Penpot Uiux Design
github/awesome-copilot
Comprehensive guide for creating professional UI/UX designs in Penpot using MCP tools.
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models.
$ npx skills add wondelai/skills --skill design-everyday-things -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install wondelai/skills design-everyday-things --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/wondelai/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/design-everyday-things .claude/skills/design-everyday-things && rm -rf skills-srcUse ~/.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/
Install the "design-everyday-things" agent skill from https://github.com/wondelai/skills/tree/main/design-everyday-things into .claude/skills/design-everyday-things/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-everyday-things", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/wondelai/skills/tree/main/design-everyday-thingsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add wondelai/skills --skill design-everyday-things -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install wondelai/skills design-everyday-things --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wondelai/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/design-everyday-things .agents/skills/design-everyday-things && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "design-everyday-things" agent skill from https://github.com/wondelai/skills/tree/main/design-everyday-things into .agents/skills/design-everyday-things/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-everyday-things", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add wondelai/skills --skill design-everyday-things -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install wondelai/skills design-everyday-things --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wondelai/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/design-everyday-things .cursor/skills/design-everyday-things && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "design-everyday-things" agent skill from https://github.com/wondelai/skills/tree/main/design-everyday-things into .cursor/skills/design-everyday-things/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-everyday-things", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/wondelai/skills.git --path design-everyday-things--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add wondelai/skills --skill design-everyday-things -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install wondelai/skills design-everyday-things --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wondelai/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/design-everyday-things .gemini/skills/design-everyday-things && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "design-everyday-things" agent skill from https://github.com/wondelai/skills/tree/main/design-everyday-things into .gemini/skills/design-everyday-things/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-everyday-things", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install wondelai/skills design-everyday-thingsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add wondelai/skills --skill design-everyday-things -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/wondelai/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/design-everyday-things .github/skills/design-everyday-things && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "design-everyday-things" agent skill from https://github.com/wondelai/skills/tree/main/design-everyday-things into .github/skills/design-everyday-things/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-everyday-things", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add wondelai/skills --skill design-everyday-things -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install wondelai/skills design-everyday-things --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wondelai/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/design-everyday-things .opencode/skills/design-everyday-things && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "design-everyday-things" agent skill from https://github.com/wondelai/skills/tree/main/design-everyday-things into .opencode/skills/design-everyday-things/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-everyday-things", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
design-everyday-thingsApply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models.
Design Everyday Things is an agent skill from wondelai/skills. Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making mistakes", "this is unintuitive", or "people cant figure out how to use it". Also trigger when reducing product complexity or feature creep. Covers the gulfs of execution and evaluation. For usability…
Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including reference files (for example `references/affordances.md`, `references/case-studies.md` and `references/conceptual-models.md`).
It sits in Frontend & Design, covering UX design. It works with iOS. The repository describes itself as: Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code, Codex, Cursor & other agentskills.io… The licence is MIT.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit c172996. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
amazon.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Design Everyday Things loads about 4k tokens when it runs, and up to ~41k if it reads all its reference files. Until then it costs about 152 tokens; SKILL.md has 1,750 words of instructions outside code blocks.
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.
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.
The full file from wondelai/skills at commit c172996, republished under its MIT licence (© wondelai). 1,750 words, ~3,953 tokens.
.claude/skills/design-everyday-things/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.Foundational design principles for creating products that are intuitive, discoverable, and understandable. The "bible of UX" — applicable to physical products, software, and any human-designed system.
Good design is actually a lot harder to notice than poor design, in part because good designs fit our needs so well that the design is invisible. When something fails, users blame themselves — but the fault is almost always in the design. Great design bridges the gap between what people want to do and what the product allows: it is discoverable (you can figure out what to do) and understandable (you can figure out what happened).
Goal: 10/10. Score 2 points per satisfied row of the Quick Diagnostic (5 rows = discoverability, evaluation, error recovery, mapping, constraints). Bands: 9-10 = users act without instructions, understand every outcome, and recover from any error; 5-6 = one gulf or error path is broken; <=3 = users must consult a manual or routinely blame themselves. Report the current score and the diagnostic rows failing it.
Every interaction with a product requires bridging two gulfs:
USER PRODUCT
│ │
├──── Gulf of Execution ────────────────→│
│ "How do I do what I want?" │
│ │
│←──── Gulf of Evaluation ──────────────┤
│ "What happened? Did it work?" │The gap between what users want to do and what the product lets them do. Users ask: What can I do here? Which control do I use?
Bridge with: clear signifiers, natural mappings, constraints, familiar conceptual models.
