Agent skill

Recognition Over Recall

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

A skill your agent uses whenever the user must locate or choose something from many possibilities — pickers, command palettes, navigation menus, autocompletes, recents lists, search results…

Apache-2.0Auto-check passed

Install Recognition Over Recall

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill recognition-over-recall -a claude-code

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

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins recognition-over-recall --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/recognition-over-recall .claude/skills/recognition-over-recall && 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
recognition-over-recall
GitHub stars
1.3k
Token cost
~3k tokens
SKILL.md length
1,347 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 whenever the user must locate or choose something from many possibilities — pickers, command palettes, navigation menus, autocompletes, recents lists, search results…

  • Works in 4 steps: The "show options" check. For each… → The recents-coverage audit. For pickers… → The autocomplete check. Are inputs… → …
  • The user must locate
  • SKILL.md covers Definition (in our own words), Origins and research lineage, Why recognition matters and When to apply, plus 10 more sections
  • Calls git

What it does

Recognition Over Recall is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill whenever the user must locate or choose something from many possibilities — pickers, command palettes, navigation menus, autocompletes, recents lists, search results, settings panels. Trigger when designing inputs that ask the user to "type the right thing," when picking between dropdowns and search-first interfaces, when reviewing why users keep typing wrong values into autocomplete fields. Recognition Over Recall is one of the foundational principles in 'Universal Principles of Design' (Lidwell…

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/research-and-cases.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 user must locate
  • Choose something from many possibilities — pickers
  • Command palettes
  • Navigation menus

Example prompts

  • “type the right thing,”
  • “Universal Principles of Design”
  • “/recognition-over-recall”

Workflow steps

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

  1. The "show options" check. For each input, ask: are the valid options shown to the user, or must they recall? Showing usually wins.
  2. The recents-coverage audit. For pickers and navigation, are recents surfaced? If not, frequent users pay a recall tax.
  3. The autocomplete check. Are inputs hooked to autocomplete (browser, password manager, custom)? Each unaided input is a recall task.
  4. The discoverability test. Can a user find a feature without prior knowledge of its name? If not, recall is required to know about it.

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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Recognition Over Recall loads about 3k tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 167 tokens; SKILL.md has 1,347 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~167
When it runs · the whole SKILL.md, loaded when a task matches
~3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.6k

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). 1,347 words, ~3,032 tokens.

Download SKILL.mdSave it as .claude/skills/recognition-over-recall/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
recognition-over-recall
description
Use this skill whenever the user must locate or choose something from many possibilities — pickers, command palettes, navigation menus, autocompletes, recents lists, search results, settings panels. Trigger when designing inputs that ask the user to "type the right thing," when picking between dropdowns and search-first interfaces, when reviewing why users keep typing wrong values into autocomplete fields. Recognition Over Recall is one of the foundational principles in 'Universal Principles of Design' (Lidwell, Holden, Butler 2003) and one of Nielsen's 10 heuristics — recognizing options is far easier than recalling them from memory.

Recognition Over Recall

People are dramatically better at recognizing things they've previously seen than at recalling them from memory. A multiple-choice question is easier than a fill-in-the-blank because the options are visible — the user only has to recognize the right one rather than retrieve it. The same principle holds across UI design: showing options beats asking the user to type from memory; using familiar conventions beats requiring the user to recall arbitrary commands.

Definition (in our own words)

Recognition memory and recall memory work differently in human cognition. Recognition is fast, relatively effortless, and survives long after the original exposure. Recall requires active retrieval — searching through memory for the right item — and is slower, more error-prone, and degrades faster over time. Designs that show options for the user to recognize from outperform designs that ask the user to recall and type. The classic case in UI design: the shift from command-line interfaces (recall: "what was that command?") to graphical menus (recognition: "I see what I want; click it") dramatically expanded who could use computers.

