ai-architect SKILL.md skillA

ai-architect from nerviz-ai/nerviz is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add nerviz-ai/nerviz/ai-architect@git:20261014.c9ffbdd

Pins git:20261014.c9ffbdd in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
nerviz-ai/nerviz
Path
.claude/skills/ai-architect/SKILL.md
Versions recorded
2
Latest version
git:20261014.c9ffbdd, committed Oct 14, 2026
First version recorded
Oct 12, 2026
Size
20,566 bytes
Repository stars
8
License
MIT

Designs the outbound AI ports of an already-scoped use case — a language model asked for a structured answer (classify, extract, moderate) or an embedding model and a vector store asked for the nearest items (semantic search, duplicate detection) — into the `29-ai.md` partial: the prompt resources, the answer type with closed fields and what an unusable answer becomes, which fields go to the provider, the store and who re-indexes it, timeout and the one retrying layer, failure families…

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

## Available specs

!`find "${CLAUDE_PROJECT_DIR:-.}/docs/use-cases" -mindepth 1 -maxdepth 1 -type d -name 'UC-*' 2>/dev/null | sort`

Empty above → none yet, run `/use-case-design` first. (`find`, not an `ls` glob: under zsh an unmatched glob
aborts the command before any fallback runs.)

## Target

$ARGUMENTS

---

# AI Architect

Designs **what a model is asked, with which data, and what its answer is allowed to change**: the
prompt as a versioned resource, the answer as a type whose closed fields the model cannot escape,
the "could not decide" value every unusable answer becomes, the fields that cross to the provider
and the ones that never do, the store a semantic search reads and who keeps it current, and how a
slow, refusing or absent provider reaches the caller. The domain already said what the port means
and which state waits for a person — that is `10-domain.md`. This skill makes the model's side of
that port honest.

**Entry rule: no AI port, no AI design.** This skill reads
`docs/use-cases/UC-NNN-<slug>/10-domain.md` and runs only when § Ports declares an output port of
kind `LLM` or `vector store`. None → stop and say so. `00-use-case.md` is required too: the
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add nerviz-ai/nerviz/ai-architect@sha256:42aa90e47f8286a1

The line at the top of this page pins the label git:20261014.c9ffbdd, 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_64zjqujzozgyupdd.svg)](https://markdownregistry.com/a/art_64zjqujzozgyupdd)

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

Versions

The registry has recorded 2 versions of this file, between Oct 12, 2026 and Oct 14, 2026, about one every day.

versioncommittedcommitsizeaudit
git:20261014.c9ffbdd latest2026-10-14 c9ffbdd 20,566 BA view · diff
git:20261012.ff599052026-10-12 ff59905 20,604 BA view

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 (20566 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

nerviz-ai/nerviz · 8 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_64zjqujzozgyupdd
GET https://markdownregistry.com/api/v1/resolve?ref=nerviz-ai/nerviz/ai-architect
GET https://markdownregistry.com/api/v1/blob/42aa90e47f8286a18055f70840591373344b5ea2d19a19185d05ec35270a26fd

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 nerviz-ai/nerviz

arch-adopt SKILL.md skill
nerviz-ai/nerviz · .claude/skills/arch-adopt/SKILL.md · Installs or updates this architecture's `.claude/` inside a Java project — norms with their globs derived for the…
git:20261019.2720210 · audit A · 8 stars
arch-doctor SKILL.md skill
nerviz-ai/nerviz · .claude/skills/arch-doctor/SKILL.md · Diagnoses the AI setup and architecture enforcement on this machine: active hooks, loaded boundary rules, build…
git:20261021.6793372 · audit A · 8 stars
audit-usage SKILL.md skill
nerviz-ai/nerviz · .claude/skills/audit-usage/SKILL.md · Reads the execution trail the `audit` hook writes into `.claude/audit-usage/` and consolidates it across runs —…
git:20261008.68d46fc · audit A · 8 stars
cache-architect SKILL.md skill
nerviz-ai/nerviz · .claude/skills/cache-architect/SKILL.md · Designs the application cache of an already-scoped use case — which reads are served from a copy, the key of each…
git:20261014.c9ffbdd · audit A · 8 stars
claude-code-architect-designer SKILL.md skill
nerviz-ai/nerviz · .claude/skills/claude-code-architect-designer/SKILL.md · Decides which Claude Code extension resolves a scenario — auto-invocable skill, manually-invoked skill, subagent, rule…
git:20261015.1303b8c · audit A · 8 stars
docker-architect SKILL.md skill
nerviz-ai/nerviz · .claude/skills/docker-architect/SKILL.md · Extends a project's docker-compose.yml and Dockerfile after project-bootstrap's base generation — adds the database or…
git:20261020.a3a3343 · audit B · 8 stars
domain-modeling SKILL.md skill
nerviz-ai/nerviz · .claude/skills/domain-modeling/SKILL.md · Details the domain and application layer of an already-designed use case — aggregate, value objects, invariants, ports…
git:20261014.7301cd9 · audit A · 8 stars
git-publish SKILL.md skill
nerviz-ai/nerviz · .claude/skills/git-publish/SKILL.md · Offers to git init/commit the current project and, optionally, create a GitHub repo (via `gh`) and push — always behind…
git:20261008.5e2a79c · audit A · 8 stars
gof-design-patterns SKILL.md skill
nerviz-ai/nerviz · .claude/skills/gof-design-patterns/SKILL.md · Chooses and implements a design pattern in Java/Spring from the symptom that justifies it. Use when the request…
git:20261014.a222dba · audit A · 8 stars
graphql-api-architect SKILL.md skill
nerviz-ai/nerviz · .claude/skills/graphql-api-architect/SKILL.md · Designs the inbound GraphQL adapter of an already-modeled use case — schema-first, Spring for GraphQL on the servlet…
git:20261014.5f1549e · audit A · 8 stars
http-client-architect SKILL.md skill
nerviz-ai/nerviz · .claude/skills/http-client-architect/SKILL.md · Designs the outbound HTTP adapter of an already-modeled use case — which client (HTTP interface with @HttpExchange over…
git:20261014.5f1549e · audit A · 8 stars
init-project SKILL.md skill
nerviz-ai/nerviz · .claude/skills/init-project/SKILL.md · Initializes a Spring Boot project from scratch with a selectable architecture. Manual ritual — interview, validate the…
git:20261021.c4eef46 · audit A · 8 stars

Every file in nerviz-ai/nerviz

Other files named ai-architect

ai-architect SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-architect/SKILL.md · Research and advise on the best way to approach a software project, including architecture, tech stack, implementation…
git:20260926.b0fd9cf · audit A · 61 stars
ai-architect SKILL.md skill
ice-lfernandes/claude-spring-architect · .claude/skills/ai-architect/SKILL.md · Designs the outbound AI ports of an already-scoped use case — a language model asked for a structured answer (classify…
git:20261014.c9ffbdd · audit A · 6 stars

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