new skill meta

This commit is contained in:
John Lancaster
2026-06-18 22:22:30 -05:00
parent 9f34e12e08
commit 818de1b3f9
7 changed files with 192 additions and 4 deletions
-1
View File
@@ -17,7 +17,6 @@ COPY src ./src
RUN uv sync --frozen --no-dev
COPY docs ./docs
COPY skills ./skills
COPY zensical.toml ./
RUN uv run zensical build
+152
View File
@@ -0,0 +1,152 @@
# Hooking Up a New Skill
Use this checklist after generating a new skill under `docs/skills/<slug>/`.
## Checklist
1. Create the authored docs content.
Add `docs/skills/<slug>/SKILL.md` and any companion files under `docs/skills/<slug>/references/`.
2. Choose the three names up front.
Use a docs slug like `fastapi-uv-docker`, a resource id like `fastapi-uv-docker`, and a Python package name like `fastapi_uv_docker`.
3. Add the runtime package.
Create `src/personal_mcp/skills/<python_namespace>/` with `__init__.py`, `server.py`, and `metadata.yaml`.
4. Expose the document resource in `server.py`.
Follow the existing pattern: create a `FastMCP` instance, register `resource://skills/<skill-id>/document`, and return `load_skill_document(skill_id=<skill-id>, skill_slug=<slug>)`.
5. Register the catalog metadata.
In `metadata.yaml`, add the skill `id`, `name`, `version`, `description`, `tags`, `capabilities`, and `depends_on`. The `capabilities` list should include `resource://skills/<skill-id>/document`.
6. Mount the skill in the root server.
Import the new server in `src/personal_mcp/mcp.py` and add an `mcp.mount(...)` call with the Python namespace.
7. Let the loader and catalog do the rest.
The document loader reads canonical Markdown from `docs/skills/<slug>/SKILL.md`, and the catalog discovers metadata from `src/personal_mcp/skills/*/metadata.yaml` automatically.
8. Rebuild and smoke-test.
Run `uv run zensical build` to publish the docs site, then run a quick Python check or start the app to confirm the new resource loads.
## Minimal Shape
- Docs content: `docs/skills/<slug>/SKILL.md`
- Optional references: `docs/skills/<slug>/references/*.md`
- Runtime package: `src/personal_mcp/skills/<python_namespace>/`
- Resource URI: `resource://skills/<skill-id>/document`
## Quick Validation
1. Confirm the Markdown document resolves through the loader.
`uv run python -c "from personal_mcp.skills.document_loader import load_skill_document; print(load_skill_document(skill_id='<skill-id>', skill_slug='<slug>')['source_path'])"`
2. Confirm the docs build still works.
`uv run zensical build`
## server.py Template
```python
from fastmcp import FastMCP
from personal_mcp.skills.document_loader import load_skill_document
<python_namespace>_server = FastMCP("<skill-id>")
@<python_namespace>_server.resource("resource://skills/<skill-id>/document")
def skill_document() -> dict[str, str]:
"""Return the canonical Markdown document for this skill."""
return load_skill_document(
skill_id="<skill-id>",
skill_slug="<slug>",
)
```
## metadata.yaml Template
```yaml
id: <skill-id>
name: <Human Readable Name>
version: 1.0.0
description: <One sentence describing what the skill provides.>
tags:
- <tag-one>
- <tag-two>
capabilities:
- resource://skills/<skill-id>/document
depends_on: []
```
## Root Mount Template
Add an import in `src/personal_mcp/mcp.py`:
```python
from personal_mcp.skills.<python_namespace>.server import <python_namespace>_server
```
Add a mount call:
```python
mcp.mount(<python_namespace>_server, namespace="<python_namespace>")
```
## Example Scaffold
For a new skill called `sqlmodel-patterns`:
1. Docs content lives in `docs/skills/sqlmodel-patterns/SKILL.md`.
2. The Python package lives in `src/personal_mcp/skills/sqlmodel_patterns/`.
3. The resource id is `sqlmodel-patterns`.
Example `server.py`:
```python
from fastmcp import FastMCP
from personal_mcp.skills.document_loader import load_skill_document
sqlmodel_patterns_server = FastMCP("sqlmodel-patterns")
@sqlmodel_patterns_server.resource("resource://skills/sqlmodel-patterns/document")
def skill_document() -> dict[str, str]:
"""Return the canonical Markdown document for this skill."""