Origins and research lineage

  • Cognitive psychology has demonstrated the recognition-over-recall asymmetry across decades of memory research. Recognition tasks (multiple choice) consistently outperform recall tasks (fill-in-the-blank) for the same content.
  • The Xerox Star user interface (1981) is the seminal applied work. The Star's designers leveraged recognition over recall throughout: menus showed available options instead of requiring command memorization. Documented in Johnson, Roberts, et al. (1995), "The Xerox 'Star': A Retrospective," in Human Computer Interaction: Toward the Year 2000.
  • Lidwell, Holden & Butler (2003) compactly stated the principle and noted recognition-driven decision-making — users often select familiar options over potentially-better unfamiliar ones (the "consumer brand familiarity" effect).
  • Jakob Nielsen included "Recognition rather than recall" as one of his 10 usability heuristics (1994 onward).
  • Hoyer & Brown (1990), "Effects of Brand Awareness on Choice for a Common, Repeat-Purchase Product." Journal of Consumer Research. Showed that brand familiarity influences purchase choices independent of objective product quality — a recognition effect in the marketplace.

Why recognition matters

Working memory is small (~4 items). Long-term memory is vast but accessed primarily through cues. Recognition tasks provide the cue (the option is visible); recall tasks ask the brain to generate the cue from scratch.

For UI design:

  • A flat list of 30 timezones asks users to recognize the right one. Fast.
  • A blank field "type your timezone" asks users to recall. Slow, error-prone, requires precise spelling.
  • A combobox combines: type a few characters; the system shows matches; user recognizes and selects. Fast and tolerant of incomplete recall.

The discipline: prefer surfaces that show what's available over surfaces that ask the user to remember.

When to apply

  • Always, when the user must select from a known set of options.
  • Especially when the option set is large or the user is occasional (less practiced; weaker recall).
  • Critically when the user might not know what's available — discoverability problem solved by recognition.

When recall is appropriate

A few cases where recall outperforms recognition:

  • Power-user shortcuts. Frequent users develop muscle memory for keyboard shortcuts. Forcing them to recognize from a menu every time slows them.
  • Free-text input for genuinely open-ended content (writing prose, naming new objects). Recognition can't show what doesn't exist yet.
  • Authentication. Passwords are deliberately recall-based for security; recognition would weaken them.
  • Creative input. Brainstorming, artistic creation, problem-solving where the answer isn't a selection from a known set.

Patterns that leverage recognition

Combobox / typeahead

The user types a few characters; the system filters from a known set; the user recognizes and selects.

html
<combobox label="Country">
  <input placeholder="Search country..." />
  <listbox>
    <option value="us">United States</option>
    <option value="uk">United Kingdom</option>
    <option value="de">Germany</option>
    <!-- 192 more -->
  </listbox>
</combobox>

Better than:

  • Long select dropdown (visible options but no filtering for large sets).
  • Free-text field (recall required; typos cause errors).
Recents and frequently-used lists

The most-recent or most-used items are surfaced first. Repeat actions become recognition tasks ("there it is again").

Recently used:
  • Projects > Acme Q4
  • Reports > Monthly summary
  • Inbox

Other workspaces:
  • Projects > ...
Command palettes (cmd-K)

The palette shows available commands; the user filters by typing partial recall and recognizes the rest. Combines fast keyboard access (for power users) with recognition (for occasional users).

Visible navigation

A sidebar showing available sections is recognition-based. The user sees what's there. Compare to command-line where the user must recall the command name.

Picker UIs over free-text

A date picker shows a calendar; the user clicks the date. Compare to a free-text "MM/DD/YYYY" field that requires the user to recall the format.

html
<input type="date" />  <!-- shows calendar picker; recognition -->
<!-- vs. -->
<input type="text" placeholder="MM/DD/YYYY" />  <!-- recall required -->
Auto-complete in form fields
html
<input name="email" type="email" autocomplete="email" />

The browser offers previously-used values; the user recognizes and selects.

Recognition in decision-making

The book makes a related point: recognition often dominates decision-making. People choose the familiar option even when an unfamiliar option is objectively better. Examples:

  • Brand-name products in stores chosen over generic equivalents at lower price.
  • Returning to the same restaurant instead of trying new ones.
  • Sticking with familiar tools even when newer ones are demonstrably better.

