Implement
sickn33/agentic-awesome-skills
Implement a piece of work based on a PRD or set of issues. An agent skill from sickn33/agentic-awesome-skills.
Implement or repair universal website search UI, fuzzy typeahead, catalog coverage, or search responsiveness.
MITAuto-check passed
Install Website Searchbar
$ npx skills add swyxio/skills --skill website-searchbar -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install swyxio/skills website-searchbar --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/swyxio/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/website-searchbar .claude/skills/website-searchbar && 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 "website-searchbar" agent skill from https://github.com/swyxio/skills/tree/main/website-searchbar into .claude/skills/website-searchbar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "website-searchbar", 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/swyxio/skills/tree/main/website-searchbarType 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 swyxio/skills --skill website-searchbar -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install swyxio/skills website-searchbar --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/website-searchbar .agents/skills/website-searchbar && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "website-searchbar" agent skill from https://github.com/swyxio/skills/tree/main/website-searchbar into .agents/skills/website-searchbar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "website-searchbar", 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 swyxio/skills --skill website-searchbar -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install swyxio/skills website-searchbar --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/website-searchbar .cursor/skills/website-searchbar && 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 "website-searchbar" agent skill from https://github.com/swyxio/skills/tree/main/website-searchbar into .cursor/skills/website-searchbar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "website-searchbar", 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/swyxio/skills.git --path website-searchbar--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 swyxio/skills --skill website-searchbar -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install swyxio/skills website-searchbar --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/website-searchbar .gemini/skills/website-searchbar && 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 "website-searchbar" agent skill from https://github.com/swyxio/skills/tree/main/website-searchbar into .gemini/skills/website-searchbar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "website-searchbar", 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 swyxio/skills website-searchbarInstalls 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 swyxio/skills --skill website-searchbar -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/website-searchbar .github/skills/website-searchbar && 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 "website-searchbar" agent skill from https://github.com/swyxio/skills/tree/main/website-searchbar into .github/skills/website-searchbar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "website-searchbar", 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 swyxio/skills --skill website-searchbar -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install swyxio/skills website-searchbar --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/website-searchbar .opencode/skills/website-searchbar && 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 "website-searchbar" agent skill from https://github.com/swyxio/skills/tree/main/website-searchbar into .opencode/skills/website-searchbar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "website-searchbar", 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.
Facts
- Skill name
website-searchbar- GitHub stars
- 176
- Token cost
- ~1.9k tokens
- SKILL.md length
- 978 words
- Files
- 3 (incl. references)
- Skills in repo
- 89
- Repo updated
- First seen
- Licence
- MIT
At a glance
Implement or repair universal website search UI, fuzzy typeahead, catalog coverage, or search responsiveness.
- SKILL.md covers UX preferences, Architecture tradeoffs, Catalog correctness and Performance decisions, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Website Searchbar is an agent skill from swyxio/skills. Implement or repair universal website search UI, fuzzy typeahead, catalog coverage, or search responsiveness. Excludes standalone directory filtering and release engineering.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/perceived-ux.md`).
The repository describes itself as: Agent skills for Claude Code and other AI agents. The licence is MIT.
Example prompts
- “/website-searchbar”
What it can do on your machine
Read from SKILL.md and the folder at commit 038ef34. 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.
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
Website Searchbar loads about 1.9k tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 48 tokens; SKILL.md has 978 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.
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 swyxio/skills at commit 038ef34, republished under its MIT licence (© swyxio). 978 words, ~1,947 tokens.
Download SKILL.mdSave it as
.claude/skills/website-searchbar/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- website-searchbar
- description
- Implement or repair universal website search UI, fuzzy typeahead, catalog coverage, or search responsiveness. Excludes standalone directory filtering and release engineering.
Website Searchbar
Use these as preferences, not a mandatory feature checklist. Honor the user's requirements and the site's existing interaction contract. Choose tradeoffs according to catalog size, browser cost, freshness needs, and web/server architecture; explain material departures from the defaults. Correctness, authorization, and preservation of user input remain requirements.
UX preferences
- Let desktop search fill available header space without squeezing branding/navigation. Grow both its slot and trigger (
flex: 1; min-width: 0); compact it when space is genuinely limited. A field-like trigger may open the shared dialog rather than duplicate the input. - Prefer a compact mobile trigger, roughly 44px tap targets, and 16px input text. Keep input and dismissal reachable at keyboard-reduced height; reuse library viewport sizing or dynamic viewport units before adding custom machinery. Scrollable type chips can save height; retain clear access to hidden filters.
- Prefer
/and Cmd/Ctrl+K. Guard/while typing and all shortcuts during composition or another dialog. Support arrows/Enter, Esc/backdrop dismissal with focus restoration, and touch navigation. Use established accessible primitives appropriate to the framework: React Aria is a React option, not a requirement for other stacks. - Open results directly at canonical pages. Preserve existing directory filters and theme/brand conventions. Prefer immediate common destinations derived from existing registries, with explicit partial/loading/error states rather than an empty-looking dialog.
