Agent skill

Aivisspeech Engine Sentry Triage

by Aivis-Project in Aivis-Project/AivisSpeech-Engine

AivisSpeech Engine の Sentry issue を調査し、修正すべきエンジン側の不具合と、入力値・ローカル環境・外部サービス由来のノイズを切り分けるためのスキルです。Sentry 側で既知ノイズを永続アーカイブする作業や、voicevoxengine/utility/sentryutility.py と関連テストを更新して既知ノイズを送信前に破棄する作業で使用します。

LGPL-3.0Auto-check passedMedia & Creative

Install Aivisspeech Engine Sentry Triage

skills CLI
$ npx skills add Aivis-Project/AivisSpeech-Engine --skill aivisspeech-engine-sentry-triage -a claude-code

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

GitHub CLI
$ gh skill install Aivis-Project/AivisSpeech-Engine aivisspeech-engine-sentry-triage --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/Aivis-Project/AivisSpeech-Engine.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/aivisspeech-engine-sentry-triage .claude/skills/aivisspeech-engine-sentry-triage && 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
aivisspeech-engine-sentry-triage
GitHub stars
182
Token cost
~545 tokens
SKILL.md length
121 words
Files
6 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
LGPL-3.0

At a glance

AivisSpeech Engine の Sentry issue を調査し、修正すべきエンジン側の不具合と、入力値・ローカル環境・外部サービス由来のノイズを切り分けるためのスキルです。Sentry 側で既知ノイズを永続アーカイブする作業や、voicevoxengine/utility/sentryutility.py と関連テストを更新して既知ノイズを送信前に破棄する作業で使用します。

  • Works in 7 steps: Sentry の実データから issue とイベントを確認します → 各 issue… → ユーザーが Sentry 側の整理を依頼した場合だけ、確定ノイズの issue… → …
  • Tasks that involve Text to speech and voice
  • SKILL.md covers 作業手順, 修正判断, 必読資料 and リポジトリ前提
  • Runs Python scripts from its folder; calls uv; needs SENTRY_AUTH_TOKEN

What it does

Aivisspeech Engine Sentry Triage is an agent skill from Aivis-Project/AivisSpeech-Engine. AivisSpeech Engine の Sentry issue を調査し、修正すべきエンジン側の不具合と、入力値・ローカル環境・外部サービス由来のノイズを切り分けるためのスキルです。Sentry 側で既知ノイズを永続アーカイブする作業や、voicevoxengine/utility/sentryutility.py と関連テストを更新して既知ノイズを送信前に破棄する作業で使用します。

Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/classification.md` and `references/filter-implementation.md`).

It sits in Media & Creative, covering Text to speech and voice. It works with Sentry, Python, FastAPI and ONNX. The repository describes itself as: AivisSpeech Engine: AI Voice Imitation System - Text to Speech Engine. The licence is LGPL-3.0.

When your agent uses it

  • Tasks that involve Text to speech and voice

Example prompts

  • “/aivisspeech-engine-sentry-triage”

Requirements

  • Python 3
  • A credential in SENTRY_AUTH_TOKEN

Workflow steps

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

  1. Sentry の実データから issue とイベントを確認します
  2. 各 issue を「修正対象」「入力値ノイズ」「ローカル環境ノイズ」「外部サービスノイズ」「保留」に分類します
  3. ユーザーが Sentry 側の整理を依頼した場合だけ、確定ノイズの issue を永続アーカイブします
  4. 同じノイズを送信前に破棄するため、voicevox_engine/utility/sentry_utility.py を更新します
  5. test/unit/utility/test_sentry_utility.py に絞り込みテストを追加します
  6. 修正すべきエラーは、修正先がこのリポジトリ内かどうかを切り分けます
  7. リポジトリルートから uv run の検証コマンドを実行します

What it can do on your machine

Read from SKILL.md and the folder at commit 880aa9b. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    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 these keys or tokens, usually read from environment variables:

    • SENTRY_AUTH_TOKEN

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

Context cost

Aivisspeech Engine Sentry Triage loads about 545 tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 58 tokens; SKILL.md has 121 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~545
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.3k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from Aivis-Project/AivisSpeech-Engine at commit 880aa9b, republished under its LGPL-3.0 licence (© Aivis-Project). 121 words, ~545 tokens.

