Coss
crafter-station/petdex
Helps implement coss UI components correctly. An agent skill from crafter-station/petdex.
Frontend specialist for React, Next.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment.
Install Oma Frontend
$ npx skills add first-fluke/oh-my-agent --skill oma-frontend -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install first-fluke/oh-my-agent oma-frontend --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/first-fluke/oh-my-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/runs/oma/.agents/skills/oma-frontend .claude/skills/oma-frontend && 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 "oma-frontend" agent skill from https://github.com/first-fluke/oh-my-agent/tree/main/benchmarks/runs/oma/.agents/skills/oma-frontend into .claude/skills/oma-frontend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oma-frontend", 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/first-fluke/oh-my-agent/tree/main/benchmarks/runs/oma/.agents/skills/oma-frontendType 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 first-fluke/oh-my-agent --skill oma-frontend -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install first-fluke/oh-my-agent oma-frontend --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/first-fluke/oh-my-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/benchmarks/runs/oma/.agents/skills/oma-frontend .agents/skills/oma-frontend && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "oma-frontend" agent skill from https://github.com/first-fluke/oh-my-agent/tree/main/benchmarks/runs/oma/.agents/skills/oma-frontend into .agents/skills/oma-frontend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oma-frontend", 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 first-fluke/oh-my-agent --skill oma-frontend -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install first-fluke/oh-my-agent oma-frontend --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/first-fluke/oh-my-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/benchmarks/runs/oma/.agents/skills/oma-frontend .cursor/skills/oma-frontend && 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 "oma-frontend" agent skill from https://github.com/first-fluke/oh-my-agent/tree/main/benchmarks/runs/oma/.agents/skills/oma-frontend into .cursor/skills/oma-frontend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oma-frontend", 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/first-fluke/oh-my-agent.git --path benchmarks/runs/oma/.agents/skills/oma-frontend--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 first-fluke/oh-my-agent --skill oma-frontend -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install first-fluke/oh-my-agent oma-frontend --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/first-fluke/oh-my-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/benchmarks/runs/oma/.agents/skills/oma-frontend .gemini/skills/oma-frontend && 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 "oma-frontend" agent skill from https://github.com/first-fluke/oh-my-agent/tree/main/benchmarks/runs/oma/.agents/skills/oma-frontend into .gemini/skills/oma-frontend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oma-frontend", 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 first-fluke/oh-my-agent oma-frontendInstalls 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 first-fluke/oh-my-agent --skill oma-frontend -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/first-fluke/oh-my-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/benchmarks/runs/oma/.agents/skills/oma-frontend .github/skills/oma-frontend && 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 "oma-frontend" agent skill from https://github.com/first-fluke/oh-my-agent/tree/main/benchmarks/runs/oma/.agents/skills/oma-frontend into .github/skills/oma-frontend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oma-frontend", 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 first-fluke/oh-my-agent --skill oma-frontend -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install first-fluke/oh-my-agent oma-frontend --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/first-fluke/oh-my-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/benchmarks/runs/oma/.agents/skills/oma-frontend .opencode/skills/oma-frontend && 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 "oma-frontend" agent skill from https://github.com/first-fluke/oh-my-agent/tree/main/benchmarks/runs/oma/.agents/skills/oma-frontend into .opencode/skills/oma-frontend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oma-frontend", 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
oma-frontend- GitHub stars
- 1.3k
- Token cost
- ~2.5k tokens
- SKILL.md length
- 1,075 words
- Files
- 9
- Skills in repo
- 57
- Repo updated
- First seen
- Licence
- MIT
At a glance
Frontend specialist for React, Next.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment.
- Works in 3 steps: Identify target route, component, state… → Read existing patterns before adding… → Determine whether work belongs in Server…
- Tasks that involve Design systems
- SKILL.md covers Scheduling, Structural Flow and Logical Operations
- Calls rg
What it does
Oma Frontend is an agent skill from first-fluke/oh-my-agent. Frontend specialist for React, Next.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Use for UI, component, page, layout, CSS, Tailwind, and shadcn work.
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files (for example `resources/checklist.md`, `resources/error-playbook.md` and `resources/examples.md`).
It sits in Frontend & Design, covering Design systems and CSS and styling. It works with shadcn/ui, Tailwind CSS, Next.js and React. The repository describes itself as: Mechanical verification for AI coding agents — skills pack or full harness (stop-hook gates, artifact checks, independent judges). The licence is MIT.
When your agent uses it
- Tasks that involve Design systems
- Tasks that involve CSS and styling
Example prompts
- “/oma-frontend”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Identify target route, component, state boundary, and design-system constraints.
- Read existing patterns before adding components or utilities.
- Determine whether work belongs in Server Components, Client Components, wrappers, hooks, or styles.
