New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Architecture Review

by extra-org in extra-org/extra

Guard the project's architecture invariants. An agent skill from extra-org/extra.

MITAuto-check passedDevelopment

Install Architecture Review

skills CLI
$ npx skills add extra-org/extra --skill architecture-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install extra-org/extra architecture-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/extra-org/extra.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/architecture-review .claude/skills/architecture-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
architecture-review
GitHub stars
113
Token cost
~1.1k tokens
SKILL.md length
521 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Guard the project's architecture invariants. An agent skill from extra-org/extra.

  • Works in 6 steps: Map the change to layers. Identify which… → Check the pipeline direction. Data flows… → Check lifecycles. Engine-once vs.… → …
  • Evaluate any change affecting layers
  • SKILL.md covers Purpose, When to Use This Skill, Files to Read First and Core Principles (project…, plus 4 more sections
  • Calls make

What it does

Architecture Review is an agent skill from extra-org/extra. Guard the project's architecture invariants. Use to evaluate any change affecting layers, boundaries, lifecycles, or contracts, and to decide whether an ADR is required.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Software architecture and Architecture decision records. The repository describes itself as: Turn your product into an AI-powered assistant. The licence is MIT.

When your agent uses it

  • Evaluate any change affecting layers
  • To decide whether an ADR is required

Example prompts

  • “/architecture-review”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Map the change to layers. Identify which src/agentplatform/
  2. Check the pipeline direction. Data flows validate → compile → graph →
  3. Check lifecycles. Engine-once vs. context-per-request; no request state
  4. Check boundaries. No client/business logic in the runtime; external
  5. Check contracts. If the YAML schema, plugin contracts, or API shape
  6. Decide. Conforms / needs redesign / needs an ADR. Record reasoning.

What it can do on your machine

Read from SKILL.md and the folder at commit 9811f5e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • make

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Architecture Review loads about 1.1k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 521 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from extra-org/extra at commit 9811f5e, republished under its MIT licence (© extra-org). 521 words, ~1,128 tokens.

Download SKILL.mdSave it as .claude/skills/architecture-review/SKILL.md (or your agent's skills folder).
name
architecture-review
description
Guard the project's architecture invariants. Use to evaluate any change affecting layers, boundaries, lifecycles, or contracts, and to decide whether an ADR is required.
generated
true
source
.ai/skills/architecture-review.md
<!--
This file is generated by tools/skills.
Do not edit this file directly.
Edit .ai/skills/architecture-review.md and run `make generate-ai`.
-->

Skill: Architecture Review

Purpose

Guard the project's architecture invariants. Use this to evaluate any change that affects layers, boundaries, lifecycles, or contracts — and to decide whether an ADR is required.

When to Use This Skill

  • A change touches more than one layer or moves logic between layers.
  • A change affects the runtime lifecycle, the YAML→graph pipeline, prompts, plugin contracts, or tool/MCP integration.
  • Reviewing whether a design respects the project's invariants.
  • Before approving anything that alters a public contract.

Files to Read First

  • AGENTS.md §3 (non-negotiable rules) and §4 (layout).
  • docs/ARCHITECTURE.md and docs/RUNTIME_LIFECYCLE.md.
  • All ADRs in docs/adr/.
  • The specific layer doc(s) the change touches.

Core Principles (project architecture invariants)

These are binding. A change that violates one must be redesigned or justified by a new/updated ADR.

  • YAML is declarative, not executable logic. No code execution from spec values; routing conditions are declarative.
  • Validate before compile. YAML is validated before it is compiled.
  • Runtime never executes raw YAML dictionaries. It operates only on typed compiled models.
  • Validated config compiles into typed internal models (CompiledAgentGraph).
  • RuntimeEngine is created once at startup; the compiled graph is immutable and shared read-only.
  • ExecutionContext is created per request and holds all request-scoped state. No request state on the engine/graph.
  • Prompt templates may be cached; rendered values are resolved per request. No global cache of rendered prompts.
  • Client-specific auth/context/business logic lives in plugin boundary, never in the runtime.
  • Tool permissions are enforced outside prompts, at the tool/data layer; injected params can't be overridden by the model.
  • Agents declare needs; the runtime resolves and enforces them.
  • Plugin contracts stay generic — no client-specific fields baked into it.
  • MCP/tool integrations go through adapters, not directly into core logic.
Show full SKILL.md (244 more words)Show less

Process

  1. Map the change to layers. Identify which src/agentplatform/<layer> packages it touches and whether responsibilities stay separated.
  2. Check the pipeline direction. Data flows validate → compile → graph → runtime → (prompts/context/tools). Flag backward/sideways coupling.
  3. Check lifecycles. Engine-once vs. context-per-request; no request state on long-lived objects; graph immutable.
  4. Check boundaries. No client/business logic in the runtime; external systems behind adapters; security enforced outside prompts.
  5. Check contracts. If the YAML schema, plugin contracts, or API shape changes, require an ADR and assess compatibility.
  6. Decide. Conforms / needs redesign / needs an ADR. Record reasoning.

Checklist Before Finishing

  • Each invariant in Core Principles is satisfied (or an ADR justifies a change).
  • Change sits in the correct layer; boundaries intact.
  • Pipeline direction preserved; no improper coupling.
  • Engine-once / context-per-request lifecycle respected.
  • No client-specific logic in the runtime; integrations via adapters.
  • Security enforced outside prompts; injected params non-overridable.
  • Contract changes have an ADR and a compatibility note.
  • make check passes.