Download SKILL.mdSave it as .claude/skills/aivisspeech-engine-sentry-triage/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
aivisspeech-engine-sentry-triage
description
AivisSpeech Engine の Sentry issue を調査し、修正すべきエンジン側の不具合と、入力値・ローカル環境・外部サービス由来のノイズを切り分けるためのスキルです。Sentry 側で既知ノイズを永続アーカイブする作業や、voicevox_engine/utility/sentry_utility.py と関連テストを更新して既知ノイズを送信前に破棄する作業で使用します。

AivisSpeech Engine Sentry トリアージ

作業手順

このスキルは、AivisSpeech Engine で今後も繰り返す Sentry ノイズ処理の流れで使用します。

  1. Sentry の実データから issue とイベントを確認します
  2. 各 issue を「修正対象」「入力値ノイズ」「ローカル環境ノイズ」「外部サービスノイズ」「保留」に分類します
  3. ユーザーが Sentry 側の整理を依頼した場合だけ、確定ノイズの issue を永続アーカイブします
  4. 同じノイズを送信前に破棄するため、voicevox_engine/utility/sentry_utility.py を更新します
  5. test/unit/utility/test_sentry_utility.py に絞り込みテストを追加します
  6. 修正すべきエラーは、修正先がこのリポジトリ内かどうかを切り分けます
  7. リポジトリルートから uv run の検証コマンドを実行します

フィルタを変更する前に、必ず Sentry の実 issue / イベントを確認します。
イベント詳細が取得できる場合は、タイトルだけで分類しないでください。

修正判断

AivisSpeech Engine 側で完結する問題は、ユーザーの追加承認を待たずに修正します。
たとえば API バリデーション不足、AudioQuery モデルの検証不足、Engine 側の例外処理・レスポンス変換・Sentry フィルタ漏れ、Engine 側で管理している辞書データの不整合は、このリポジトリで実装とテストまで進めます。

SBV2 コア、依存ライブラリ、配布モデル、別リポジトリの辞書データに修正が必要な場合は、このリポジトリだけで直せるように見せかけません。
Sentry issue、最新イベント、該当スタック、再現条件、修正候補、修正先リポジトリを短くまとめて、ユーザーへ対応依頼として報告します。

修正先が曖昧な場合は、まずこのリポジトリ内で入力検証・前処理・呼び出し境界を確認します。
Engine 側で不正入力を止められるなら Engine 側で直し、コア内部の正常入力処理で壊れている場合はユーザーへ詳細報告します。

必読資料

作業前に以下を読みます。

  • references/sentry-workflow.md: Sentry API の使い分け、90日 issue 一覧、アーカイブ時の注意
  • references/classification.md: 既存調査に基づく「破棄」「残す」「保留」の分類ルール
  • references/filter-implementation.md: このリポジトリでの実装・テスト方針

タイトルベースの粗い確認だけでよい場面では、scripts/probe_sentry_filter.py を使えます。

bash
uv run python .codex/skills/aivisspeech-engine-sentry-triage/scripts/probe_sentry_filter.py \
  --repo-root . \
  --query "is:ignored" \
  --stats-period 90d

このスクリプトは読み取り専用です。
最終的な「残す / 破棄する」判断の前にはイベント詳細を確認してください。

リポジトリ前提

コマンドは AivisSpeech Engine のリポジトリルートから実行します。

Python 実行には uv run python を使います。
グローバルの python や python3 は絶対に使いません。

バンドル済み Sentry helper で取得できる内容は、まず helper を使います。
helper で表現できないクエリが必要な場合は、curl または uv run python で Sentry REST API を直接叩きます。
ただし、ユーザーが Sentry issue 状態の更新を明示した場合を除き、読み取り専用のリクエストに限定します。

SENTRY_AUTH_TOKEN は絶対に出力しません。

ユーザーが明示しない限り、ステージング、ステージング解除、コミット、リセット、クリーンアップ、ファイル削除は行いません。

© Aivis-Project, LGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references) in .codex/skills/aivisspeech-engine-sentry-triage of Aivis-Project/AivisSpeech-Engine.

  • SKILL.md
  • agents/openai.yaml
  • references/classification.md
  • references/filter-implementation.md
  • references/sentry-workflow.md
  • scripts/probe_sentry_filter.py

Open the folder on GitHubat commit 880aa9b

Compare with similar skills

Aivisspeech Engine Sentry Triage 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.

Aivisspeech Engine Sentry Triage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Aivisspeech Engine Sentry Triage this skillAivis-Project/AivisSpeech-Engine182—~545Automated safety check: PassLGPL-3.0
Kokoro Ttscalesthio/generative-media-skills197—~4.8kAutomated safety check: PassMIT
Azure Realtime Podcast Generationmicrosoft/skills3.1k1 repos~947Automated safety check: PassMIT
Webcode Local Windows Tts Installershuyu-labs/WebCode278—~787Automated safety check: PassCustom licence
Sentry Python SDKgetsentry/sentry-for-ai268—~4.1kAutomated safety check: PassApache-2.0
Deepgram Python Text-to-Speechdeepgram/deepgram-python-sdk469—~1.8kAutomated safety check: PassMIT

Similar skills

  • Kokoro Tts

    calesthio/generative-media-skills

    Local and self-hosted text-to-speech with Kokoro, the ~82M-parameter open-weight (Apache 2.0) model by hexgrad.

