graph-personalization SKILL.md skillA
This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.
graph-personalization from aws-samples/sample-aws-solutions-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add aws-samples/sample-aws-solutions-skills/graph-personalization@v1.0Pins v1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- aws-samples/sample-aws-solutions-skills
- Path
graph-personalization-skill/claude-code/skills/graph-personalization/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0, committed Jun 24, 2026
- Size
- 9,743 bytes
- Repository stars
- 14
- License
- MIT-0
Build a Customer Similarity Graph + Bedrock-explainable recommendation system on AWS using Amazon Neptune (graph DB) + Bedrock Claude + Kinesis (real-time updates) + React Admin UI. Generates production-ready CDK with Graph schema per industry (e-commerce / media / B2B SaaS / recruiting / healthcare), parameterized Cypher queries with privacy thresholds, recency-decayed weights, Cold start fallback, and natural-language recommendation explanations. Use when user asks for…
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
# Graph Personalization Builder ## Purpose Model user behavior/attribute data as a graph (Amazon Neptune) to generate a production-ready CDK system that delivers relationship-based personalization recommendations — such as **"what users similar to you liked"**, **"content your friends watched"**, and **"features used by larger customers in the same industry"** — plus Bedrock natural-language explanations. The per-industry graph schema difference is the biggest specific value. ## Knowledge sources - `shared/reference/architecture.md` — full architecture + WHY each component - `shared/reference/decision-tree.md` — 12 decision branches (industry/node/edge/data source/update/scenario/explainability/latency/Neptune mode/ML/Frontend/Auth) - `shared/reference/aws-services.md` — Neptune mode comparison, Bedrock models, cost scenarios - `shared/reference/constraints.md` — 25 pitfalls (must read) - `shared/reference/graph-schemas.md` — **per-industry vertex/edge schema (E-commerce / Media / B2B SaaS / Recruiting / Healthcare)** - `shared/patterns/cdk-stacks.md` — 7 stacks (Network/Graph/Ingestion/ML/Auth/API/Frontend) …
Read the whole file at its exact version.
How to install
mdr add aws-samples/sample-aws-solutions-skills/graph-personalization@sha256:a288fba92064fa81The line at the top of this page pins the label v1.0, 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.
[](https://markdownregistry.com/a/art_o6lgbs3zbaxxhpiu)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jun 24, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9743 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
aws-samples/sample-aws-solutions-skills · 14 stars · license MIT-0 · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_o6lgbs3zbaxxhpiu GET https://markdownregistry.com/api/v1/resolve?ref=aws-samples/sample-aws-solutions-skills/graph-personalization GET https://markdownregistry.com/api/v1/blob/a288fba92064fa81b19d55824b7930db3e52bc21dcc277fc4eb48f2a7d8facac
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 aws-samples/sample-aws-solutions-skills
Every file in aws-samples/sample-aws-solutions-skills