- For name/title search, normally disable autocorrection/capitalization. Preserve input focus when filtering or scrolling suggestions; deliberately navigating or dismissing may leave it. Query changes should reveal leading results after an earlier scroll.
- Use URL-addressable full results and facets when useful for the site's size and content model. A small site may need only suggestions. Preserve edits and back/forward behavior when synchronizing query state with the URL.
Architecture tradeoffs
Prefer existing loaders, dependencies, and hosting. MiniSearch and uFuzzy are examples of suitable fuzzy-search libraries; choose according to the current stack and ranking needs.
| Approach | Acceptable tradeoff |
|---|---|
| Client catalog | Transfer, parse, memory, and indexing cost buys local low-latency suggestions. Fits bounded catalogs and static hosting; load on intent when the payload is substantial. |
| Existing server search | Small browser payload buys network latency and possible cold initialization. Fits larger/dynamic catalogs, server-held authorization, and richer facets. |
| Hybrid | Instant common paths or local suggestions plus server-side complete results/facets. Useful when browser and backend serve different latency or query needs. |
A dedicated service can be appropriate for demonstrated scale or query requirements, but is not a prerequisite. Static catalogs can follow the existing build/publication lifecycle. Do not impose Workers, D1, a database, or an indexing service merely to add search.
Catalog correctness
For catalog implementation or repair, trace authoritative published-page metadata, not just a loader named “search.” Related hits and plausible totals can conceal missing canonical pages.
- Compare searchable published identities/URLs with indexed documents. Merge missing public metadata and deduplicate within entity type by canonical identity; prefer current page titles/descriptions while preserving confirmed aliases, relationships, and facets.
- Use coverage checks derived from actual published metadata, alongside synthetic ranking tests. Verify canonical inclusion and appropriate exact-title/type-filtered retrieval, overlap precedence, and affected facets. Inspect missing inclusion before tuning fuzziness; do not assume another entity type has the same defect.
- Refresh against every contributing source's versions/cache policy. Share initialization and reuse warm indexes when applicable, without indefinite staleness or mixing incompatible publication versions. Query cancellation must not abort initialization still shared by other consumers.
- Search only data authorized for the caller. Public/downloadable catalogs must exclude private fields and raw records; normally project IDs, types, URLs, titles, aliases, concise summaries, and needed facets. Summaries rather than transcripts are the default scope. A cached index does not replace authorization.
- Prefer exact names/titles ahead of prefixes and bounded fuzzy matches. Preserve distinct identities for duplicate names, handle Unicode, and share ranking/projection semantics when browser and backend both search.
Show full SKILL.md (363 more words)Show less
Performance decisions
For responsiveness work, separate dialog opening from suggestion latency: chunk loading → paint/focus versus debounce → network/catalog initialization → indexing/ranking → result paint. Optimize the measured stage rather than assuming fuzziness is expensive.
For a perceived-speed or discovery refinement pass on an already-working search, read references/perceived-ux.md. It covers destination prefetch, navigation feedback, recent destinations, and popularity signals. Choose improvements from observed friction; this is not a required feature checklist for ordinary search fixes.
- Keep heavier UI lazy when beneficial; preload on focus/hover/touch intent, or during idle if opening latency warrants it. Tiny interfaces may reasonably ship eagerly. Opening must work without a completed preload.
- A shared catalog download can remove per-query round trips. Measure compressed bytes, parse/index time, memory, and phone long tasks before choosing it; no fixed catalog count or byte threshold proves suitability. Show useful local matches while fuller coverage initializes, and yield index construction in batches if it blocks typing.
- Remote typeahead commonly starts after two characters with about 150ms debounce; tune this to the product. Local suggestions need not inherit network pacing. Guard stale responses and prevent hydration/URL updates from overwriting active edits; aborting requests alone is insufficient.
- Measure initial JavaScript, lazy UI, catalog transfer, and cold/warm user-visible latency separately. Keep environment/cache conditions comparable. Node ranking, warmed local opening, and uncontrolled first production observations are not equivalent measurements; zero timer readings do not prove zero work.
Scope-dependent acceptance
Apply checks that can change acceptance of the requested outcome:
- UX changes: Exercise the affected desktop/mobile loop, navigation, typing, focus, and viewport fit. Use touch gestures for touch claims; check short/landscape layouts when overlays change. Emulation does not establish native-phone keyboard behavior.
- Catalog changes: Verify published coverage, canonical retrieval, and affected ranking/facets. When exposure or authorization changes, verify the intended projection and access boundary.
- Performance changes: Demonstrate the requested improvement under comparable conditions without breaking the affected interaction. Broader device, theme, or architecture studies are follow-up unless their risk is introduced by this change.
