Configure G1 Sim2real
EGalahad/sim2real
Install, repair, and verify sim2real on G1 robot computers. An agent skill from EGalahad/sim2real.
学習済み Lightning checkpoint (.ckpt) を ONNX export → sanity check → RTF benchmark → HuggingFace upload まで連鎖実行する read-mostly skill。
Install Publish Model
$ npx skills add ayutaz/piper-plus --skill publish-model -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ayutaz/piper-plus publish-model --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ayutaz/piper-plus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/publish-model .claude/skills/publish-model && rm -rf skills-srcUse ~/.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/
Install the "publish-model" agent skill from https://github.com/ayutaz/piper-plus/tree/dev/.claude/skills/publish-model into .claude/skills/publish-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish-model", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ayutaz/piper-plus/tree/dev/.claude/skills/publish-modelType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ayutaz/piper-plus --skill publish-model -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ayutaz/piper-plus publish-model --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ayutaz/piper-plus.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/publish-model .agents/skills/publish-model && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "publish-model" agent skill from https://github.com/ayutaz/piper-plus/tree/dev/.claude/skills/publish-model into .agents/skills/publish-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish-model", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ayutaz/piper-plus --skill publish-model -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ayutaz/piper-plus publish-model --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ayutaz/piper-plus.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/publish-model .cursor/skills/publish-model && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "publish-model" agent skill from https://github.com/ayutaz/piper-plus/tree/dev/.claude/skills/publish-model into .cursor/skills/publish-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish-model", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ayutaz/piper-plus.git --path .claude/skills/publish-model--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ayutaz/piper-plus --skill publish-model -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ayutaz/piper-plus publish-model --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ayutaz/piper-plus.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/publish-model .gemini/skills/publish-model && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "publish-model" agent skill from https://github.com/ayutaz/piper-plus/tree/dev/.claude/skills/publish-model into .gemini/skills/publish-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish-model", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ayutaz/piper-plus publish-modelInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ayutaz/piper-plus --skill publish-model -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ayutaz/piper-plus.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/publish-model .github/skills/publish-model && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "publish-model" agent skill from https://github.com/ayutaz/piper-plus/tree/dev/.claude/skills/publish-model into .github/skills/publish-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish-model", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ayutaz/piper-plus --skill publish-model -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ayutaz/piper-plus publish-model --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ayutaz/piper-plus.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/publish-model .opencode/skills/publish-model && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "publish-model" agent skill from https://github.com/ayutaz/piper-plus/tree/dev/.claude/skills/publish-model into .opencode/skills/publish-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "publish-model", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
publish-model- GitHub stars
- 230
- Token cost
- ~1.1k tokens
- SKILL.md length
- 245 words
- Files
- 1
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- MIT
At a glance
学習済み Lightning checkpoint (.ckpt) を ONNX export → sanity check → RTF benchmark → HuggingFace upload まで連鎖実行する read-mostly skill。
- Tasks that involve Model hubs and datasets
- SKILL.md covers 引数, 現在の状態, フェーズ 1: 事前検査 and フェーズ 2: ONNX export, plus 7 more sections
- Calls uv, cargo and git
What it does
Publish Model is an agent skill from ayutaz/piper-plus. 学習済み Lightning checkpoint (.ckpt) を ONNX export → sanity check → RTF benchmark → HuggingFace upload まで連鎖実行する read-mostly skill。 export 仕様 (FP16 / EMA / emblang unify / opset 15) を docs/spec/onnx-export-contract.toml から取得し、 全 7 ランタイムでの load 可否を gate する。
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 AI & LLM Engineering, covering Model hubs and datasets. It works with ONNX and Hugging Face. The repository describes itself as: Multilingual neural TTS (6 languages: JA/EN/ZH/ES/FR/PT, code supports SV) — C++, C, Rust, Go, Python, npm (WASM). VITS + Prosody, streaming, CUDA/CoreML/DirectML. pip install…. The licence is MIT.