What it can do on your machine
Read from SKILL.md and the folder at commit b364119. 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:
rg
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
Oma Frontend loads about 2.5k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 1,075 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 first-fluke/oh-my-agent at commit b364119, republished under its MIT licence (© first-fluke). 1,075 words, ~2,465 tokens.
Download SKILL.mdSave it as
.claude/skills/oma-frontend/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- oma-frontend
- description
- Frontend specialist for React, Next.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Use for UI, component, page, layout, CSS, Tailwind, and shadcn work.
Frontend Agent - UI/UX Specialist
Scheduling
Goal
Build, modify, and verify React/Next.js/TypeScript user interfaces that follow project architecture, design-system constraints, accessibility expectations, and existing frontend conventions.
Intent signature
- User asks for UI, component, page, layout, CSS, Tailwind, shadcn, form, interaction, client state, or frontend API integration work.
- User needs browser-facing implementation in a React/Next.js TypeScript codebase.
When to use
- Building user interfaces and components
- Client-side logic and state management
- Styling and responsive design
- Form validation and user interactions
- Integrating with backend APIs
When NOT to use
- Backend API implementation → use Backend Agent
- Database access, migrations, or ORM setup → use Backend Agent
- Auth server setup (better-auth server library, DB adapters) → use Backend Agent
- Native mobile development → use Mobile Agent
Expected inputs
- Target page, component, flow, or UI behavior
- Existing app structure, design tokens, component library, i18n files, and API contracts
- Acceptance criteria and target responsive states
Expected outputs
- Frontend code changes in pages, components, hooks, styles, tests, or wrappers
- UI that respects project tokens, i18n, server/client boundaries, and accessibility expectations
- Verification results from relevant lint, typecheck, tests, or browser checks
Dependencies
- React, Next.js, TypeScript, TailwindCSS v4, and
shadcn/ui - Project sources of truth such as
packages/design-tokens,packages/i18n, and shared utilities resources/execution-protocol.md,resources/checklist.md, examples, snippets, and Tailwind rules
Control-flow features
- Branches by server/client component boundary, responsive state, component library availability, and i18n/token requirements
- Reads and writes frontend codebase files
- May call shadcn registry tools or local verification commands
Structural Flow
Entry
- Identify target route, component, state boundary, and design-system constraints.
- Read existing patterns before adding components or utilities.
- Determine whether work belongs in Server Components, Client Components, wrappers, hooks, or styles.
Scenes
- PREPARE: Load relevant project conventions, UI requirements, and acceptance criteria.
- ACQUIRE: Inspect existing components, tokens, i18n keys, APIs, and shadcn availability.
- ACT: Implement UI, state, styles, validation, and integration.
- VERIFY: Run checklist, automated checks, and browser/responsive validation when applicable.
- FINALIZE: Summarize changed UI behavior and verification.
Transitions
- If a strict shadcn primitive exists, use or wrap it before creating generic markup.
- If UI text is user-facing and i18n exists, add strings through the i18n source of truth.
- If interaction or hooks are needed, mark the boundary as Client Component.
- If backend contracts are missing, coordinate with backend/API planning.
Failure and recovery
- If design tokens or i18n sources are missing, state assumptions and follow existing local patterns.
- If verification fails, fix before handoff or report the blocker.
- If required shadcn registry access fails, use existing local components or document fallback.
Exit
- Success: UI works across target responsive states and passes relevant checks.
- Partial success: missing assets, backend contracts, or verification gaps are explicit.
Logical Operations
Actions
| Action | SSL primitive | Evidence |
|---|---|---|
| Inspect existing frontend patterns | READ | Components, routes, hooks, styles |
| Select component and state approach | SELECT | Server/client and shadcn workflow |
| Implement UI code | WRITE | TSX, CSS, hooks, wrappers |
| Validate form/data contracts | VALIDATE | Zod/forms/API schemas |
| Call shadcn or verification tools | CALL_TOOL | Registry, lint, typecheck, tests |
| Compare responsive states | COMPARE | Desktop/mobile behavior |
| Report result | NOTIFY | Final summary |
Tools and instruments
- React, Next.js, TypeScript, TailwindCSS v4, shadcn/ui
ahooks,es-toolkit,nuqs, TanStack Query, Jotai, TanStack React Form,zod- Lint, typecheck, tests, and browser inspection when applicable
Canonical workflow path
rg --files
rg "components/ui|shadcn|use client|generateMetadata|useQuery|i18n|design-tokens" .Then run the project's frontend verification commands, typically lint, typecheck, tests, and browser/responsive checks when the UI changes.
Resource scope
| Scope | Resource target |
|---|---|
CODEBASE | Frontend routes, components, styles, hooks, tests |
LOCAL_FS | Design tokens, i18n files, resource references |
PROCESS | Build, lint, typecheck, test, browser commands |
NETWORK | Backend APIs or registry tools when required |
Preconditions
- Target UI behavior and affected frontend area are identifiable.
