hybrid-edge-cloud SKILL.md skillA

hybrid-edge-cloud from claude-dev-suite/claude-dev-suite is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add claude-dev-suite/claude-dev-suite/hybrid-edge-cloud@git:20260601.8eda6f7

Pins git:20260601.8eda6f7 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
claude-dev-suite/claude-dev-suite
Path
skills/ai-systems/hybrid-edge-cloud/SKILL.md
Versions recorded
1
Latest version
git:20260601.8eda6f7, committed Jun 1, 2026
Size
2,458 bytes
Repository stars
48
License
MIT

Hybrid edge-cloud AI architecture: local-first inference with cloud escalation, model cascading, and splitting the workload across device and datacenter to balance latency, cost, privacy, and quality. Architect-level topology. USE WHEN: designing systems that combine on-device and cloud AI, "local-first", "cloud fallback", "model cascade", "escalation", "hybrid inference", routing by confidence/complexity, edge+cloud trade-offs. DO NOT USE FOR: pure on-device (use `edge-inference`); pure…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Hybrid Edge–Cloud AI

Combine a small/fast local model with a large/capable cloud model to get the best
of both — when neither pure-edge nor pure-cloud fits.

## Patterns
- **Local-first + cloud escalation**: run a small on-device model; escalate to
  the cloud only when needed (low confidence, long context, hard query). Most
  requests stay local (fast, cheap, private); hard ones get cloud quality.
- **Model cascade**: cheap model → if confidence < threshold → bigger model →
  … . Tune thresholds to a cost/quality target. Works within cloud too.
- **Speculative / draft-verify**: small model drafts, large model verifies — a
  latency optimization more than a topology, but composes here.
- **Split computation**: feature extraction / preprocessing on device, heavy
  inference in cloud (classic for vision/audio).

## Decision drivers
- **Escalation trigger**: confidence score, input complexity/length, task type,
  or explicit user action. The trigger quality makes or breaks the design.
- **Privacy boundary**: what may leave the device? Sometimes only embeddings or
  redacted text escalate.
- **Connectivity**: must it degrade gracefully offline? Local model = floor.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_z33auazj4sleqy5v/d26af3262ba985a7367f0a77db6e213ec4b9598a1cf9bcf231c1663d4a2ec7c1.json

Then /plugin install hybrid-edge-cloud@markdownregistry-z33auazj4sleqy5v in Claude Code. It installs git:20260601.8eda6f7, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add claude-dev-suite/claude-dev-suite/hybrid-edge-cloud@sha256:d26af3262ba985a7

The line at the top of this page pins the label git:20260601.8eda6f7, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_z33auazj4sleqy5v.svg)](https://markdownregistry.com/a/art_z33auazj4sleqy5v)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in claude-dev-suite/claude-dev-suite/hybrid-edge-cloud since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of hybrid-edge-cloud from somewhere else? Ask it: where did my hybrid-edge-cloud come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Jun 1, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260601.8eda6f7 latest2026-06-01 8eda6f7 2,458 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2458 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

claude-dev-suite/claude-dev-suite · 48 stars · license MIT · pushed 2026-11-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_z33auazj4sleqy5v
GET https://markdownregistry.com/api/v1/resolve?ref=claude-dev-suite/claude-dev-suite/hybrid-edge-cloud
GET https://markdownregistry.com/api/v1/blob/d26af3262ba985a7367f0a77db6e213ec4b9598a1cf9bcf231c1663d4a2ec7c1

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from claude-dev-suite/claude-dev-suite

CLAUDE.md CLAUDE.md file
claude-dev-suite/claude-dev-suite · CLAUDE.md
git:20261006.50a1140 · audit A · 48 stars
axe-core SKILL.md skill
claude-dev-suite/claude-dev-suite · skills/accessibility/axe-core/SKILL.md · axe-core - accessibility testing engine for automated WCAG compliance checks. USE WHEN: user mentions "axe"…
git:20260206.5b2d9a9 · audit A · 48 stars
wcag SKILL.md skill
claude-dev-suite/claude-dev-suite · skills/accessibility/wcag/SKILL.md · WCAG 2.2 Web Content Accessibility Guidelines. Covers conformance levels A/AA/AAA, success criteria, testing with…
git:20260206.5b2d9a9 · audit A · 48 stars
anthropic-python SKILL.md skill
claude-dev-suite/claude-dev-suite · skills/ai-integration/anthropic-python/SKILL.md · Anthropic Python SDK for Claude API integration. Covers messages API, streaming, tool use, vision, error handling, and…
git:20260315.e77955e · audit A · 48 stars
decision-model-calibration SKILL.md skill
claude-dev-suite/claude-dev-suite · skills/ai-integration/decision-model-calibration/SKILL.md · Turning a model's class probabilities into numbers you can set a threshold on: building the labelled corpus, measuring…
git:20261003.658fd16 · audit A · 48 stars
langchain SKILL.md skill
claude-dev-suite/claude-dev-suite · skills/ai-integration/langchain/SKILL.md · LangChain framework for LLM application development. Covers chains, agents, tools, RAG pipelines, vector stores…
git:20260305.f2b6ac9 · audit A · 48 stars
rag-patterns SKILL.md skill
claude-dev-suite/claude-dev-suite · skills/ai-integration/rag-patterns/SKILL.md · Retrieval-Augmented Generation architecture patterns. Chunking strategies, retrieval pipelines, re-ranking, hybrid…
git:20260305.f2b6ac9 · audit A · 48 stars
typed-decision-models SKILL.md skill
claude-dev-suite/claude-dev-suite · skills/ai-integration/typed-decision-models/SKILL.md · Replacing an LLM used as a classifier with a model that returns typed decisions and probabilities instead of prose —…
git:20261003.658fd16 · audit A · 48 stars
typesafe-jev SKILL.md skill
claude-dev-suite/claude-dev-suite · skills/ai-integration/typesafe-jev/SKILL.md · Building against TypeSafe's Jev: the /v1/systemone HTTP API, the Python (`typesafe-sdk`) and JS (`@typesafe-ai/sdk`)…
git:20261003.658fd16 · audit A · 48 stars
vector-databases SKILL.md skill
claude-dev-suite/claude-dev-suite · skills/ai-integration/vector-databases/SKILL.md · Vector database integration for embeddings and similarity search. Pinecone, Weaviate, Qdrant, ChromaDB, pgvector. Index…
git:20260305.f2b6ac9 · audit A · 48 stars
agentic-architecture SKILL.md skill
claude-dev-suite/claude-dev-suite · skills/ai-systems/agentic-architecture/SKILL.md · Architecture of LLM agent systems: orchestration topologies (single agent, supervisor/sub-agents, pipelines, networks)…
git:20260601.8eda6f7 · audit A · 48 stars
ai-hardware-selection SKILL.md skill
claude-dev-suite/claude-dev-suite · skills/ai-systems/ai-hardware-selection/SKILL.md · Selecting accelerators for AI workloads: GPU vs TPU vs NPU vs FPGA vs CPU, and the metrics that actually decide it —…
git:20260601.8eda6f7 · audit A · 48 stars

Every file in claude-dev-suite/claude-dev-suite

Browse by kind, by grade A, or by owner.