How do I install the Cache Docs skill?

Run npx skillmds@latest add tomevault-io/cache-docs in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Cache Docs safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Cache Docs?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Cache Docs free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Cache Docs?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Cache Docs by tomevault-io — Agent Skill

Name: Cache Docs
Author: tomevault-io

Cache Docs

When fetching library documentation, API references, or technical docs for project dependencies via WebFetch, automatically save a copy to the docs/ folder. Also triggers when user pastes documentation or discusses library APIs that should be cached for reference. Every non-stdlib import in the project should have corresponding reference docs cached. Use when this capability is needed.

tomevault-io 40a7c9c 2 files · 3.2 KB Updated Sep 17, 2026

File contents

Documentation Caching Skill

When you fetch or receive documentation for a library dependency, cache it locally.

When to Activate

After any WebFetch of documentation sites (readthedocs, official docs, GitHub READMEs)
When user pastes library documentation into the conversation
When discussing a library's API and realizing docs should be cached
When importing a new dependency that lacks cached documentation

Caching Process

Determine the library name from the URL or content context
Create the directory if it doesn't exist: docs/<library-name>/
Generate a slugified filename from the page title or topic
Write the file with YAML frontmatter:

---
source: <original URL>
fetched: <ISO 8601 date>
library: <library name>
summary: <one-line summary of what this doc covers>
---

# <Page Title>

<Content here>

Update the index at docs/_index.md with the new entry

File Organization

docs/
├── _index.md           # Auto-maintained index of all cached docs
├── pycrdt/
│   ├── quickstart.md
│   └── api-reference.md
├── stytch/
│   ├── magic-links.md
│   └── rbac.md
├── nicegui/
│   └── getting-started.md
└── sqlmodel/
    └── tutorial.md

Index Format

The _index.md should list all cached documentation:

# Cached Documentation Index

## pycrdt
- [Quickstart](pycrdt/quickstart.md) - Getting started with pycrdt CRDT library
- [API Reference](pycrdt/api-reference.md) - Full API documentation

## stytch
- [Magic Links](stytch/magic-links.md) - Email magic link authentication
- [RBAC](stytch/rbac.md) - Role-based access control

...

Important Notes

Always preserve code examples from documentation
Include version information when available
If documentation is very long, summarize and link to source
Cache critical information even if full doc doesn't fit

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: cache-docsdescription: When fetching library documentation, API references, or technical docs for project dependencies via WebFetch, automatically save a copy to the docs/ folder. Also triggers when user pastes documentation or discusses library APIs that should be cached for reference. Every non-stdlib import in the project should have corresponding reference docs cached. Use when this capability is needed.---# Documentation Caching SkillWhen you fetch or receive documentation for a library dependency, cache it locally.## When to Activate- After any WebFetch of documentation sites (readthedocs, official docs, GitHub READMEs)- When user pastes library documentation into the conversation- When discussing a library's API and realizing docs should be cached- When importing a new dependency that lacks cached documentation## Caching Process1. **Determine the library name** from the URL or content context2. **Create the directory** if it doesn't exist: `docs/<library-name>/`3. **Generate a slugified filename** from the page title or topic4. **Write the file** with YAML frontmatter:```markdown---source: <original URL>fetched: <ISO 8601 date>library: <library name>summary: <one-line summary of what this doc covers>---# <Page Title><Content here>```5. **Update the index** at `docs/_index.md` with the new entry## File Organization```textdocs/├── _index.md # Auto-maintained index of all cached docs├── pycrdt/│ ├── quickstart.md│ └── api-reference.md├── stytch/│ ├── magic-links.md│ └── rbac.md├── nicegui/│ └── getting-started.md└── sqlmodel/ └── tutorial.md```## Index FormatThe `_index.md` should list all cached documentation:```markdown# Cached Documentation Index## pycrdt- [Quickstart](pycrdt/quickstart.md) - Getting started with pycrdt CRDT library- [API Reference](pycrdt/api-reference.md) - Full API documentation## stytch- [Magic Links](stytch/magic-links.md) - Email magic link authentication- [RBAC](stytch/rbac.md) - Role-based access control...```## Important Notes- Always preserve code examples from documentation- Include version information when available- If documentation is very long, summarize and link to source- Cache critical information even if full doc doesn't fit---> Converted and distributed by [TomeVault](https://tomevault.io/claim/mqfacultyofarts) — claim your Tome and manage your conversions.

Frequently asked questions