- Required design tokens, i18n, and API contracts are available or assumptions are stated.
Effects and side effects
- Mutates frontend source, styles, tests, and possibly i18n keys.
- May add dependencies or shadcn components only when justified by project conventions.
- Does not edit
components/ui/*directly.
Show full SKILL.md (441 more words)Show less
Guardrails
- Follow the existing React, Next.js, TypeScript, and FSD-lite architecture in the target project.
- Use
shadcn/uiprimitives and wrappers for UI work; treatcomponents/ui/*as read-only. - Keep server/client boundaries explicit: Server Components for static/layout work, Client Components for interaction and hooks.
- Use project sources of truth for design tokens, i18n strings, and shared utilities before adding local alternatives.
- Run the execution checklist before handoff and include relevant verification results.
- Next.js 16
proxy.tsis mandatory;middleware.tsis BANNED: this project is Next.js 16+.middleware.tsis NOT "deprecated" — it is forbidden, touch it and you die. The canonical request-proxy / auth-gate file isproxy.ts(root orsrc/) exporting aproxyfunction. NEVER create, recommend, suggest, or "restore"middleware.ts. NEVER flagproxy.tsas dead code, unused, or not-wired. Any such finding is a fatal self-error — retract it immediately and writeproxy.ts.
Libraries
| Category | Library |
|---|---|
| Framework | next@16+ (App Router) + react@19+ — next < 16 is BANNED |
| Date | luxon |
| Styling | TailwindCSS v4 + shadcn/ui |
| Hooks | ahooks (pre-made hooks preferred) |
| Utils | es-toolkit (first choice) |
| State (URL) | nuqs |
| State (Server) | TanStack Query |
| State (Client) | Jotai (minimize use) |
| Forms | @tanstack/react-form + zod |
| Auth | better-auth (client SDK only — never import server library or database adapters) |
| Animation | motion — import from motion/react. framer-motion (legacy package name) is BANNED. |
Shadcn Workflow
- Search:
shadcn_search_items_in_registries - Review:
shadcn_get_item_examples_from_registries - Install:
shadcn_get_add_command_for_items
Server vs Client Components
- Server Components: Layouts, marketing pages, SEO metadata (
generateMetadata,sitemap) - Client Components: Interactive features and
useQueryhooks
UI Implementation (Shadcn/UI)
- Usage: Prefer strict shadcn primitives (
Card,Sheet,Typography,Table) overdivor generic classes. - Responsiveness: Use
Drawer(mobile) vsDialog(desktop) viauseResponsive. - Customization: Treat
components/ui/*as read-only. Create wrappers (e.g.,components/common/ProductButton.tsx) or usecvacomposition. Never editcomponents/ui/button.tsxdirectly.
Sources of Truth
- DESIGN.md (project root): visual system source of truth — read Section 9 (Agent Prompt Guide) verbatim for component prompts when present
- Design Tokens:
packages/design-tokens(OKLCH) — never hardcode colors - i18n strings:
packages/i18n— never hardcode UI text - Custom utilities: check
es-toolkitfirst; if implementing custom logic, >90% unit test coverage is mandatory
Designer Collaboration
- Sync: Map code variables to Figma layer names
- UX: Ensure key actions are visible "Above the Fold"
References
- Follow
resources/execution-protocol.mdstep by step. - See
resources/examples.mdfor input/output examples. - Before submitting, run
resources/checklist.md. Vendor-specific execution protocols are injected automatically byoma agent:spawn. Source files live under../_shared/runtime/execution-protocols/{vendor}.md.
- Project frontend rules (MUST load before review/implementation):
../../rules/frontend.md - Tech stack & Serena shortcuts:
resources/tech-stack.md - Execution steps:
resources/execution-protocol.md - Code examples:
resources/examples.md - Code snippets:
resources/snippets.md - Checklist:
resources/checklist.md - Error recovery:
resources/error-playbook.md - Component template:
resources/component-template.tsx - Tailwind rules:
resources/tailwind-rules.md - Context loading:
../_shared/core/context-loading.md - Reasoning templates:
../_shared/core/reasoning-templates.md - Clarification:
../_shared/core/clarification-protocol.md - Context budget:
../_shared/core/context-budget.md - Lessons learned:
../_shared/core/lessons-learned.md
[!IMPORTANT] Treat
components/ui/*as read-only. Create wrappers for customization.
© first-fluke, 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 8 other files in benchmarks/runs/oma/.agents/skills/oma-frontend of first-fluke/oh-my-agent.
