From forge-core
Create, derive, and validate .mdschema files for markdown documents. USE WHEN create schema, add schema, derive schema, validate schema, check schema, mdschema, lint schema, heading rules, frontmatter validation, or editing any markdown file in a directory that contains a .mdschema.
npx claudepluginhub n4m3z/forge-core**/*.md**/.mdschemaThis skill uses the workspace's default tool permissions.
Create and validate `.mdschema` files that enforce frontmatter fields and heading structure across forge artifacts. Wraps the `mdschema` CLI with forge-specific conventions.
Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.
Processes PDFs: extracts text/tables/images, merges/splits/rotates pages, adds watermarks, creates/fills forms, encrypts/decrypts, OCRs scans. Activates on PDF mentions or output requests.
Share bugs, ideas, or general feedback.
Create and validate .mdschema files that enforce frontmatter fields and heading structure across forge artifacts. Wraps the mdschema CLI with forge-specific conventions.
See MarkdownSchema.md — the rule for conforming to a sibling .mdschema when one exists in the file's directory.
| Workflow | Trigger | Section |
|---|---|---|
| Create | "create schema", "add schema", "new schema" | Create Workflow |
| Derive | "derive schema", "infer schema" | @Derive.md |
| Validate | "validate", "check", "lint schema" | @Validate.md |
Always .mdschema (no .yml extension). Lives alongside the files it validates:
skills/.mdschema # validates skills/*/SKILL.md
agents/.mdschema # validates agents/*.md
.mdschema # validates *.md in current directory
| Artifact | Required fields | Optional fields | max_depth |
|---|---|---|---|
| Skill | name, description, version | argument-hint | 3 |
| Agent | name, description, version | -- | 3 |
| Project docs | (frontmatter optional) | -- | 4 |
All schemas enforce no_skip_levels: true.
Skill schema:
frontmatter:
fields:
- name: name
- name: description
- name: version
heading_rules:
no_skip_levels: true
max_depth: 3
Agent schema:
frontmatter:
fields:
- name: name
- name: description
- name: version
heading_rules:
no_skip_levels: true
max_depth: 3
Project docs schema:
frontmatter:
optional: true
heading_rules:
no_skip_levels: true
max_depth: 4
Identify the directory and artifact type:
skills/ directory with */SKILL.md files → skill schemaagents/ directory with *.md files → agent schemaIf ambiguous, ask the user.
Look for .mdschema in the target directory. If one exists, show it and ask whether to replace or update.
Use the reference schema for the detected artifact type from the conventions table.
Write .mdschema to the target directory using the Write tool.
Run validation immediately to confirm the schema works:
mdschema check "<glob>" --schema <path>/.mdschema
Glob patterns by artifact type:
"skills/*/SKILL.md""agents/*.md""*.md"Report results. If violations are found, present them and ask whether to fix the documents or adjust the schema.
@Derive.md
@Validate.md
.mdschema -- never .mdschema.yml or .mdschema.yamlversion should be required for skills and agents to catch nesting errorsno_skip_levels is always true -- no exceptionsmdschema is not installed, tell the user: brew install jackchuka/tap/mdschema