For product design, this means familiarity is a competitive moat. Users who know your product's interaction patterns will choose your product over alternatives requiring re-learning.

Worked examples

Show full SKILL.md (539 more words)Show less
Example 1: timezone selector

Bad (recall):

html
<input name="timezone" placeholder="Type your timezone" />

Good (recognition):

html
<select name="timezone">
  <option>America/Los_Angeles (PST/PDT)</option>
  <option>America/New_York (EST/EDT)</option>
  <option>Europe/London (GMT/BST)</option>
  <!-- 200+ more -->
</select>

Better (recognition + filtering):

html
<combobox name="timezone">
  <input placeholder="Search..." />
  <listbox>
    <group label="Recent">
      <option>America/Los_Angeles</option>
    </group>
    <group label="All">
      <option>...</option>
    </group>
  </listbox>
</combobox>

The combobox version: recents at top (recognition), filterable for the rest.

Example 2: command-line CLI vs. command palette

CLI (recall):

$ git checkout -b feature/new-thing

Command palette (recognition):

[ Cmd-K opens palette ]
Search: "create branch"
> Create branch
> Switch to branch
> Delete branch

Both reach the same outcome. The CLI is faster for users who recall; the palette is faster for users who don't. Modern dev tools offer both.

Example 3: navigation menu over command memory

Early word processors (WordStar, vi) required users to recall command sequences. Modern word processors show menus; the user recognizes the option.

The recognition-based approach made word processors mass-market; the recall-based approach kept them tools for the technical.

Example 4: recents in a file picker
Open file...

Recent files:
  - resume-2026.docx
  - project-notes.md
  - budget.xlsx

Browse:
  Documents/
  Downloads/
  Desktop/

Recents collapse the recall task (where did I put it?) to recognition (there it is).

Cross-domain examples

Multiple choice exams

The classic recognition-over-recall demonstration. Multiple choice exams are easier than essay or fill-in-the-blank because they provide cues. Test designers calibrate by limiting how cue-rich the choices are.

Restaurants: visible menus

A printed menu at a restaurant lets diners recognize options. Asking diners to "tell us what you want" without a menu would dramatically slow ordering and limit choice variety.

Retail: shelf displays

Stocked shelves where products are visible enable recognition-based shopping. Compare to bartender ordering ("what cocktails do you have?"), where customers must recall.

Library card catalogs (historical)

Pre-digital libraries provided card catalogs (recognition: browse cards) and shelf browsing (recognition: see books). Modern search engines combine both: type partial recall, recognize from results.

Anti-patterns

  • Empty fields requiring exact recall. A field labeled "country" with no autocomplete; users must remember exact spelling.
  • Hidden features requiring command knowledge. "There's a feature for that, but you have to know to look for it." Discoverability problem.
  • Over-reliance on muscle memory. Designs assuming all users will memorize keyboard shortcuts; new users left out.
  • No recents. Frequent destinations not surfaced; users repeatedly retype.
  • Generic placeholders that don't aid recognition. "Enter value" instead of showing examples.

Heuristics

  1. The "show options" check. For each input, ask: are the valid options shown to the user, or must they recall? Showing usually wins.
  2. The recents-coverage audit. For pickers and navigation, are recents surfaced? If not, frequent users pay a recall tax.
  3. The autocomplete check. Are inputs hooked to autocomplete (browser, password manager, custom)? Each unaided input is a recall task.
  4. The discoverability test. Can a user find a feature without prior knowledge of its name? If not, recall is required to know about it.
  • exposure-effect — exposure builds recognition; familiar items become preferred.
  • serial-position-effects — first and last items in a list are recognized fastest.
  • visibility — visible options enable recognition; hidden options don't.
  • hicks-law — recognition collapses Hick's Law for typeahead-filtered options.
  • mental-model — recognition leverages prior models; recall asks for explicit retrieval.
  • mimicry — borrowing familiar patterns leverages recognition.

Sub-aspect skills

  • recognition-pickers-and-palettes — pickers, dropdowns, comboboxes, command palettes; recognition-based selection patterns.
  • recognition-recents-and-suggestions — using recents, frequently-used, and contextual suggestions to accelerate repeat tasks.

