A pre-commit documentation review that checks whether project guides and change logs still match code changes. It covers files such as CLAUDE.md, README files, CHANGELOG, feature documentation, and code comments.

Use it before committing or for a chosen commit range, staged changes, or file. It reviews implementation, test, build, and documentation changes and updates documentation where needed.

It reduces documentation drift, where the code changes but instructions and descriptions become outdated. Finding these mismatches before a commit helps keep the project understandable.

How ayutaz/piper-plus configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ayutaz/piper-plus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ayutaz/piper-plus/dev/.claude/skills/sync-docs/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ayutaz/piper-plus

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ayutaz/piper-plus/sync-docs/github.svg)](https://agentmods.dev/skills/ayutaz/piper-plus/sync-docs)

Your own site

<a href="https://agentmods.dev/skills/ayutaz/piper-plus/sync-docs"><img src="https://agentmods.dev/badge/skills/ayutaz/piper-plus/sync-docs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ayutaz/piper-plus/sync-docs"><img src="https://agentmods.dev/badge/skills/ayutaz/piper-plus/sync-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,622 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.02622
Opus 5.5	$0.00024	$0.01049
Sonnet 5.5	$0.00012	$0.00524
Haiku 4.5	$0.00006	$0.00262

Measured 14d ago against content hash 9aed5d3efdd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sync-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/sync-docs/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ドキュメント同期 (エージェントチーム並列監査)

コード変更に対して CLAUDE.md / README / CHANGELOG / docs/features / docstring を一括で監査し、更新が必要な箇所を検出して自動適用します。

前提

このスキルは コミット前 に使うことを想定しています。コミット済みの変更と未ステージ変更の両方を対象にします。

入力

$ARGUMENTS が空: dev..HEAD (現在のブランチの全変更) + 未コミット変更
$ARGUMENTS = staged: ステージ済み変更のみ (git diff --cached)
$ARGUMENTS = HEAD~3..HEAD: 特定のコミット範囲
$ARGUMENTS = ファイルパス: そのファイルの変更のみ

現在の状態

ブランチ: !git rev-parse --abbrev-ref HEAD
dev との差分ファイル数: !git diff --name-only dev..HEAD 2>/dev/null | wc -l | tr -d ' '
未コミット変更: !git status --short 2>/dev/null | wc -l | tr -d ' '

フェーズ 1: 変更サマリ収集

git diff --name-only で変更ファイルをカテゴリ分類:
- 実装 (src/python_run/piper_plus/*.py, src/python/g2p/**, src/rust/piper-core/**, src/cpp/*.cpp, src/csharp/**, src/go/**, src/wasm/openjtalk-web/src/*.js)
- テスト (*/tests/**, */test/**)
- ビルド (*.toml, *.json, CMakeLists.txt, *.yml)
- ドキュメント (*.md, docs/**)
各カテゴリのファイル数と代表ファイルを記録

フェーズ 2: 並列ドキュメント監査 (エージェントチーム)

以下の 7 エージェントを 1 メッセージで並列起動 します:

Agent 1: CLAUDE.md 監査

subagent_type: Explore task: CLAUDE.md の「実装済み機能」「重要なファイルパス」「OpenAI 互換 API」セクションを確認し、実装変更に対する追加・修正が必要か判定。新規モジュール/クラス/HTTP エンドポイント/テストファイルが未記載なら、具体的な diff を提案。

Agent 2: ルート README 監査

subagent_type: Explore task: README.md, README_EN.md, README.*.md (他言語) の Features / Interfaces / Feature Support Matrix を確認。新機能が各ランタイムで利用可能になった場合、対応 runtime 行を更新。

Agent 3: ランタイム別 README 監査

subagent_type: Explore task: src/python_run/README.md, src/python_run/README_http.md, src/wasm/openjtalk-web/README.npm.md, src/rust/piper-cli/README.md, src/go/README.md を確認。API 例・CLI フラグ・HTTP エンドポイントが最新か判定。

Agent 4: CHANGELOG 監査

subagent_type: Explore task: CHANGELOG.md と src/wasm/openjtalk-web/CHANGELOG.md の [Unreleased] セクションが、コード変更 (新機能/バグ修正/破壊的変更) を反映しているか確認。未反映なら具体的な markdown を提案。

Agent 5: docs/features・docs/spec 監査

subagent_type: Explore task: docs/features/*.md と docs/spec/*.toml / *.md を確認。新機能の専用ドキュメントが必要か、既存の仕様ファイル (ort-session-contract.toml, short-text-contract.toml, phoneme-timing-contract.toml など) の更新が必要か判定。

Read the full file on GitHub · 168 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

14d ago Changed 9aed5d3efdd3
2mo ago First seen · 168 lines · 61 tokens per session scan A 13b01c62ffa8

Subscribe to this mod's changes

sync-docs is a skill published in the GitHub repository ayutaz/piper-plus (239 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 2,622 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Multilingual PyTorch Writing and docs deep-learning japanese onnx speech-synthesis

physicsnemo-shard-tensor

Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…

NVIDIA/physicsnemo · 152 tokens

physicsnemo-discover

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…

NVIDIA/physicsnemo · 124 tokens

deep-learning

Use when training or debugging a neural net in PyTorch — the forward/loss/backward/step loop and its silent bugs, mixed precision (AMP), AdamW/LR schedules, DDP/FSDP/ZeRO, checkpoints and seeds. NOT LoRA/QLoRA on a pretrained LLM (that is finetuning), NOT tabular sklearn/XGBoost (that is machine-learning), NOT…

ericrisco/rsc-harness · 102 tokens

single-cell-multi-omics-analysis-scvi

Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics…

PharMolix/OpenBioMed · 94 tokens

graphsignal-profiler

Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about graphsignal-run or graphsignal.watch(), or asks about CUPTI / Prometheus / OTLP setup.

graphsignal/graphsignal-profiler · 74 tokens

atc-model-converter

Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation. Workflow 1 auto-discovers input shapes and parameters from user source code. Workflow 2 exports PyTorch models to ONNX. Workflow 3 converts ONNX to .om via ATC with multi-CANN version support. Workflow 4 adapts the user's full…

Ascend/agent-skills · 142 tokens

piper-plus: Skill for Claude Code