Agent skill

Architecture Review

by fossasia in fossasia/eventyay-interpretation

A skill your agent uses to evaluate proposed architecture changes against VoxBento's design principles.

Apache-2.0Auto-check passedBackend & APIs

Install Architecture Review

skills CLI
$ npx skills add fossasia/eventyay-interpretation --skill architecture-review -a claude-code

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

GitHub CLI
$ gh skill install fossasia/eventyay-interpretation 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/fossasia/eventyay-interpretation.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/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
1.6k
Token cost
~1.2k tokens
SKILL.md length
538 words
Files
1
Skills in repo
38
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses to evaluate proposed architecture changes against VoxBento's design principles.

  • Works in 5 steps: Browser-first media. Audio never touches… → FastAPI is coordination only. Routes,… → Jitsi is monitoring only. Interpreters… → …
  • Evaluate proposed architecture changes against VoxBentos design principles
  • SKILL.md covers Fundamental Architecture…, Component Responsibilities…, Evaluating Proposed Changes and Red Flags in Architecture…, plus 1 more section
  • Calls uv

What it does

Architecture Review is an agent skill from fossasia/eventyay-interpretation. Use this skill to evaluate proposed architecture changes against VoxBento's design principles.

Its SKILL.md is about 1.2k 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 Backend & APIs, covering Software architecture and Backend development. It works with Python and FastAPI. The repository describes itself as: A plugin for live interpretation of video streams. The licence is Apache-2.0.

When your agent uses it

  • Evaluate proposed architecture changes against VoxBentos design principles
  • Tasks that involve Software architecture
  • Tasks that involve Backend development

Example prompts

  • “/architecture-review”

Requirements

  • Python 3

Workflow steps

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

  1. Browser-first media. Audio never touches the Python process. Browser → WHIP → MediaMTX → WHEP → listener browser.
  2. FastAPI is coordination only. Routes, WebSocket signalling, auth, admin. No audio processing.
  3. Jitsi is monitoring only. Interpreters watch/hear the floor session. It is not the ingest path.
  4. Single publisher per channel. Enforced at two layers: Python (BoothRegistry.set_active_interpreter) and MediaMTX (overridePublisher: yes).
  5. In-memory booth state. BoothRegistry is module-level in portal/booth_state.py. No external state store yet (see TD-03 in…

What it can do on your machine

Read from SKILL.md and the folder at commit 1ca0139. 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:

    • uv

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

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    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 1.2k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 538 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 fossasia/eventyay-interpretation at commit 1ca0139, republished under its Apache-2.0 licence (© fossasia). 538 words, ~1,157 tokens.

Download SKILL.mdSave it as .claude/skills/architecture-review/SKILL.md (or your agent's skills folder).
name
architecture-review
description
Use this skill to evaluate proposed architecture changes against VoxBento's design principles.

Skill: Architecture Review

Use this skill to evaluate proposed architecture changes against VoxBento's design principles.


Fundamental Architecture Principles

  1. Browser-first media. Audio never touches the Python process. Browser → WHIP → MediaMTX → WHEP → listener browser.
  2. FastAPI is coordination only. Routes, WebSocket signalling, auth, admin. No audio processing.
  3. Jitsi is monitoring only. Interpreters watch/hear the floor session. It is not the ingest path.
  4. Single publisher per channel. Enforced at two layers: Python (BoothRegistry.set_active_interpreter) and MediaMTX (overridePublisher: yes).
  5. In-memory booth state. BoothRegistry is module-level in portal/booth_state.py. No external state store yet (see TD-03 in TECHNICAL_DEBT_REPORT.md).