Common Mistakes to Avoid

  • Letting the runtime read raw YAML or skip compilation.
  • Storing request state on RuntimeEngine/compiled graph for convenience.
  • Caching rendered prompts globally.
  • Slipping client auth/business rules into the runtime instead of plugins.
  • Calling MCP/LLM/DB directly from core logic instead of through an adapter.
  • Changing a contract silently without an ADR.

Expected Final Report

State: which layers/contracts the change touches; how each relevant invariant is upheld (or which ADR justifies a deviation); lifecycle/boundary findings; whether an ADR is required; and a clear verdict (conforms / redesign / ADR needed).

© extra-org, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/architecture-review of extra-org/extra.

Open the folder on GitHubat commit 9811f5e

Compare with similar skills

Architecture Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Architecture Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Architecture Review this skillextra-org/extra113—~1.1kAutomated safety check: PassMIT
Create Vibe Featuremistralai/mistral-vibe5.1k—~1.2kAutomated safety check: PassApache-2.0
Architecture Decisions and ADRsfirst-fluke/oh-my-agent1.3k—~2.6kAutomated safety check: PassMIT
System Architecture DesignerJeffallan/claude-skills12k—~1.2kAutomated safety check: PassMIT
Light System DesignLight0305/Light-skills640—~3.6kAutomated safety check: PassMIT
Architecture DesignerAratKruglik/claude-laravel1551 repos~895Automated safety check: PassNone

Similar skills

  • Create Vibe Feature

    mistralai/mistral-vibe

    Official

    Guides feature work in the Mistral Vibe Python CLI so each change lands in the right module and matches the project's architecture decision records.

    5.1k GitHub stars~1.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Architecture Decisions and ADRs

    first-fluke/oh-my-agent

    Evaluates system boundaries and tradeoffs and writes architecture recommendations, option comparisons or ADRs, with a Mermaid diagram when structure changes.

    1.3k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed

  • System Architecture Designer

    Jeffallan/claude-skills

    Guides system architecture design end to end: gathering requirements, matching them to a pattern, documenting trade-offs with ADRs, and reviewing.

    12k GitHub stars~1.2k tokensUpdated 5 days ago
    DevelopmentAuto-check passed

  • Light System Design

    Light0305/Light-skills

    Evidence-based workflow for designing or modernizing a software system: current-state inventory, options, API and schema contracts, migration plans, ADRs and verification.

    640 GitHub stars~3.6k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed

  • Architecture Designer

    AratKruglik/claude-laravel

    A skill your agent uses when designing new system architecture, reviewing existing designs, or making architectural decisions.

    155 GitHub starsUsed in 1 repo~895 tokens
    DevelopmentAuto-check passed

  • Architecture Decision Record Writer

    dralgorhythm/claude-agentic-framework

    Writes Architecture Decision Records with title, status, context, decision, rationale and consequences for significant technical choices, kept short and numbered.

    125 GitHub stars~529 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed

More from extra-org/extra

All 14 skills in this repo

  • Testing

    extra-org/extra

    How to write and run fast, deterministic, behavior-focused pytest tests that never touch real external systems.

    113 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Documentation

    extra-org/extra

    Keep the repository's documentation accurate, honest, and synchronized with the code.

    113 GitHub stars~848 tokensUpdated today
    Auto-check passed

  • Senior Python Engineering

    extra-org/extra

    The standard for writing Python here — small, typed, explicit, testable modules with side effects pushed to the edges.

    113 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Skill Authoring

    extra-org/extra

    How to create or restructure a skill so the .ai/skills/ system stays consistent, operational, and trustworthy.

    113 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Code Review

    extra-org/extra

    Senior-level code review for the agent platform — architecture and boundaries first, then correctness, security, testability, and simplicity.

    113 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Git Workflow

    extra-org/extra

    Work safely with Git — keep changes scoped and reviewable, never overwrite the user's work, and produce clear history.

    113 GitHub stars~781 tokensUpdated today
    Auto-check: notes

Categories

Questions about Architecture Review

What does Architecture Review do?

Guard the project's architecture invariants. An agent skill from extra-org/extra. Architecture Review is an agent skill from extra-org/extra. Guard the project's architecture invariants.

When should I use Architecture Review?

Architecture Review fits situations like: evaluate any change affecting layers; to decide whether an ADR is required.

How do I install Architecture Review in Claude Code?

Run `npx skills add extra-org/extra --skill architecture-review -a claude-code`. Or copy the skill folder (.claude/skills/architecture-review in extra-org/extra) into .claude/skills/architecture-review in your project. Claude Code loads it when a task matches its description.

How do I install Architecture Review in Codex?

Run `npx skills add extra-org/extra --skill architecture-review -a codex`. Or copy the skill folder (.claude/skills/architecture-review in extra-org/extra) into .agents/skills/architecture-review in your project. Codex loads it when a task matches its description.

Can I use Architecture Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add extra-org/extra --skill architecture-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architecture-review, .gemini/skills/architecture-review, .github/skills/architecture-review and .opencode/skills/architecture-review in your project.

What does Architecture Review need to run?

Going by SKILL.md and its folder, Architecture Review needs the command-line tools its instructions call (make).

Does Architecture Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Architecture Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Architecture Review use?

Architecture Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Architecture Review use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Architecture Review?

Skills that share tags, products or a category with Architecture Review: Create Vibe Feature (mistralai/mistral-vibe, 5.1k stars), Architecture Decisions and ADRs (first-fluke/oh-my-agent, 1.3k stars), System Architecture Designer (Jeffallan/claude-skills, 12k stars) and Light System Design (Light0305/Light-skills, 640 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architecture Review?

extra-org (a GitHub organization) maintains it in extra-org/extra, which has 113 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 8, 2026.

Source: extra-org/extra on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.