Talk Firtman Web MCP Agentic Web

Use when the user asks about Maximiliano Firtman's ("Maxi") AI Native DevCon talk on Web MCP and the agentic web — including questions about how Web MCP differs from MCP, exposing frontend tools to AI agents, the imperative vs declarative Web MCP APIs, tool design guidance (name/description/input schema/execute), the Chrome 149 origin trial, using Chrome DevTools MCP or Puppeteer as a bridge today, the Doom demo, or applying Firtman's "pick one high-value page state" adoption approach to current work.

9 stars 4 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add jscraik/Agent-Skills --skill talk-firtman-web-mcp-agentic-web
Manual install
git clone --depth 1 https://github.com/jscraik/Agent-Skills.git /tmp/Agent-Skills
mkdir -p ~/.claude/skills
cp -r /tmp/Agent-Skills/Plugins/aidevcon/skills/talk-firtman-web-mcp-agentic-web ~/.claude/skills/talk-firtman-web-mcp-agentic-web

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Web MCP and the Agentic Web — Maximiliano Firtman

Firtman argues that AI agents increasingly need to interact with the web, but today's techniques (HTTP fetch, browser-use plugins, computer use, screenshot inference) are slow, token-hungry, and unreliable. **Web MCP** is a proposed W3C standard (entering Chrome 149 origin trial) that lets web developers expose typed, named tools from the frontend directly to agents — replacing pixel-guessing inference with an explicit contract that has access to the full browser context (DOM, forms, sensors, session, client APIs).

## Grounding rules — MUST follow when answering

1. Before answering any specific question, read `outline.md` to locate the relevant section, then read that section of `transcript.md`.
2. When attributing words, **quote short, non-sensitive excerpts** from `transcript.md`. Never put quotation marks around paraphrased content.
3. If a claim isn't in `transcript.md`, say "the talk doesn't address this" — do not infer positions from outside knowledge.
4. Cite by transcript line range whenever possible.
Read the full skill on GitHub

Details

Skill name
talk-firtman-web-mcp-agentic-web
Path
Plugins/aidevcon/skills/talk-firtman-web-mcp-agentic-web/SKILL.md
License
Apache-2.0
Repo updated
16 November 2026

FAQ

What does the Talk Firtman Web MCP Agentic Web skill do?

Use when the user asks about Maximiliano Firtman's ("Maxi") AI Native DevCon talk on Web MCP and the agentic web — including questions about how Web MCP differs from MCP, exposing frontend tools to AI agents, the imperative vs declarative Web MCP APIs, tool design guidance (name/description/input schema/execute), the Chrome 149 origin trial, using Chrome DevTools MCP or Puppeteer as a bridge today, the Doom demo, or applying Firtman's "pick one high-value page state" adoption approach to current work.

How do I install the Talk Firtman Web MCP Agentic Web skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add jscraik/Agent-Skills --skill talk-firtman-web-mcp-agentic-web. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Talk Firtman Web MCP Agentic Web popular?

It lives in jscraik/Agent-Skills, which has 9 GitHub stars and 4 forks.

Related skills

1password

9

jscraik/Agent-Skills

Plan, diagnose, and validate 1Password CLI workflows. Use when tasks need op CLI sign-in, secret references, op run, op inject, item reads, env injection, or service-account secret access.

Security

Agentation

9

jscraik/Agent-Skills

Audit, validate, and troubleshoot Agentation integrations in frontend apps. Use when annotations, MCP registration, endpoint sync, webhook delivery, or watch mode readiness are failing.

AI, LLMs & Agents

Agents Md

9

jscraik/Agent-Skills

Use when reviewing, creating, shrinking, or refactoring AGENTS.md and directly linked instruction guidance for stale or conflicting rules against current model documentation, scoped routing, deduplication, or progressive disclosure.

AI, LLMs & Agents

Talk Groetzinger Skills Everywhere

9

jscraik/Agent-Skills

Explains Kevin Groetzinger's Skills Everywhere talk and helps teams operationalize reusable skills: trigger design, ownership, discoverability, maintenance, quality review, and adoption loops. Use when the user asks about skill design, skill rollout, skill sprawl, shared agent instructions, or making skills reliable across a team.

AI, LLMs & Agents

Talk Dubnov Merge Rate AI Adoption

9

jscraik/Agent-Skills

Answers questions about, applies frameworks from, and generates artifacts based on Tammuz Dubnov's talk "When Our PM Started Writing Code: What Merge Rate Taught Us About AI Adoption." Grounds every response in the bundled transcript and outline files. Use when a user asks about AI-native org design, merge rate measurement, non-technical contributors shipping PRs, harness engineering, zero-dev-touch rate, AI adoption ROI, or wants to audit their team against Tammuz's framework, apply his concepts to their situation, draft a measurement dashboard or checklist, or understand terms like Calamarou

AI, LLMs & Agents

Talk Jones Odevo AI Native Transformation

9

jscraik/Agent-Skills

Use when the user asks about Daniel Jones (Deejay) and Tomasz's talk "More software, faster — Odevo's AI Native transformation" — including questions about how Odevo (Sweden's third-largest private tech company, residential property management) rolled out agentic coding to its developers, the discovery → workshops → pilot → training → train-the-trainer playbook, prerequisites for adopting agentic coding (CI/CD, platform, tests, coding standards), liberating structures and TRIZ workshop techniques, context window management, the 94% AI adoption metric, the 8-years-to-3-weeks platform rewrite, s

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.