one. If >85% across many users for many months, the default is doing its job.
  2. The "who does this serve?" check. For each default, ask: does this default primarily serve the user, or the business? If it's the business, examine whether the user would consent if asked clearly.
  3. The "describe in one sentence" test. Can you describe what the default is and why in one plain sentence? If yes, it's defensible. If you can't, it's probably opaque to users too.
  • hicks-law (parent).
  • hicks-law-menus — the complementary case where defaults aren't appropriate (the menu is a list of actions, not a choice with one obvious answer).
  • hicks-law-pricing — defaults are central to pricing tier selection.
  • satisficing — the cognitive principle that explains why defaults work: users accept the first acceptable option.
  • framing — how the default is labeled (e.g., "Recommended") affects acceptance rate.
  • nudge (interaction) — defaults are the canonical nudge; treat them as a design responsibility.

© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/hicks-law-defaults of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/defaults-research.md

Open the folder on GitHubat commit 3e1456a

Compare with similar skills

Hicks Law Defaults next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hicks Law Defaults compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hicks Law Defaults this skillhashgraph-online/awesome-codex-plugins1.3k—~2.8kAutomated safety check: PassApache-2.0
Hicks LawOwl-Listener/designer-skills2.9k1 repos~665Automated safety check: PassMIT
Select Namethedaviddias/Front-End-Checklist74k—~451Automated safety check: PassMIT
Engine Selectionsickn33/agentic-awesome-skills47k1 repos~1.2kAutomated safety check: PassMIT
Od Defaultnexu-io/open-design100k—~919Automated safety check: PassApache-2.0
Five Questionsbrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~1.7kAutomated safety check: NotesCustom licence

Similar skills

  • Hicks Law

    Owl-Listener/designer-skills

    Apply Hick's Law — decision time grows with the number of simultaneous choices.

    2.9k GitHub starsUsed in 1 repo~665 tokens
    Auto-check passed
  • Select Name

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Provide accessible names for select elements.

    74k GitHub stars~451 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Engine Selection

    sickn33/agentic-awesome-skills

    Selects game engines and frameworks by platform, genre, and architecture (full canvas shell vs hybrid DOM shell + guest viewport).

    47k GitHub starsUsed in 1 repo~1.2k tokens
    Game DevelopmentAuto-check passed
  • Od Default

    nexu-io/open-design

    Hidden fallback scenario for free-form Home prompts. An agent skill from nexu-io/open-design.

    100k GitHub stars~919 tokensUpdated today
    Media & CreativeAuto-check passed
  • Five Questions

    brycewang-stanford/Auto-Empirical-Research-Skills

    Deeply analyze any empirical economics PDF using the five-question framework (五问框架): research question, identification strategy, core estimand, robustness logic, and scholarly contribution.

    4.6k GitHub stars~1.7k tokensUpdated 5 days ago
    Documents & OfficeAuto-check: notes
  • Discovery Question Form

    nexu-io/open-design

    Structured clarification form for unresolved material requirements.

    100k GitHub stars~1.5k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 716 skills in this repo
  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.3k GitHub stars~922 tokensUpdated today
    Auto-check passed
  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.3k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.3k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.3k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Calle

    hashgraph-online/awesome-codex-plugins

    Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.

    1.3k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.3k GitHub stars~618 tokensUpdated today
    Auto-check passed

Questions about Hicks Law Defaults

What does Hicks Law Defaults do?

A skill your agent uses when the question is what to pre-select in a list of options — radio groups, dropdowns, configuration UIs, plan pickers, sign-up flows, settings. Hicks Law Defaults is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill when the question is what to pre-select in a list of options — radio groups, dropdowns, configuration UIs, plan pickers, sign-up flows, settings.

When should I use Hicks Law Defaults?

Hicks Law Defaults fits situations like: the question is what to pre-select in a list of options — radio groups; configuration UIs; picking whats selected on first load; stakeholders argue shouldnt we let the user choose?.

How do I install Hicks Law Defaults in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill hicks-law-defaults -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/hicks-law-defaults in hashgraph-online/awesome-codex-plugins) into .claude/skills/hicks-law-defaults in your project. Claude Code loads it when a task matches its description.

How do I install Hicks Law Defaults in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill hicks-law-defaults -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/hicks-law-defaults in hashgraph-online/awesome-codex-plugins) into .agents/skills/hicks-law-defaults in your project. Codex loads it when a task matches its description.

Can I use Hicks Law Defaults in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill hicks-law-defaults -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hicks-law-defaults, .gemini/skills/hicks-law-defaults, .github/skills/hicks-law-defaults and .opencode/skills/hicks-law-defaults in your project.

What does Hicks Law Defaults need to run?

SKILL.md names no scripts, command-line tools or credentials: Hicks Law Defaults is instructions for the agent only.

Does Hicks Law Defaults access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hicks Law Defaults safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hicks Law Defaults use?

Hicks Law Defaults is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hicks Law Defaults use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.2k tokens, read only when the agent opens those files.

What are the alternatives to Hicks Law Defaults?

Skills that share tags, products or a category with Hicks Law Defaults: Hicks Law (Owl-Listener/designer-skills, 2.9k stars), Select Name (thedaviddias/Front-End-Checklist, 74k stars), Engine Selection (sickn33/agentic-awesome-skills, 47k stars) and Od Default (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hicks Law Defaults?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,267 GitHub stars. The repository holds 716 skills in this directory. The repository was last updated on October 10, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.