The gap between what the product did and what users understand happened. Users ask: What happened? Did it work? What state is the system in?
Bridge with: immediate visible feedback, clear system-state indicators, meaningful error messages, progress indicators.
Design goal: Make both gulfs as narrow as possible — action and understanding should be immediate.
See: references/two-gulfs.md for gulf analysis exercises.
Definition: Can users figure out what actions are possible and how to perform them? Its five components — affordances, signifiers, constraints, mappings, feedback — are detailed below.
Test: Put a new user in front of your product. If they can't figure out what to do within 10 seconds, discoverability is broken.
Anti-pattern: "The user manual explains it." If users need a manual, the design failed.
Definition: The relationship between an object's properties and a user's capabilities that determines how the object could be used.
Key insight: Affordances exist whether or not they are perceived — what matters for design is perceived affordance.
| Type | Definition | Example |
|---|---|---|
| Real | Physical capability exists | A button affords pressing |
| Perceived | User believes capability exists | A raised area looks clickable |
| Hidden | Exists but isn't obvious | Right-click context menu |
| False | Appears to afford action but doesn't | Decorative element that looks clickable |
| Anti-affordance | Prevents action | A barrier that blocks movement |
Digital applications:
| Element | Affordance | How to Signal |
|---|---|---|
| Button | Clicking/tapping | Raised, colored, shadow, hover state |
| Text field | Text input | Border, placeholder text, label |
| Scroll area | Scrolling | Scroll bar, fade at edge, partial content |
Common failures: flat design erasing perceived affordances (button or label?), too-small touch targets, interactive and decorative elements that look identical.
See: references/affordances.md for affordance design patterns.
Definition: Signals that communicate where the action should take place. Affordances determine what you CAN do; signifiers show you WHERE and HOW.
| Type | Definition | Example |
|---|---|---|
| Deliberate | Designed to communicate | "Push" label on door, placeholder text |
| Accidental | Unintentional but informative | Worn path in grass (people walk here) |
| Social | Other people's behavior | Line of people indicates entrance |
Digital signifiers:
| Signifier | What It Communicates | Example |
|---|---|---|
| Cursor change + hover state | This is interactive | Pointer → hand on links; button color change |
| Icons + labels | Function of the element | Magnifying glass = search; "Submit", "Cancel" |
| Color + position | Status, category, hierarchy | Red = error, green = success; close button top-right |
Design rule: When in doubt, add a signifier — better to over-communicate than leave users guessing.
See: references/signifiers.md when deciding which signifier to add to an unclear control.
Definition: The relationship between controls and their effects. Natural mapping means the spatial layout of controls matches the layout of what they control.
| Mapping Quality | Example | Why It Works/Fails |
|---|---|---|
| Natural | Volume slider (up = louder) | Matches mental model |
| Poor | Light switch panel | No spatial correspondence to lights |
| Poor | Stovetop knobs in a row | Layout doesn't match burner positions |
Digital principles: controls near what they affect, layout mirroring content, direction matching expectation (scroll down = content moves up), related controls grouped.
| Technique | How It Works | Example |
|---|---|---|
| Proximity | Control near target | Edit button next to content |
| Spatial | Layout mirrors real world | Map controls match compass directions |
| Cultural | Follows conventions | Red = stop/danger, green = go/safe |
| Sequential | Follows natural order | Steps 1, 2, 3 left to right (or top to bottom) |
See: references/mappings.md for mapping analysis exercises.
Definition: Limiting the possible actions to prevent errors.
| Type | Mechanism | Example |
|---|---|---|
| Physical | Shape/size prevents wrong action | USB plug only fits one way |
| Cultural | Social norms guide behavior | Red means stop, green means go |
| Semantic | Meaning restricts options | A rearview mirror only makes sense facing backward |
| Logical | Logic limits choices | Only one hole left for the last screw |
Digital constraints:
| Constraint | Implementation | Example |
|---|---|---|
| Input validation | Restrict what can be entered | Date picker vs. free text |
| Disabled states | Gray out unavailable options | "Submit" disabled until form valid |
| Forced sequence + undo | Steps in order; allow reversal | Wizard with locked steps; Gmail "Undo send" |
Design rule: Every constraint you add is one less error the user can make — make wrong actions impossible rather than punishing them.
See: references/constraints.md for constraint design patterns.
