From forge-core
Move bulk reference material from the main SKILL.md body into @-included companion files so the always-loaded content stays lean. USE WHEN an adopted or authored skill's body exceeds its information density because it inlines reference tables, pricing, catalogs, or per-variant guidance.
npx claudepluginhub n4m3z/forge-coreThis skill is limited to using the following tools:
Move bulk reference material out of `SKILL.md` into companion files referenced with `@` includes. The SKILL.md stays the entrypoint an AI reads to decide behavior; companions load on demand when the AI needs the reference data. Referenced by [ForgeAdopt](../ForgeAdopt/SKILL.md) as the `extract` transform.
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.
Move bulk reference material out of SKILL.md into companion files referenced with @ includes. The SKILL.md stays the entrypoint an AI reads to decide behavior; companions load on demand when the AI needs the reference data. Referenced by ForgeAdopt as the extract transform.
Follows [ARCH-0002](docs/decisions/ARCH-0002 Skills Companion Files.md).
| Content shape | Extract to a companion? |
|---|---|
| Long reference table (model pricing, language-specific rules, catalogs) | Yes |
| Per-variant guidance (one section per framework, language, or ecosystem) | Yes, one companion per variant |
| Command reference (many commands, each with flags and examples) | Yes, if it spans more than a screen |
| Full example project | Yes, always |
| Workflow that decides HOW to use the skill | No, stays in SKILL.md |
| Constraints, red flags, anti-patterns | No, stays in SKILL.md |
| Decision tables with 3-7 rows | No, inline |
Identify candidate sections — content that is reference material rather than instruction.
For each candidate, move it to a companion file named by its scope (PythonReference.md, Tables.md, ModelPricing.md).
Replace the extracted block with an @ include in SKILL.md:
## Language-specific guidance
@python-security.md
@typescript-security.md
@go-security.md
Keep the section heading in SKILL.md so the AI knows the companion exists.
Re-read SKILL.md alone. It should still be a complete instruction — the AI must be able to decide what to do without loading the companion.
SKILL.mdTemplateReference.md, SchemaValidation.md)python-django-security.md)SKILL.md must remain complete as instruction on its own — companions are reference, not required loading@-include another companion) — compose at the SKILL.md level