- SKILL.md
- resources/checklist.md
- resources/component-template.tsx
- resources/error-playbook.md
- resources/examples.md
- resources/execution-protocol.md
- resources/snippets.md
- resources/tailwind-rules.md
- resources/tech-stack.md
Open the folder on GitHubat commit b364119
Compare with similar skills
Oma Frontend 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 |
|---|---|---|---|---|---|---|
| Oma Frontend this skillfirst-fluke/oh-my-agent | 1.3k | — | ~2.5k | Automated safety check: Pass | MIT | |
| Cosscrafter-station/petdex | 4.2k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Ss Learnbitjaru/styleseed | 974 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Styleseedbitjaru/styleseed | 974 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Shadcn Tailwind UILiarMTTT/TavernWeave | 153 | — | ~1.7k | Automated safety check: Pass | Custom licence | |
| Redesign My Landingpageinstructa/agent-skills | 139 | — | ~1.8k | Automated safety check: Pass | None |
Similar skills
Ss Learn
bitjaru/styleseed
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or…
Styleseed
bitjaru/styleseed
Build, improve, or inspect UI with StyleSeed. An agent skill from bitjaru/styleseed.
Shadcn Tailwind UI
LiarMTTT/TavernWeave
Build, restyle, or review accessible React interfaces that use shadcn/ui, Radix UI primitives, and Tailwind CSS.
Redesign My Landingpage
instructa/agent-skills
Build, critique, and iterate high-converting marketing or product landing pages using React + Vite + TypeScript + Tailwind and shadcn/ui components, with all icons sourced from Iconify.
Frontend Development
avibebuilder/claude-prime
A skill your agent uses for ANY work involving React, Next.js, TypeScript, or Tailwind in the browser layer.
More from first-fluke/oh-my-agent
All 57 skills in this repoOMA Multi-Agent Orchestration
first-fluke/oh-my-agent
Decomposes a complex feature into tasks, dispatches parallel specialist agents with durable state, and supervises verification, QA review and retries.
OMA Multi-Agent Orchestrator
first-fluke/oh-my-agent
Splits a complex feature into prioritized tasks, spawns specialist CLI subagents in parallel, tracks them through shared memory and verifies each result.
Architecture Decisions and ADRs
first-fluke/oh-my-agent
Evaluates system boundaries and tradeoffs and writes architecture recommendations, option comparisons or ADRs, with a Mermaid diagram when structure changes.
OMA Backend Agent
first-fluke/oh-my-agent
Backend specialist for APIs, database work, authentication and migrations that follows clean architecture with router, service and repository layers.
oma Bootstrap
first-fluke/oh-my-agent
Installs or checks the oma CLI and its runtimes (bun, uv, serena) in a fresh workspace so that oma-* skills can run their commands.
Design-First Brainstorm
first-fluke/oh-my-agent
Explores intent, constraints and alternative approaches before any planning, working through questions one at a time and saving an approved design for later steps.
Related
Categories
Questions about Oma Frontend
What does Oma Frontend do?
Frontend specialist for React, Next.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Oma Frontend is an agent skill from first-fluke/oh-my-agent.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment.
When should I use Oma Frontend?
Oma Frontend fits situations like: tasks that involve Design systems; tasks that involve CSS and styling.
How do I install Oma Frontend in Claude Code?
Run `npx skills add first-fluke/oh-my-agent --skill oma-frontend -a claude-code`. Or copy the skill folder (benchmarks/runs/oma/.agents/skills/oma-frontend in first-fluke/oh-my-agent) into .claude/skills/oma-frontend in your project. Claude Code loads it when a task matches its description.
How do I install Oma Frontend in Codex?
Run `npx skills add first-fluke/oh-my-agent --skill oma-frontend -a codex`. Or copy the skill folder (benchmarks/runs/oma/.agents/skills/oma-frontend in first-fluke/oh-my-agent) into .agents/skills/oma-frontend in your project. Codex loads it when a task matches its description.
Can I use Oma Frontend 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 first-fluke/oh-my-agent --skill oma-frontend -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/oma-frontend, .gemini/skills/oma-frontend, .github/skills/oma-frontend and .opencode/skills/oma-frontend in your project.
What does Oma Frontend need to run?
Going by SKILL.md and its folder, Oma Frontend needs the command-line tools its instructions call (rg).
Does Oma Frontend 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 Oma Frontend 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 Oma Frontend use?
Oma Frontend 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 Oma Frontend use?
About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Oma Frontend?
Skills that share tags, products or a category with Oma Frontend: Coss (crafter-station/petdex, 4.2k stars), Ss Learn (bitjaru/styleseed, 974 stars), Styleseed (bitjaru/styleseed, 974 stars) and Shadcn Tailwind UI (LiarMTTT/TavernWeave, 153 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Oma Frontend?
first-fluke (a GitHub organization) maintains it in first-fluke/oh-my-agent, which has 1,338 GitHub stars. The repository holds 57 skills in this directory. The repository was last updated on October 9, 2026.
Source: first-fluke/oh-my-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.