Definition: Communicating the results of an action back to the user. Feedback must be immediate (within 0.1s for direct manipulation), informative, appropriately dosed, and non-intrusive.
| Type | When to Use | Example |
|---|---|---|
| Visual | Most actions | Button press animation, color change, checkmark |
| Auditory | Important events, confirmations | Success chime, error sound |
| Haptic | Touch devices, confirmation | Vibration on key press |
| Progress | Long operations | Progress bar, spinner, skeleton screen |
Digital feedback patterns:
| Situation | Feedback Needed | Example |
|---|---|---|
| Form submission | Success/error message | "Saved!" toast or inline error |
| Loading | Progress indicator | Spinner, skeleton screen, percentage |
| Error | What went wrong + how to fix | "Invalid email. Please check format." |
Response times: 0.1s feels instantaneous; 1s is a noticeable delay (change cursor); 10s loses attention (show progress bar); over 10s users leave (show percentage, allow backgrounding).
Common failures: no feedback (did my click register?), delayed feedback (feels broken), unclear feedback, alert overload.
See: references/feedback.md when an action gives no clear result and you need the right feedback type and timing.
Definition: The user's mental model of how a product works.
| Model | Held By | Description |
|---|---|---|
| Design model | Designer | How the designer thinks it works |
| User's model | User | How the user thinks it works |
| System image | Product | What the product actually communicates |
Goal: The user's model should match the design model; the system image is the only bridge. Matching models let users predict outcomes and recover from errors; mismatches breed confusion, self-blame, and support calls.
Example (thermostat): design model — set a temperature, the system maintains it; common user model — higher setting heats faster (wrong), so users crank it to 90°F.
Build correct models with: familiar metaphors (desktop, trash), visible system state, clear feedback, consistent behavior, progressive disclosure.
See: references/conceptual-models.md when the user's model diverges from how the product works. For fully worked teardowns (door handles, thermostats, digital products), see references/case-studies.md.
Norman's key insight: there is no such thing as "human error" — only bad design. When someone errs, look for the design flaw, not the person's flaw.
Slips — correct intention, wrong action:
| Slip Type | Cause | Example | Design Fix |
|---|---|---|---|
| Action slip | Wrong action on right target | Click "Delete" instead of "Edit" | Separate destructive actions |
| Memory lapse | Forget step in sequence | Forget attachment after writing "attached" | Gmail's attachment reminder |
| Mode error | Right action, wrong mode | Type in caps lock | Show mode state clearly |
| Capture error | Habit overrides intention | Drive to old office on autopilot | Interrupt at decision points |
Mistakes — wrong intention, executed correctly:
| Mistake Type | Cause | Example | Design Fix |
|---|---|---|---|
| Rule-based | Apply wrong rule | Use formula for wrong situation | Provide context, confirm |
| Knowledge-based | Incomplete/wrong mental model | Misunderstand how system works | Better conceptual model |
| Memory lapse | Forget goal or plan | Forget why you opened the fridge | Reminders, history |
Prevent: constraints that make errors impossible, undo/redo everywhere, confirmation for destructive actions, sensible defaults, forgiving input. Recover: clear error messages, never erase the user's work, partial saves, easy reset to a known good state.
Error message checklist:
See: references/human-error.md for error prevention patterns.
Norman's model for how humans interact with products:
1. GOAL → "I want to adjust the temperature"
2. PLAN → "I'll use the thermostat"
3. SPECIFY → "I'll press the up arrow"
4. PERFORM → (presses button)
─── Gulf of Execution ───
5. PERCEIVE → (sees display change)
6. INTERPRET → "The number went up"
7. COMPARE → "Is this what I wanted?"
─── Gulf of Evaluation ───Design implications: support stages 1-3 with signifiers, mappings, and constraints; stage 4 with good affordances; stages 5-7 with feedback and visible state. Walk any interaction through each stage to find where users get stuck.
See: references/seven-stages.md for stage-by-stage analysis.
Observation → Idea Generation → Prototyping → Testing → (iterate)Two specifics that change how you run this loop: in Observation, don't ask users what they want (they don't know) — watch for workarounds and frustrations in real contexts. In Testing, use real users not designers — 5 reveal ~85% of problems, so observe behavior over opinions and iterate.