    197 GitHub stars~4.8k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Official

    Builds podcast-style audio narration from text with Azure OpenAI's GPT Realtime Mini over WebSocket, from a Python FastAPI backend to a React player.

    3.1k GitHub starsUsed in 1 repo~947 tokens
    Media & CreativeAuto-check passed
  • A skill your agent uses when building a local Windows WebCode installer from this repo for machine testing, especially when the package must bundle the Kokoro or sherpa-onnx Reply TTS service, model…

    278 GitHub stars~787 tokensUpdated 3 mo ago
    Media & CreativeAuto-check passed
  • Sentry Python SDK

    getsentry/sentry-for-ai

    Official

    Full Sentry SDK setup for Python. An agent skill from getsentry/sentry-for-ai.

    268 GitHub stars~4.1k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Deepgram Python Text-to-Speech

    deepgram/deepgram-python-sdk

    Guides Python code that calls Deepgram Text-to-Speech v1, covering one-shot REST, streaming WebSocket and the TextBuilder helper.

    469 GitHub stars~1.8k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Speech Engine

    elevenlabs/skills

    Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine.

    482 GitHub stars~2.5k tokensUpdated yesterday
    Media & CreativeAuto-check: warnings

Questions about Aivisspeech Engine Sentry Triage

What does Aivisspeech Engine Sentry Triage do?

AivisSpeech Engine の Sentry issue を調査し、修正すべきエンジン側の不具合と、入力値・ローカル環境・外部サービス由来のノイズを切り分けるためのスキルです。Sentry 側で既知ノイズを永続アーカイブする作業や、voicevoxengine/utility/sentryutility.py と関連テストを更新して既知ノイズを送信前に破棄する作業で使用します。. Aivisspeech Engine Sentry Triage is an agent skill from Aivis-Project/AivisSpeech-Engine.

When should I use Aivisspeech Engine Sentry Triage?

Aivisspeech Engine Sentry Triage fits situations like: tasks that involve Text to speech and voice.

How do I install Aivisspeech Engine Sentry Triage in Claude Code?

Run `npx skills add Aivis-Project/AivisSpeech-Engine --skill aivisspeech-engine-sentry-triage -a claude-code`. Or copy the skill folder (.codex/skills/aivisspeech-engine-sentry-triage in Aivis-Project/AivisSpeech-Engine) into .claude/skills/aivisspeech-engine-sentry-triage in your project. Claude Code loads it when a task matches its description.

How do I install Aivisspeech Engine Sentry Triage in Codex?

Run `npx skills add Aivis-Project/AivisSpeech-Engine --skill aivisspeech-engine-sentry-triage -a codex`. Or copy the skill folder (.codex/skills/aivisspeech-engine-sentry-triage in Aivis-Project/AivisSpeech-Engine) into .agents/skills/aivisspeech-engine-sentry-triage in your project. Codex loads it when a task matches its description.

Can I use Aivisspeech Engine Sentry Triage 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 Aivis-Project/AivisSpeech-Engine --skill aivisspeech-engine-sentry-triage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aivisspeech-engine-sentry-triage, .gemini/skills/aivisspeech-engine-sentry-triage, .github/skills/aivisspeech-engine-sentry-triage and .opencode/skills/aivisspeech-engine-sentry-triage in your project.

What does Aivisspeech Engine Sentry Triage need to run?

Going by SKILL.md and its folder, Aivisspeech Engine Sentry Triage needs Python for the scripts in its folder, the command-line tools its instructions call (uv) and credentials named SENTRY_AUTH_TOKEN. Our summary lists: Python 3; A credential in SENTRY_AUTH_TOKEN.

Does Aivisspeech Engine Sentry Triage 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 Aivisspeech Engine Sentry Triage 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Aivisspeech Engine Sentry Triage use?

Aivisspeech Engine Sentry Triage is published under the LGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Aivisspeech Engine Sentry Triage use?

About 545 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.7k tokens, read only when the agent opens those files.

What are the alternatives to Aivisspeech Engine Sentry Triage?

Skills that share tags, products or a category with Aivisspeech Engine Sentry Triage: Kokoro Tts (calesthio/generative-media-skills, 197 stars), Azure Realtime Podcast Generation (microsoft/skills, 3.1k stars), Webcode Local Windows Tts Installer (shuyu-labs/WebCode, 278 stars) and Sentry Python SDK (getsentry/sentry-for-ai, 268 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Aivisspeech Engine Sentry Triage?

Aivis-Project (a GitHub organization) maintains it in Aivis-Project/AivisSpeech-Engine, which has 182 GitHub stars. The repository was last updated on October 10, 2026.

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