Closing

Recognition Over Recall is one of the cheapest cognition wins in design. Showing options where the user would otherwise have to remember reduces error rates, speeds tasks, and dramatically widens the user base. The discipline is recognizing each input as a recall-vs-recognition choice and defaulting to recognition unless there's a specific reason not to.

© 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/recognition-over-recall of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/research-and-cases.md

Open the folder on GitHubat commit 3e1456a

Compare with similar skills

Recognition Over Recall 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.

Recognition Over Recall compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Recognition Over Recall this skillhashgraph-online/awesome-codex-plugins1.3k—~3kAutomated safety check: PassApache-2.0
Recognition Rewardssickn33/agentic-awesome-skills47k1 repos~3.4kAutomated safety check: PassMIT
Logic Locatesickn33/agentic-awesome-skills47k1 repos~977Automated safety check: PassMIT
Recallcursor/plugins11k7 repos~1.3kAutomated safety check: PassNone
Intent Recognitionn8n-io/n8n207k—~7.1kAutomated safety check: PassCustom licence
Agentmemory Recallrohitg00/agentmemory29k—~557Automated safety check: PassApache-2.0

Similar skills

  • Recognition Rewards

    sickn33/agentic-awesome-skills

    Recognition register: employee, reward type, category, visibility, message and points awarded.

    47k GitHub starsUsed in 1 repo~3.4k tokens
    Auto-check passed
  • Logic Locate

    sickn33/agentic-awesome-skills

    Locate the root cause of a CONFIRMED failure via backward-then-forward semi-formal tracing.

    47k GitHub starsUsed in 1 repo~977 tokens
    DevelopmentAuto-check passed
  • Recall

    cursor/plugins

    Official

    Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief.

    11k GitHub starsUsed in 7 repos~1.3k tokens
    Auto-check passed
  • Official

    Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother…

    207k GitHub stars~7.1k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Agentmemory Recall

    rohitg00/agentmemory

    Searches agentmemory for past observations, sessions and learnings with hybrid keyword, vector and graph search, and reports only what comes back.

    29k GitHub stars~557 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Cognee Memory Recall

    topoteretes/cognee

    Explains how to query cognee agent memory with recall(): how the search type is chosen, how to narrow a query to datasets, and what the returned results contain.

    32k GitHub stars~2.6k tokensUpdated today
    AI & LLM EngineeringAuto-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 Recognition Over Recall

What does Recognition Over Recall do?

A skill your agent uses whenever the user must locate or choose something from many possibilities — pickers, command palettes, navigation menus, autocompletes, recents lists, search results…. Recognition Over Recall is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill whenever the user must locate or choose something from many possibilities — pickers, command palettes, navigation menus, autocompletes, recents lists, search results, settings panels.

When should I use Recognition Over Recall?

Recognition Over Recall fits situations like: the user must locate; choose something from many possibilities — pickers; command palettes; navigation menus.

How do I install Recognition Over Recall in Claude Code?

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

How do I install Recognition Over Recall in Codex?

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

Can I use Recognition Over Recall 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 recognition-over-recall -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recognition-over-recall, .gemini/skills/recognition-over-recall, .github/skills/recognition-over-recall and .opencode/skills/recognition-over-recall in your project.

What does Recognition Over Recall need to run?

Going by SKILL.md and its folder, Recognition Over Recall needs the command-line tools its instructions call (git).

Does Recognition Over Recall access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Recognition Over Recall 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 Recognition Over Recall use?

Recognition Over Recall 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 Recognition Over Recall use?

About 3k tokens (SKILL.md is roughly 12k 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 567 tokens, read only when the agent opens those files.

What are the alternatives to Recognition Over Recall?

Skills that share tags, products or a category with Recognition Over Recall: Recognition Rewards (sickn33/agentic-awesome-skills, 47k stars), Logic Locate (sickn33/agentic-awesome-skills, 47k stars), Recall (cursor/plugins, 11k stars) and Intent Recognition (n8n-io/n8n, 207k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Recognition Over Recall?

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.