mcpbeat Sign in

MCP Apps Sync Docs Agent Skill

> Syncs MCP Apps documentation with the @apollo/client-ai-apps changelog. Always use this skill or version range, (2) phrases like "sync docs from version X", "update docs from changelog", "what changed since v0.x.x", "docs are out of date", or "check the changelog" appear in context of MCP Apps documentation, (3) checking whether mcp-apps-*.mdx files reflect recent releases. The changelog URL and doc file paths are pre-configured — the user only needs to provide the minimum version to sync from.

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
301
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/apollographql/apollo-mcp-server --skill mcp-apps-sync-docs

What it tells the agent to use

found in the instruction text
Bash runs shell commands — read the instruction before connecting

The instruction itself

8 sections, as written by the author

Overview

This skill updates the MCP Apps documentation based on changes in the @apollo/client-ai-apps CHANGELOG from a specified version onward. It reads the changelog, compares it against the current docs, and makes targeted edits — without committing.

What you need from the user

One thing: a minimum version (e.g., 0.6.0 or v0.6.2). All changelog entries from that version to the latest will be analyzed.

Step 1: Fetch the changelog

Use the GitHub CLI to fetch the full changelog:

gh api repos/apollographql/apollo-client-ai-apps/contents/CHANGELOG.md --jq '.content' | base64 -d

Step 2: Parse relevant versions

The changelog uses this structure:

## 0.6.5 (2026-03-23)

### Features

#### Feature title

Description and code examples...

### Fixes

#### Fix title

Description...

Collect all version sections where the version number is greater than or equal to the user's minimum version. Ignore everything below that version. Parse each section into: version number, date, list of features, list of fixes, and any breaking changes or deprecations called out explicitly.

Step 3: Read the docs

Read all six documentation files. Understand what each one covers before analyzing the changelog:

  • docs/source/mcp-apps.mdx — MCP Apps overview: what are MCP apps, high-level overview, architecture diagram
  • docs/source/mcp-apps-architecture.mdx — How MCP Apps work: the discovery and tool execution phases, architecture diagrams
  • docs/source/mcp-apps-quickstart.mdx — Step-by-step setup guide using the Apollo AI Apps Template; Vite plugin behavior; project structure
  • docs/source/mcp-apps-development.mdx — Day-to-day development patterns, directives, hooks, and client usage
  • docs/source/mcp-apps-prerequisites.mdx — System and account prerequisites before building
  • docs/source/mcp-apps-reference.mdx — API reference: directives (@tool, @prefetch, @private), hooks (useToolInfo, etc.), manifest, configuration

Step 4: Analyze the changes

For each changelog entry, decide whether a doc change is needed:

Features — Is this already documented? If not, which file is the right home?

  • New hooks, directives, or client APIs belong in mcp-apps-reference.mdx
  • Changes to how Vite plugin builds or generates files belong in mcp-apps-quickstart.mdx or mcp-apps-development.mdx
  • Changes to how the architecture works belong in mcp-apps-architecture.mdx
  • New system requirements belong in mcp-apps-prerequisites.mdx

Deprecations — Are the deprecated APIs mentioned positively in the docs? Add a deprecation notice near the relevant section and point to the replacement.

Breaking changes / behavior changes — Do the docs describe the old behavior as correct? Update them to reflect the new behavior.

Bug fixes — Generally skip these unless the docs explicitly described the buggy behavior as correct (e.g., documented a workaround that is no longer needed).

Step 5: Make the edits

Edit the affected files directly using available tools. As you do:

  • Match the existing tone, MDX component usage (e.g., <Note>, code fences with language tags), and heading levels
  • Insert new content in the section that makes the most sense contextually, not just at the end of the file
  • For deprecations, add a notice near the existing mention — don't remove the old API from docs until it's actually gone
  • For breaking changes, update the description in place so readers see the current behavior
  • Keep each change minimal and traceable to its changelog entry
  • Write as if the behavior or code was always that way. DO NOT write in past tense (avoid language such as "previously it was x, now it is y")

Do not commit. Leave all edits as unstaged file changes for the user to review.

Step 6: Summarize what you did

Give the user a concise report:

  • Which files were modified
  • For each change: what was updated and which changelog entry it corresponds to
  • Which changelog entries were skipped and why (e.g., "internal fix, no user-facing behavior change")

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take apollographql/mcp-apps-sync-docs from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.