In-house flow
Write the thing that does not exist yet
For the point where the answer stops being "install something" and starts being "build it". Two Anthropic meta-skills that make the skill-or-server decision legible, and the third-party one that tests the failure both of them leave open.
The failure this is for
Somebody writes a SKILL.md, reads it back, ships it, and it never runs. Not errors: never runs. The model reads the description, judges it irrelevant to how the request was phrased, and moves on. There is no log line for a skill that was not consulted.
The MCP version is the same shape one level down. The server compiles, the Inspector calls succeed by hand, and in a live session the agent either ignores the tool or calls it with arguments that do not match the schema.
| The failure | What it looks like | What answers it |
|---|---|---|
| Built the wrong shape | a skill shelling out to curl, a server wrapping static advice | read both meta-skills first |
| The skill never triggers | no error, no invocation, no signal | measure the description |
| One tool per endpoint | technically complete, unusable | tool design as its own step |
| Passes offline, fails live | Inspector green, session wrong | test from inside a session |
The first fork, which neither item names
Reading both Anthropic skills before writing anything is the actual "should this be a skill or a server" step, and it works precisely because neither one tells you the answer. What they do is make the two costs legible.
Everything in skill-creator is machinery for making a description reliably trigger in natural language. Everything in mcp-builder is machinery for making tool schemas an LLM can call correctly. If your thing is mostly "here is how we do X", the entire apparatus of the second one is overhead you would be paying for nothing. If your thing needs to reach a system that can answer back, the first one has no way to express that. The asymmetry is the answer, and you get it by reading both rather than by finding a page that decides for you.
Why a ten-star skill is in a stack with a hundred-and-sixty-thousand-star one
Both anchors contain a test step, and neither tests the thing that actually breaks.
Skill-creator tests whether the description triggers. Mcp-builder's build phase tests whether the server compiles and answers the protocol. Neither one puts a real request, phrased the way a colleague would phrase it, into a live session and checks which tool got called with what. That gap is where the shipped-and- broken servers live, because it is downstream of every check that is easy to run.
The item that fills it is a ten-star personal repository, which is exactly why most people will not have it. It earns its place under the same rule the rest of this catalog uses: it is a procedure written in markdown, it holds no credentials, and the worst case is that you read it and disagree.
Three items, and the two that should be here
This stack is short because the honest version of it is short.
There is no row for the MCP Inspector. Mcp-builder tells you to run
npx @modelcontextprotocol/inspector, and it is the correct advice. The
Inspector cannot be listed here: it is a CLI, and every ingestion path this
catalog has produces skills or MCP servers. Same reason Repomix is missing from
the codebase-reading stack. The gap is in our shelves, not in the ecosystem.
There is nowhere to publish a skill. Servers have the official MCP Registry
and its mcp-publisher CLI. Skills have aggregators, and this project's own
sourcing rules exclude them as content sources. That is a real hole in the
ecosystem rather than an oversight in this research, and it is worth knowing
before you finish writing something you were hoping to distribute.
One item was cut here for the reason the schema stack states: a six-star server that walks you through publishing, which would want registry and CI credentials to do its job. The official CLI does the same work and you build it yourself.
Set it all up
3 of 3, in order
npx -y skills add anthropics/skills --skill skill-creator
npx -y skills add anthropics/skills --skill mcp-builder
npx -y skills add ckorhonen/claude-skills --skill mcp-testerSome of these are the commands their projects publish and some are assembled from repository paths. Each one is labelled where it appears below. Nobody here has run them as a set.
How it goes
Their working order, our numbers
Anthropic's own meta-skill, and its best idea is to treat "does the model actually invoke this" as measurable rather than hoped for. It generates around twenty should-trigger and should-not-trigger phrasings, runs each against the real model several times, and rewrites the description until the rate holds on phrasings it has not seen. The description is the product. Most skills fail there and fail silently.
Skill creatorSkill
anthropics/skills/skills/skill-creator164,354★ repono licenseno license
npx -y skills add anthropics/skills --skill skill-creatorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
Read alongside the one above rather than after it, because between them they answer the question neither asks out loud. Its subject is tools an LLM can call correctly: schemas, pagination, errors, and ten evaluation questions that have to be answerable through the server. Its standing warning is the one-tool-per-endpoint wrapper, which works and is useless.
Mcp builderSkill
anthropics/skills/skills/mcp-builder164,354★ repono licenseno license
npx -y skills add anthropics/skills --skill mcp-builderAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
Then test the thing neither of the two above tests. Not "does it compile" and not "does the protocol respond", but whether a real session picks the right tool with the right arguments from how a person actually phrased it. Six phases, ending in a redundancy check across tools. Ten stars, and it is a procedure in markdown rather than something asking for your credentials.
Mcp testerSkill
ckorhonen/claude-skills/skills/mcp-tester10★ repoMIT
npx -y skills add ckorhonen/claude-skills --skill mcp-testerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
More of these
Stacks are written by hand and there are not many. The catalog underneath is large, and its default ordering puts whatever has been picked at the front.