Component Responsibilities (strict boundaries)

ComponentDoesDoes NOT do
FastAPI portalRoutes, auth, admin, WS coordination, DB queriesAudio processing, transcoding, media relay
MediaMTXWHIP ingest, WHEP playback, RTSP for ffmpegAuth, coordination, UI
Jitsi MeetFloor session monitoring (receive-only iframe)Audio ingest, interpreter publishing
Browser JSWebRTC/WHIP, WebSocket, Jitsi iframe, mic meterServer-side logic, DB access
ffmpeg (spawned)PCM extraction from RTSP for transcriptionAnything else
Transcription providersText from PCM audioMedia relay, broadcast, DB write

Evaluating Proposed Changes

Does this introduce a new dependency?
  • Check if it's already in pyproject.toml.
  • Ask: can this be done with existing FastAPI/SQLAlchemy/httpx capabilities?
  • New Python dependencies → run uv add {pkg} (not pip); never edit uv.lock manually.
Does this add server-side audio processing?
  • STOP. Audio must not flow through the Python process.
  • Route audio directly: browser → MediaMTX → listener.
  • If transcription is needed: use the existing portal/transcription/ subsystem.
Does this add a frontend framework?
  • STOP. Frontend is plain ES modules. No Vue, React, jQuery, build step.
  • See .github/instructions/js.instructions.md for JavaScript conventions.
Does this require a new DB column?
  • Add to portal/models.py with proper Mapped typing.
  • Create an Alembic migration in alembic/versions/.
  • For SQLite compatibility: use batch_alter_table in the migration (see migration 008 as reference).
Does this change the WebSocket protocol?
  • The protocol is used by static/js/interpreter-booth.js — both files must change together.
  • New message types must be handled in portal/websockets/manager.py ws_booth loop + _handle_* function.
  • Role enforcement: role is always from session.granted_role, never from client data['role'].
Show full SKILL.md (202 more words)Show less
Does this change auth?
  • Three separate token types exist (session_token, user_token, admin_token). Do not conflate.
  • All tokens use HS256 with settings.effective_jwt_secret.
  • WebSocket auth: cookies are read at connect time and stored in Session.granted_role.

Red Flags in Architecture Proposals

ProposalRisk
"Add a WebSocket message to send audio data"Violates browser-first principle
"Use Redis for real-time booth state"Valid but requires careful migration of BoothRegistry
"Add a REST endpoint that returns the JWT secret"Security violation
"Encode the role in the WebSocket join message and trust it"Violates role trust model
"Store all session data in a cookie"Risk of cookie size limits + replay attacks
"Add Vue for the admin panel"Violates no-framework constraint
"Use aiortc for SFU"Explicitly forbidden in invariants
"Proxy WHIP through FastAPI"Breaks browser-first media architecture

Good Architecture Patterns in This Codebase

  • safe_redirect(url) — validates redirects to prevent open redirect attacks. Use it for all redirects.
  • _ensure_mediamtx_path(channel_id) — creates alwaysAvailable paths. Call before returning WHIP URL.
  • asyncio.Lock in BoothRegistry — all booth mutations serialized. Prevents race conditions.
  • Lazy DB engine init — _get_engine() in portal/database.py defers connection until first use.
  • from __future__ import annotations — deferred evaluation prevents circular import issues.
  • Fernet encryption for API keys — SHA-256 derived key, supports key rotation via MultiFernet.

© fossasia, Apache-2.0. 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 .agents/skills/architecture-review of fossasia/eventyay-interpretation.

Open the folder on GitHubat commit 1ca0139

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in fossasia/eventyay-interpretation, which our catalogue first saw on October 7, 2026.

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 skillfossasia/eventyay-interpretation1.6k—~1.2kAutomated safety check: PassApache-2.0
Code Review Skillawesome-skills/code-review-skill2.1k—~2.8kAutomated safety check: NotesMIT
Documentation Guidevolfpeter/holm132—~1.4kAutomated safety check: PassMIT
Framework Migration AssistantArabelaTso/Skills-4-SE253—~1.9kAutomated safety check: PassApache-2.0
Engineering PrinciplesAzure/agent-app-orchestrator103—~282Automated safety check: PassMIT
Specx Diwire Compositionmaksimzayats/specx202—~1.1kAutomated safety check: PassMIT

Similar skills

  • Code Review Skill

    awesome-skills/code-review-skill

    Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C/.NET, Kotlin, Swift, Dart…

    2.1k GitHub stars~2.8k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes
  • Documentation Guide

    volfpeter/holm

    A skill your agent uses when writing or modifying documentation, guides, or example READMEs.