return load_skill_document(
skill_id="sqlmodel-patterns",
skill_slug="sqlmodel-patterns",
)
```
Example `metadata.yaml`:
```yaml
id: sqlmodel-patterns
name: SQLModel Patterns
version: 1.0.0
description: Provide reusable patterns for building apps with SQLModel.
tags:
- sqlmodel
- python
- patterns
capabilities:
- resource://skills/sqlmodel-patterns/document
depends_on: []
```
Example `mcp.py` additions:
```python
from personal_mcp.skills.sqlmodel_patterns.server import sqlmodel_patterns_server
mcp.mount(sqlmodel_patterns_server, namespace="sqlmodel_patterns")
```
## Bootstrap Sequence
1. Create `docs/skills/<slug>/SKILL.md`.
2. Copy the `server.py` template into `src/personal_mcp/skills/<python_namespace>/server.py`.
3. Copy the `metadata.yaml` template into `src/personal_mcp/skills/<python_namespace>/metadata.yaml`.
4. Add `__init__.py` in the new package directory.
5. Import and mount the server in `src/personal_mcp/mcp.py`.
6. Run the validation commands above.
+2
View File
@@ -5,6 +5,7 @@ from personal_mcp.skills.fastapi_async_sqlalchemy_modernization.server import (
fastapi_async_sqlalchemy_modernization_server,
)
from personal_mcp.skills.fastapi_uv_docker.server import fastapi_uv_docker_server
from personal_mcp.skills.new_skill.server import new_skill_server
from personal_mcp.skills.nicegui.server import nicegui_server
from personal_mcp.skills.nicegui_ui_customization.server import (
nicegui_ui_customization_server,
@@ -21,6 +22,7 @@ mcp.mount(
fastapi_async_sqlalchemy_modernization_server,
namespace="fastapi_async_sqlalchemy_modernization",
)
mcp.mount(new_skill_server, namespace="new_skill")
mcp.mount(nicegui_server, namespace="nicegui")
mcp.mount(nicegui_ui_customization_server, namespace="nicegui_ui_customization")
mcp.mount(pytest_scaffolding_server, namespace="pytest_scaffolding")
+8 -3
View File
@@ -5,9 +5,8 @@ def _repo_root() -> Path:
return Path(__file__).resolve().parents[3]
def load_skill_document(*, skill_id: str, skill_slug: str) -> dict[str, str]:
"""Load the canonical skill markdown document for an MCP skill."""
document_path = _repo_root() / "docs" / "skills" / skill_slug / "SKILL.md"
def load_markdown_document(*, skill_id: str, document_path: Path) -> dict[str, str]:
"""Load an arbitrary Markdown document and expose it as a skill resource."""
if not document_path.exists():
raise FileNotFoundError(
f"Missing skill document for '{skill_id}': {document_path}"
@@ -20,3 +19,9 @@ def load_skill_document(*, skill_id: str, skill_slug: str) -> dict[str, str]:
"source_path": str(document_path),
"content": document_path.read_text(encoding="utf-8"),
}
def load_skill_document(*, skill_id: str, skill_slug: str) -> dict[str, str]:
"""Load the canonical skill markdown document for an MCP skill."""
document_path = _repo_root() / "docs" / "skills" / skill_slug / "SKILL.md"
return load_markdown_document(skill_id=skill_id, document_path=document_path)
@@ -0,0 +1 @@
"""Pseudo-skill exposing the new skill bootstrap guide."""
@@ -0,0 +1,12 @@
id: new-skill
name: New Skill Bootstrap
version: 1.0.0
description: Provide the bootstrap checklist and templates for creating new MCP skills.
tags:
- bootstrap
- scaffolding
- skills
- mcp
capabilities:
- resource://skills/new-skill/document
depends_on: []
@@ -0,0 +1,17 @@
from pathlib import Path
from fastmcp import FastMCP
from personal_mcp.skills.document_loader import load_markdown_document
new_skill_server = FastMCP("new-skill")
@new_skill_server.resource("resource://skills/new-skill/document")
def skill_document() -> dict[str, str]:
"""Return the bootstrap guide used to scaffold new skills."""
document_path = Path(__file__).resolve().parents[4] / "docs" / "new_skill.md"
return load_markdown_document(
skill_id="new-skill",
document_path=document_path,
)