SkillPedia Skills Encyclopedia
中文 EN

技能 2026-09-29 03:04 UTC

ext-skillsv45.530

版本【45.530】由提交人 tobi-oye 提交,主要更新类型为:功能特性新增与扩展。提交说明:docs(findings): transport of an io.modelcontextprotocol/ frontmatter metadata key over SEP-2640 (#136)。为项目引入了新的能力与模块支持。

tobi-oye 167da6c modelcontextprotocol/ext-skills

Commit提交信息原文

docs(findings): transport of an io.modelcontextprotocol/ frontmatter metadata key over SEP-2640 (#136)

Adds an experimental finding for
[#126](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/126)
item 4, reserving the `io.modelcontextprotocol/` namespace inside the
Agent Skills frontmatter `metadata` map. One commit on current `main`.

## Why

The group agreed on
[2026-06-16](https://github.com/modelcontextprotocol/modelcontextprotocol/discussions/2941)
(§2) to propose the reservation upstream in the Agent Skills spec.
SEP-2640 already reserves the prefix on the MCP side and defines no keys
under it, but nothing had exercised the path, and a wording suggestion
reads better with evidence behind it. This is that evidence, run before
the upstream proposal rather than after.

## What was run

A demo server serves a skill whose frontmatter is exactly:

```yaml
---
name: namespace-detection-demo
description: Demonstrates transport of MCP-reserved Agent Skills metadata.
metadata:
  io.modelcontextprotocol/test-marker: "detected-by-vscode"
---
```

VS Code started that server over stdio, called `skills/list`, and
recognized the key four milliseconds later:

```
17:48:45.530  [editor -> server] {"jsonrpc":"2.0","id":3,"method":"skills/list","params":{}}
17:48:45.534  [info] [mcp-skills-experiment] io.modelcontextprotocol/test-marker detected on skill
              "namespace-detection-demo" from "skills-demo-local" (value "detected-by-vscode")
17:48:45.534  [info] [mcp-skills] "skills-demo-local" served 4 skill(s): tabletop-dice,
              mcp-glossary, namespace-detection-demo, release-notes-writer
```

Four cases, each recording discovery, the host's log output, and whether
the fetched `SKILL.md` still passes the frontmatter identity check that
gates loading:

| Case | Discovery | Host log | Load |
| :-- | :-- | :-- | :-- |
| `io.modelcontextprotocol/test-marker` present | ok | one `info` line,
detection | passes |
| only `com.example/test-marker` | ok | nothing | passes |
| `io.modelcontextprotocol/unknown-test-key` | ok | one `trace` line,
ignored | passes |
| no `metadata` | ok | nothing | passes |

The first ran in the running editor against a live server; the other
three are unit tests against the same discovery entry point. No parser
changes were needed anywhere. Server: 28 tests pass plus the stdio
conformance suite. Host: 39 pass. No model is on the evidence path —
wire logs, protocol responses and deterministic host logs only.

**Tested commits:** server
[`bb21190`](https://github.com/tobi-oye/skills-over-mcp-demo/commit/bb21190820a6b5f71462b657b0cbb48ae3b1070f)
(on
[olaservo/skills-over-mcp-demo](https://github.com/olaservo/skills-over-mcp-demo)
`abf2262`), host
[`2984fa2`](https://github.com/tobi-oye/vscode/commit/2984fa2b47b),
SEP-2640 at
[`a3e147c`](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/a3e147ca2710f68214247aecc729731ee1ae8d03/seps/2640-skills-extension.md)
on the canonical `sep/skills-extension` branch.

## What it does not claim

Stated explicitly in the entry: this shows transport, preservation and
host recognition are technically possible. It does **not** show the
namespace should be reserved — that is a governance and interoperability
decision for the Agent Skills project.
`io.modelcontextprotocol/test-marker` is a throwaway fixture, not a
proposed production property. This is `SKILL.md` frontmatter `metadata`,
not MCP `_meta`; the `io.modelcontextprotocol.skills/` convention from
[#60](https://github.com/modelcontextprotocol/experimental-ext-skills/pull/60)
is a separate mechanism and is unaffected.

## Two things worth the group's attention

**Ignoring is not the same as not comparing.** Because a host compares
fetched frontmatter field-by-field against the published entry, a
reserved key it does not understand still participates in verification:
a marker whose value differs between listing and file fails the check
and the skill does not load. So "implementations SHOULD ignore keys
under this prefix that they do not recognize" needs to mean *do not act
on them*, not *do not compare them*. Worth a clarifying clause in the
SEP if the group agrees.

**Reserved metadata inherits the listing cache's lifetime.** Two
`skills/list` calls produced two detection lines, but a third
contribution of the same skills to the model's context produced none —
it came from the host's cache without re-running discovery. Fine for a
log line; relevant for any future key meant to influence behaviour.

Limitations are listed in the entry. The main ones: the live session
covered discovery and detection but never loaded the skill, so the
"still loads" column rests on tests and the server-side verified read;
and the live host negotiated `2025-11-25`, so the 2026-07-28
listing-cache attributes were exercised server-side only.

A documentation-only proposal to `agentskills/agentskills` follows from
this:
[agentskills#546](https://github.com/agentskills/agentskills/pull/546).

AI assistance: this finding, the experiment code and this description
were drafted with Claude Code and reviewed by me.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: olaservo <olahungerford@gmail.com>