    132 GitHub stars~1.4k tokensUpdated 25 days ago
    Backend & APIsAuto-check passed
  • Framework Migration Assistant

    ArabelaTso/Skills-4-SE

    Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI).

    253 GitHub stars~1.9k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Engineering Principles

    Azure/agent-app-orchestrator

    Official

    Agent Landing Zone Orchestrator architecture and implementation principles.

    103 GitHub stars~282 tokensUpdated 2 days ago
    Backend & APIsAuto-check passed
  • Specx Diwire Composition

    maksimzayats/specx

    Wire dependency injection for a specx Python service with diwire.

    202 GitHub stars~1.1k tokensUpdated 2 mo ago
    Backend & APIsAuto-check passed
  • Python Development Python Scaffold

    aiskillstore/marketplace

    You are a Python project architecture expert specializing in scaffolding production-ready Python applications.

    433 GitHub starsUsed in 7 repos~1.9k tokens
    Backend & APIsAuto-check passed

More from fossasia/eventyay-interpretation

All 38 skills in this repo
  • Git Guardrails Claude Code

    fossasia/eventyay-interpretation

    Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.

    1.6k GitHub starsUsed in 12 repos~578 tokens
    Auto-check passed
  • Diagnosing Bugs

    fossasia/eventyay-interpretation

    Diagnosis loop for hard bugs and performance regressions. An agent skill from fossasia/eventyay-interpretation.

    1.6k GitHub starsUsed in 32 repos~2.1k tokens
    Auto-check passed
  • Domain Modeling

    fossasia/eventyay-interpretation

    Build and sharpen a project's domain model. An agent skill from fossasia/eventyay-interpretation.

    1.6k GitHub starsUsed in 30 repos~821 tokens
    Auto-check passed
  • Improve

    fossasia/eventyay-interpretation

    Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute.

    1.6k GitHub starsUsed in 10 repos~3.7k tokens
    Auto-check: warnings
  • Migrate To Shoehorn

    fossasia/eventyay-interpretation

    Migrate test files from as type assertions to @total-typescript/shoehorn.

    1.6k GitHub starsUsed in 12 repos~698 tokens
    Auto-check passed
  • Setup Pre Commit

    fossasia/eventyay-interpretation

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo.

    1.6k GitHub starsUsed in 12 repos~565 tokens
    Auto-check passed

Works with

Questions about Architecture Review

What does Architecture Review do?

A skill your agent uses to evaluate proposed architecture changes against VoxBento's design principles. Architecture Review is an agent skill from fossasia/eventyay-interpretation. Use this skill to evaluate proposed architecture changes against VoxBento's design principles.

When should I use Architecture Review?

Architecture Review fits situations like: evaluate proposed architecture changes against VoxBentos design principles; tasks that involve Software architecture; tasks that involve Backend development.

How do I install Architecture Review in Claude Code?

Run `npx skills add fossasia/eventyay-interpretation --skill architecture-review -a claude-code`. Or copy the skill folder (.agents/skills/architecture-review in fossasia/eventyay-interpretation) 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 fossasia/eventyay-interpretation --skill architecture-review -a codex`. Or copy the skill folder (.agents/skills/architecture-review in fossasia/eventyay-interpretation) 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 fossasia/eventyay-interpretation --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 (uv). Our summary lists: Python 3.

Does Architecture Review access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. 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 Apache-2.0 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 1.2k tokens (SKILL.md is roughly 4.6k 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: Code Review Skill (awesome-skills/code-review-skill, 2.1k stars), Documentation Guide (volfpeter/holm, 132 stars), Framework Migration Assistant (ArabelaTso/Skills-4-SE, 253 stars) and Engineering Principles (Azure/agent-app-orchestrator, 103 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architecture Review?

fossasia (a GitHub organization) maintains it in fossasia/eventyay-interpretation, which has 1,551 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 5, 2026.

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