Htmx
Use when the user asks about htmx, hx-get, hx-post, hx-swap, hx-target, hypermedia/HATEOAS apps or server-driven partial page updates. Produces htmx attributes, HTML-fragment server responses and CSRF-safe request handling. Not for client-side reactivity inside a page (use alpinejs).
Install
npx skills add j4flmao/agent-skills --skill htmxgit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/frontend/htmx ~/.claude/skills/htmxPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# htmx ## Purpose Build hypermedia-driven web applications where the server sends HTML fragments in response to AJAX requests triggered by HTML attributes — no JavaScript required. ## Agent Protocol ### Trigger Exact user phrases: "htmx setup", "htmx project", "htmx hx-get", "htmx hx-post", "htmx HATEOAS", "htmx hypermedia", "htmx server", "htmx ajax", "hypermedia app". ### Input Context Before activating, verify: - htmx is included (CDN script or npm). - What backend framework is used (Django, Rails, Go, Laravel, etc.). ### Output Artifact No file output. Produces HTML snippets with htmx attributes as text. ### Response Format HTML with htmx attributes: ```html <button hx-get="/api/data" hx-target="#result" hx-swap="innerHTML"> Load Data </button> <div id="result"></div> ``` No preamble. No postamble. No explanations. Compress output — why use many token when few do trick. ### Completion Criteria - [ ] AJAX requests use hx-get, hx-post, hx-put, hx-patch, or hx-delete. - [ ] Responses are HTML fragments, not JSON. - [ ] Target element specified with hx-target or defaults to the triggering element. - [ ] Swap strategy chosen: innerHTML, outerHTML, beforebegin, afterbegin, beforeend, afterend. - [ ] HATEOAS: server returns next-available actions as hypermedia links. - [ ] History and URL updates via hx-push-url or hx-replace-url. - [ ] Validation and feedback via hx-trigger, hx-indicator, hx-disable. ### Max Response Length ~4096 tokens.
Details
- Skill name
htmx- Repository
- j4flmao/agent-skills
- Path
skills/frontend/htmx/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Htmx skill do?
Use when the user asks about htmx, hx-get, hx-post, hx-swap, hx-target, hypermedia/HATEOAS apps or server-driven partial page updates. Produces htmx attributes, HTML-fragment server responses and CSRF-safe request handling. Not for client-side reactivity inside a page (use alpinejs).
How do I install the Htmx skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill htmx. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Htmx popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Input Systems
45j4flmao/agent-skills
Use when the user asks about a game input system, action mapping, key rebinding, gamepad input, touch gestures, IME text input, haptics or input latency. Produces device-agnostic input architecture tied to the simulation tick. Not for menu accessibility audits (use design-accessibility) or Unity-specific setup (use unity).
Frontend Web Components
45j4flmao/agent-skills
Use when the user asks about custom elements, shadow DOM, slots and templates, ElementInternals, form-associated elements, declarative shadow DOM or framework-free cross-framework components. Produces standards-based web components. Not for Lit (use frontend-lit) or Stencil (use stencil).
Nextjs Internals
45j4flmao/agent-skills
Use when the user asks why a Next.js route is dynamic, how the App Router renders and streams, the RSC payload, partial prerendering, Cache Components / 'use cache', the router cache or the request lifecycle. Produces a diagnosis of static vs dynamic rendering and stale data in Next.js 15/16. Not for everyday App Router features (use react-nextjs).
Browse the most popular Claude skills, all frontend & design skills, or write your own with the skills generator.