| Mistake | Why It Fails | Fix |
|---|---|---|
| No signifiers | Users can't find features | Add visual cues for every interactive element |
| No feedback | Users don't know if action worked | Respond to every action within 0.1s |
| Blaming users | Ignores design flaws | Look for design cause of every "user error" |
| Feature creep | Complexity overwhelms | Apply constraints, progressive disclosure |
| Inconsistency | Breaks conceptual model | Same action = same result everywhere |
| Ignoring context | Designed for ideal conditions | Observe real usage environments |
Audit any design:
| Question | If No | Action |
|---|---|---|
| Can users figure out what to do? | Poor discoverability | Add signifiers, improve affordances |
| Do users understand what happened? | Gulf of evaluation too wide | Add feedback, show system state |
| Can users recover from errors? | No error tolerance | Add undo, confirmation, clear messages |
| Does the control layout match the output? | Poor mapping | Reorganize controls to match spatial layout |
| Are impossible/irrelevant options hidden? | Missing constraints | Disable, hide, or remove invalid options |
For the complete framework:
Don Norman, PhD is co-founder of the Nielsen Norman Group, director of The Design Lab at UC San Diego, and a former VP of Advanced Technology at Apple, where he coined the term "user experience." The Design of Everyday Things (1988, revised 2013) is widely considered the most influential design book ever written and is required reading in design programs worldwide.
© wondelai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 10 other files (references) in design-everyday-things of wondelai/skills.
Open the folder on GitHubat commit c172996
Design Everyday Things 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Design Everyday Things this skillwondelai/skills | 2.4k | — | ~4k | Automated safety check: Pass | MIT | |
| Penpot Uiux Designgithub/awesome-copilot | 40k | 1 repos | ~3k | Automated safety check: Pass | MIT | |
| UI Designhashgraph-online/awesome-codex-plugins | 1.3k | — | ~904 | Automated safety check: Pass | Apache-2.0 | |
| Impeccablebestofjs/bestofjs | 3.1k | 26 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Interface Design for Dashboards and Appsholaboss-ai/holaOS | 11k | 3 repos | ~6k | Automated safety check: Pass | MIT | |
| Animategrowupanand/ConvoForm | 102 | 6 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 |
github/awesome-copilot
Comprehensive guide for creating professional UI/UX designs in Penpot using MCP tools.
hashgraph-online/awesome-codex-plugins
Design, build, or improve web and mobile interfaces using real product examples from UIZZE’s 800,000+ web and iOS screens.
bestofjs/bestofjs
A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…
holaboss-ai/holaOS
Pushes an agent past generic defaults when designing dashboards, admin panels, SaaS apps and tools, with attention to structure, type, navigation and how data is shown.
growupanand/ConvoForm
Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight.
docker/docs
Handle Hugo docs information-architecture moves: discover old vs new URLs, add front matter aliases (Phase 1), update in-repo links (Phase 2), interactive List 2 resolution and fragment validation…
wondelai/skills
Navigate the technology adoption lifecycle from early adopters to mainstream market.
wondelai/skills
Run a structured 5-day process to prototype, test, and validate product ideas with real users.
wondelai/skills
Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment).
wondelai/skills
Diagnose and fix retention problems using behavior design (B=MAP).
wondelai/skills
Design products and pricing around validated willingness to pay, from Ramanujam & Tacke's "Monetizing Innovation".
wondelai/skills
Build a scalable outbound B2B sales machine with specialized roles (SDR, AE, CSM).
Works with
Categories
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Design Everyday Things is an agent skill from wondelai/skills. Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models.
Design Everyday Things fits situations like: the user mentions why is this confusing; error prevention; discoverability; human-centered design.
Run `npx skills add wondelai/skills --skill design-everyday-things -a claude-code`. Or copy the skill folder (design-everyday-things in wondelai/skills) into .claude/skills/design-everyday-things in your project. Claude Code loads it when a task matches its description.
Run `npx skills add wondelai/skills --skill design-everyday-things -a codex`. Or copy the skill folder (design-everyday-things in wondelai/skills) into .agents/skills/design-everyday-things in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wondelai/skills --skill design-everyday-things -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/design-everyday-things, .gemini/skills/design-everyday-things, .github/skills/design-everyday-things and .opencode/skills/design-everyday-things in your project.
SKILL.md names no scripts, command-line tools or credentials: Design Everyday Things is instructions for the agent only.
SKILL.md names 1 domain. As links in the text: amazon.com. This is read from the text; nothing was executed.
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.
Design Everyday Things is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4k tokens (SKILL.md is roughly 16k 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 37k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Design Everyday Things: Penpot Uiux Design (github/awesome-copilot, 40k stars), UI Design (hashgraph-online/awesome-codex-plugins, 1.3k stars), Impeccable (bestofjs/bestofjs, 3.1k stars) and Interface Design for Dashboards and Apps (holaboss-ai/holaOS, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
wondelai (a GitHub organization) maintains it in wondelai/skills, which has 2,371 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on September 10, 2026.
Source: wondelai/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.