alchemy-reference-architecture
Design a production Alchemy architecture with capability-specific adapters, explicit trust boundaries, partial-state semantics, and reversible operations
Install / Use
npx skills add jeremylongshore/tons-of-skills-marketplace --skill alchemy-reference-architectureInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Our assessment of alchemy-reference-architecture
alchemy-reference-architecture scores 83/100 on our quality scale, 2763rd of 4,659 Development & Engineering skills we index.
Its SKILL.md is 5.1 KB long, well organised into 13 sections and no code examples: a solid amount of guidance for an agent.
With 2,785 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated 8 days ago, so alchemy-reference-architecture is actively maintained.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
alchemy-reference-architecture compared with similar skills
All 4 of these similar skills score higher than alchemy-reference-architecture; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| alchemy-reference-architecture (this skill)by jeremylongshore | 83 | 2.8k | 8d ago | SKILL.md |
| ai-job-searchby MadsLorentzen | 100 | 44.8k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 41.7k | 2d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 10d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 10d ago | SKILL.md |
Frequently asked questions
- How do I install alchemy-reference-architecture?
- Run
npx skills add jeremylongshore/tons-of-skills-marketplace --skill alchemy-reference-architecture. The install tabs above show the steps for each supported agent. - Which AI agents does alchemy-reference-architecture work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is alchemy-reference-architecture safe to use?
- It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is alchemy-reference-architecture still maintained?
- The repository was last updated 8 days ago, so alchemy-reference-architecture is actively maintained.
Skill content
View source on GitHubname: alchemy-reference-architecture description: >- Design a production Alchemy architecture with capability-specific adapters, explicit trust boundaries, partial-state semantics, and reversible operations. Use when reviewing or creating an Alchemy-backed system. Trigger with "Alchemy architecture", "design an Alchemy dApp backend", or "review Alchemy boundaries". allowed-tools: Read,Glob,Grep,Write,Edit argument-hint: "<product-capabilities> <chain-set> <trust-model>" version: 2.0.0 license: MIT author: Jeremy Longshore jeremy@intentsolutions.io tags: [saas, alchemy, architecture, governance] model: inherit effort: high compatibility: "Designed for Claude Code; live Alchemy access requires network access, an appropriate credential, account capacity, and explicit approval"
Alchemy Production Reference Architecture
Overview
Design a production Alchemy architecture with capability-specific adapters, explicit trust boundaries, partial-state semantics, and reversible operations. This workflow produces a reviewable artifact and negative-path evidence before any live side effect.
Prerequisites
- Current first-party Alchemy documentation for the selected product, chain, feature, client, authentication method, limit, and lifecycle.
- Named product, application, security, data/privacy, budget, release, and operations owners appropriate to the requested scope.
- Synthetic or approved non-production fixtures, a credential canary, explicit success criteria, and a tested rollback boundary.
Current Contract
Current architecture separates EVM RPC through viem, Data APIs through typed HTTP adapters, Wallet APIs v5 through a transaction-policy boundary, Notify intake through authenticated idempotent queues, and Admin usage through restricted operations tooling. No shared archived SDK client or credential should collapse these contracts.
Authentication
Model browser, edge, API, worker, webhook, Admin, and signer identities separately. Application keys may serve permitted reads; Admin access keys, Notify tokens, webhook signing keys, and wallet signing authority remain isolated by runtime, owner, and policy.
Instructions
- Inventory user journeys, data ownership, chains, Node/Data/Portfolio/Wallet/Notify/Admin capabilities, writes, callbacks, SLOs, and regulatory constraints.
- Draw trust and data-flow boundaries including browser access, server adapters, queue, cache, database, secret store, observability, signer, provider, and external metadata.
- Define typed capability adapters with chain assertions, pagination, partial success, finality, idempotency, bounded retry, and unsupported-feature outcomes.
- Keep read paths and transaction intent/signing paths separate; require simulation, policy, user consent, and audit receipts for writes.
- Design account-wide backpressure, cache freshness, webhook acknowledgement/replay, provider outage, status reconciliation, privacy deletion, and cost controls.
- Threat-model and failure-test the design, map owners and approvals, then document incremental rollout and rollback variants.
Tool Discipline
Use Read, Glob, and Grep to inspect current documentation, configuration, code, fixtures, and evidence. Use Write and Edit only for approved repository artifacts. Skill invocation alone does not authorize network access, credentials, wallet addresses, customer data, plan changes, spend, key creation or rotation, webhook changes, deployment, replay, transaction construction, signing, broadcast, or deletion.
Approval Boundaries
Architecture, security, product, operations, privacy/data, and budget owners approve their boundaries. Introducing a signer, browser credential, new retained data, or external provider requires explicit review.
Error Handling
- Do not model Alchemy as one reliable box; show endpoint families, account limits, partial responses, indexing, and chain finality.
- Do not let a queue acknowledgement imply successful downstream blockchain or user-visible processing.
- Do not place Admin or signing credentials in the general application API tier.
Output
Return the context and data-flow diagrams, capability/client matrix, credential and ownership map, state/error contracts, SLO/capacity model, threat model, failure tests, rollout variants, and rollback plan. Mark assumptions, observations, source dates, environment-specific behavior, owners, and unresolved gaps explicitly.
Examples
- Route a browser request through a server Portfolio adapter that preserves partial network state and caches only under an explicit freshness label.
- Place Wallet APIs transaction construction and signer policy outside the read API so a compromised read key cannot authorize a transaction.
Validation
Exercise and record expected and observed results for:
- browser boundary bypass
- wrong chain
- Portfolio partial success
- queue duplicate
- account saturation
- signer unavailable
Resources
- Current first-party evidence map — recheck dated Alchemy sources before execution.
- Treat observed account, application, network, indexer, chain, or provider behavior as environment-specific evidence, never a universal guarantee.
Related Skills
ai-job-search
44.8kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
41.7kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
