01 MCP server

Let your agent ask which skill to use, then hand it over.

An open, read-only MCP server over all 51 book-based skills and 14 guided journeys. It routes a task to the right framework, tells your agent which ones to skip and why, and serves the real SKILL.md in-session. No install, no account, no auth.

POST https://skills.wondel.ai/mcp
5 tools · read-only No install · no account · no auth Streamable HTTP Stateless · 2026-07-28 revision

02 The round trip

One task in,
the right method out

  1. 01 your task “our landing page gets traffic but nobody signs up”
  2. 02 recommend_skills which frameworks to load, and which to skip, whenever a skill’s own “not for” line rules it out
  3. 03 load_skill the upstream SKILL.md, ready to follow in this session
  4. 04 your agent works applying the method instead of improvising one

Nothing is installed and nothing is cached on your side. Steps 02 and 03 are two ordinary tool calls, and your agent decides whether to make them.

wondel-skills · read-only
→ recommend_skills task: “our landing page gets traffic but nobody signs up” LOAD cro-methodology — Traffic is healthy, the funnel leaks, and nobody can say at which step or for what reason. LOAD influence-psychology — Your homepage shows testimonials and a logo bar but nothing that tells a stranger why credible people trust you. SKIP one-page-marketing — not for: One square is the entire problem — go straight to the specialist, like Scorecard Marketing for lead capture.

Every verdict quotes the skill’s own hand-written “use when” or “not for” line, so the routing changes when the skill does.

03 Connect it

Streamable HTTP,
one URL, nothing to configure.

Claude Code

claude mcp add --transport http wondel-skills https://skills.wondel.ai/mcp

Any mcpServers client

{ "mcpServers": { "wondel-skills": { "type": "http", "url": "https://skills.wondel.ai/mcp" } } }

04 The surface

5 tools

Every one is read-only and annotated as such, so clients can call them without asking you first. Start with recommend_skills when you have a task and search_skills when you have a keyword.

01 search_skills query, kind?, category?, limit? Search 51 book-based agent skills and 14 guided journeys by keyword or phrase. Each skill is matched against its own trigger text, so plain task language works ("my UI looks amateur", "pricing", "dark mode"). Returns compact hits, each quoting the line that matched. Use recommend_skills instead when you have a task rather than a keyword.
02 recommend_skills task, stack?, phase?, max? Route a task to the right skills. Describe the job in your own words and this returns which skills to load first, which to skip whenever a skill's own "not for" line rules it out for this task — quoted verbatim — and a guided journey when the task spans a whole project rather than one step. This is the tool to reach for first.
03 get_skill slug, sections? Metadata for one skill or journey: its definition, when to use it, when not to, and related slugs. Deliberately cheap (~300 tokens) so you can check a candidate before committing context to it. Pass sections to widen, or sections:["all"] for the whole page. This does not return the skill instructions — load_skill does.
04 load_skill slug, part? The skill's actual instructions — the upstream SKILL.md, ready to follow in this session with nothing installed. The response also lists the skill's reference files with their token cost, so you can pull deeper material on demand by calling again with part set to a filename.
05 get_journey slug? | goal? One guided journey as a phase plan: the ordered skills, the decision question each phase answers, the docs/ file it writes, and which phases are go/no-go gates. Pass slug for a known journey, or goal to have one picked.

Resources, for clients that attach context directly instead of calling tools: wondel://catalog (An index of all 65 skills and journeys in one ~15 KB JSON read — slug, name, one-liner, category. Use it to see what exists; get_skill returns when-to-use detail for the few you care about), wondel://journeys (The 14 guided journeys with their full phase plans, artifacts and gates), skill://{slug} (One skill's upstream SKILL.md. Enumerable and slug-completable, so clients can offer all 65 by name), skill://{slug}/references/{file} (A skill's deep-dive reference — the progressive-disclosure layer under SKILL.md). The skill:// template is enumerable and slug-completable, so all 65 show up by name.

16 prompts. In clients that surface MCP prompts as slash commands, each guided journey becomes one (/create-business, /create-website, /create-app, /improve-business, /improve-website, /improve-app, /grow-business, /grow-website, /grow-app, /improve-code-quality, /remove-technical-debt, /design-code-architecture, /conversion-optimization, /architecture-optimization) that walks you phase by phase, asks the decision question at each step, and writes the answers to your docs/ folder. Plus /pick-skill (task): Hands the model the full catalog and asks it to choose and load the right skill for a task you describe. Plus /audit-with (slug, target): Loads a named skill and applies it as an audit to a file, directory or URL.

Each tool also takes a context string, one line on the task you are solving. It never reaches the tool, it is stripped before the handler runs; it is there so the usage numbers say what agents came here to do rather than only which tool they pressed. Leave it out and the call still works. What we record per call (tool, arguments, a truncated result, duration, your client’s user agent) goes to our own PostHog on EU servers. No account, no auth, no cookie, and nothing that identifies you beyond that.

05 The honest case

We argue skills usually beat MCP.
So why this?

Our own explainer on skills versus MCP makes the case that a skill is instruction and MCP is connection, and that reaching for a server when your agent can already read the thing adds a service to operate without adding any access. We still think that.

This server does not contradict it, because it is not connecting your agent to a system. It is solving the two problems that a library of 65 frameworks has and a single skill does not. Which one? Routing is a real question when the wrong choice costs you a context window; recommend_skills answers it from each skill’s own hand-written “not for” list, which is the part no keyword search can reproduce. How do I try one? Reading a skill before installing it used to mean browsing GitHub; now it is one tool call.

For everyday work, install what you use (npx skills add wondelai/skills --all --global) and skip the network entirely. Everything here is MIT-licensed and readable at github.com/wondelai/skills, built on the open agentskills.io standard.

06 Questions

Before you connect.

01 Do I still need this if I have already installed the skills? Mostly no, and that is the honest answer. Installed skills live on disk, load with no network hop, and your agent picks them up by itself. The server earns its place in three situations: an agent that has nothing installed and needs a framework now; choosing between 65 entries, which is what recommend_skills is for; and reading a skill's deep-dive reference files on demand instead of carrying them in context.
02 What does connecting cost me in context? About 2,600 tokens for the tool definitions, paid once per session — that is the real price of connecting, and it is why there are five tools rather than twenty-five. After that the surface is deliberately cheap: a search hit is ~70 tokens as text and ~120 if your client reads the structured lane, and get_skill ~400. Only load_skill spends real context (~4,500 tokens for an average SKILL.md), because that is the call that returns instructions to follow — and it returns them once, in one lane, rather than paying for the same document twice.
03 Is there authentication or a rate limit? Neither. Every tool is read-only, there is no state and no account, so the endpoint is open and CORS is unrestricted — browser-hosted MCP clients work too. Tool calls are answered live; it is the reads behind them — the upstream SKILL.md files and the repo file tree — that are cached at the Cloudflare edge for an hour, which is why a warm load_skill returns in about 60ms. If you want a guarantee rather than a promise, install the skills instead: npx skills add wondelai/skills --all --global.
04 Which clients does it work with? Anything that speaks streamable HTTP MCP — Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw, Hermes Agent and others. The server implements the stateless 2026-07-28 revision and still answers older stateless clients on the same URL, so there is no separate legacy endpoint and no SSE session to keep alive.

Installed skills load from disk, no network hop.

Or install the library and skip the round trip.

npx skills add wondelai/skills --all --global
Copy the endpoint Browse the library

MIT licensed · Claude, Claude Code, Codex, Cursor, OpenClaw, Hermes · No account

  We build the skills you already use. Now we’ll build yours. See what we build  ·  Book a 15-min call