Stop when the named outcome and checks for risks introduced by the change pass. A layout adjustment does not require a catalog audit, a catalog repair does not require new infrastructure, and this skill adds no separate release gates.
© swyxio, MIT. 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 2 other files (references) in website-searchbar of swyxio/skills.
- SKILL.md
- agents/openai.yaml
- references/perceived-ux.md
Open the folder on GitHubat commit 038ef34
Compare with similar skills
Website Searchbar 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 |
|---|---|---|---|---|---|---|
| Website Searchbar this skillswyxio/skills | 176 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Implementsickn33/agentic-awesome-skills | 47k | 5 repos | ~306 | Automated safety check: Pass | MIT | |
| Implementcodewhale-hq/Codewhale | 41k | — | ~190 | Automated safety check: Pass | MIT | |
| Website Searchthedaviddias/Front-End-Checklist | 74k | — | ~556 | Automated safety check: Pass | MIT | |
| Implement Universaliusztinpaul/designing-real-world-ai-agents-workshop | 512 | — | ~5.6k | Automated safety check: Pass | MIT | |
| Openclaw Repair Sweepopenclaw/openclaw | 392k | — | ~1.8k | Automated safety check: Pass | MIT |
Similar skills
Implement
codewhale-hq/Codewhale
Carry an authorized, defined request or approved plan through scoped edits and proportionate verification.
Website Search
thedaviddias/Front-End-Checklist
A skill your agent uses when applies to sites with internal site search functionality.
Implement Universal
iusztinpaul/designing-real-world-ai-agents-workshop
Harness-agnostic version of /implement. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop.
Openclaw Repair Sweep
openclaw/openclaw
Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.
Incremental Implementation
addyosmani/agent-skills
Delivers a change in thin vertical slices, each implemented, tested, verified and committed before the next, using vertical, contract-first or risk-first slicing.
More from swyxio/skills
All 89 skills in this repoProgrammatic Agents
swyxio/skills
Run a selected coding-agent CLI programmatically, with latency, error, usage, cost, and trace logging.
Reserved Handle Policy
swyxio/skills
Design, implement, audit, or refresh protected username and handle namespaces for public products.
New Mac Setup
swyxio/skills
Fully automated new Mac setup for fullstack web developers and AI engineers.
Youtube API
swyxio/skills
Manage YouTube videos programmatically via the YouTube Data API v3 — upload video files, upload custom thumbnails, update video metadata (titles, descriptions, tags), and query video/channel info…
Youtube Studio Batch Upload
swyxio/skills
Batch YouTube Studio upload workflow for videos sourced from Airtable, Google Drive, Loom, YouTube, or local files.
Deep Trajectory Analysis
swyxio/skills
Reconstruct and visually analyze paired agent, game, or policy trajectories to determine whether changed actions produced their intended effects.
Questions about Website Searchbar
What does Website Searchbar do?
Implement or repair universal website search UI, fuzzy typeahead, catalog coverage, or search responsiveness. Website Searchbar is an agent skill from swyxio/skills. Implement or repair universal website search UI, fuzzy typeahead, catalog coverage, or search responsiveness.
How do I install Website Searchbar in Claude Code?
Run `npx skills add swyxio/skills --skill website-searchbar -a claude-code`. Or copy the skill folder (website-searchbar in swyxio/skills) into .claude/skills/website-searchbar in your project. Claude Code loads it when a task matches its description.
How do I install Website Searchbar in Codex?
Run `npx skills add swyxio/skills --skill website-searchbar -a codex`. Or copy the skill folder (website-searchbar in swyxio/skills) into .agents/skills/website-searchbar in your project. Codex loads it when a task matches its description.
Can I use Website Searchbar 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 swyxio/skills --skill website-searchbar -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/website-searchbar, .gemini/skills/website-searchbar, .github/skills/website-searchbar and .opencode/skills/website-searchbar in your project.
What does Website Searchbar need to run?
SKILL.md names no scripts, command-line tools or credentials: Website Searchbar is instructions for the agent only.
Does Website Searchbar 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 Website Searchbar 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 Website Searchbar use?
Website Searchbar is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Website Searchbar use?
About 1.9k tokens (SKILL.md is roughly 7.8k 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 1.4k tokens, read only when the agent opens those files.
What are the alternatives to Website Searchbar?
Skills that share tags, products or a category with Website Searchbar: Implement (sickn33/agentic-awesome-skills, 47k stars), Implement (codewhale-hq/Codewhale, 41k stars), Website Search (thedaviddias/Front-End-Checklist, 74k stars) and Implement Universal (iusztinpaul/designing-real-world-ai-agents-workshop, 512 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Website Searchbar?
swyxio (a GitHub user) maintains it in swyxio/skills, which has 176 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 5, 2026.
Source: swyxio/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.