When your agent uses it
- Tasks that involve Model hubs and datasets
Example prompts
- “/publish-model”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Bash(uv run *), Bash(ls *), Bash(stat *), Bash(sha256sum *), Bash(file *), Bash(git diff *), Bash(git status *), Read, Edit, Grep
What it can do on your machine
Read from SKILL.md and the folder at commit 421d066. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash(uv run *)Bash(ls *)Bash(stat *)Bash(sha256sum *)Bash(file *)Bash(git diff *)Bash(git status *)ReadEditGrep
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
uvcargogit
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv and git, 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
Publish Model loads about 1.1k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 245 words of instructions outside code blocks.
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 ayutaz/piper-plus at commit 421d066, republished under its MIT licence (© ayutaz). 245 words, ~1,112 tokens.
Download SKILL.mdSave it as
.claude/skills/publish-model/SKILL.md (or your agent's skills folder).- name
- publish-model
- description
- 学習済み Lightning checkpoint (.ckpt) を ONNX export → sanity check → RTF benchmark → HuggingFace upload まで連鎖実行する read-mostly skill。 export 仕様 (FP16 / EMA / emb_lang unify / opset 15) を `docs/spec/onnx-export-contract.toml` から取得し、 全 7 ランタイムでの load 可否を gate する。
- allowed-tools
- Bash(uv run *), Bash(ls *), Bash(stat *), Bash(sha256sum *), Bash(file *), Bash(git diff *), Bash(git status *), Read, Edit, Grep
- argument-hint
- <ckpt-path> [--output <onnx-path>] [--repo <hf-repo>] [--skip-benchmark]
- disable-model-invocation
- true
Model Publish Pipeline Skill
Lightning checkpoint から HuggingFace 公開までを 1 つの skill に集約。 現状 4 ステップ手動運用 (export → infer test → RTF bench → HF push) で、 工程間の引き継ぎミスが頻発する。
memory feedback_merge_caution.md に従い、 publish (HuggingFace への push) は確認後に明示実行。 デフォルトは export + sanity + bench までで停止。
引数
$1(必須): checkpoint パス、 例/data/piper/output-tsukuyomi-finetune-6lang-v2/last.ckpt--output PATH: 出力 ONNX パス (デフォルト: checkpoint 隣に.onnx)--repo OWNER/REPO: HuggingFace repo 名 (デフォルト:ayousanz/<voice-key>)--skip-benchmark: フェーズ 4 を skip--apply: フェーズ 5 (HuggingFace upload) も実行
現在の状態
- ブランチ: !
git rev-parse --abbrev-ref HEAD - 引数: $ARGUMENTS
フェーズ 1: 事前検査
# Checkpoint 存在 / サイズ確認
ls -la "$1"
file "$1" # PyTorch Lightning checkpoint であることを確認
# Contract gate (drift 検出して bump 前 fail)
uv run python scripts/check_onnx_export_contract.py 2>&1 | tail -3
uv run python scripts/check_phoneme_set_version.py 2>&1 | tail -3フェーズ 2: ONNX export
CLAUDE.md の推奨設定 (FP16 + EMA + stochastic + emb_lang 自動統一) を使う:
CUDA_VISIBLE_DEVICES="" uv run python -m piper_train.export_onnx \
"$CKPT_PATH" "$OUTPUT_ONNX"出力後の verification:
# ONNX checker / shape inference
uv run python -c "import onnx; m=onnx.load('$OUTPUT_ONNX'); onnx.checker.check_model(m); onnx.shape_inference.infer_shapes(m)"
# Size 確認 (FP16 で ~50% 削減されているか)
ls -la "$OUTPUT_ONNX"フェーズ 3: Inference sanity check
# JSONL 1 行入力で推論テスト
echo '{"phoneme_ids": [1, 2, 3, 4, 5], "speaker_id": 0}' | \
CUDA_VISIBLE_DEVICES="" uv run python -m piper_train.infer_onnx \
--model "$OUTPUT_ONNX" --output-dir /tmp/sanity
# 出力 wav の sanity 確認
ls -la /tmp/sanity/*.wav無音 / クリップ / 形状不一致を catch。
フェーズ 4: RTF benchmark (optional)
uv run python tools/benchmark/run_benchmark.py \
--model "$OUTPUT_ONNX" --warmup 5 --runs 30 \
--output /tmp/rtf_$(basename "$OUTPUT_ONNX" .onnx).jsonbaseline (README.md の Benchmark 表、 Xeon E5-2650 v4 / 25 phoneme 英文 / 27ms) と比較し、 ±30% 以内なら OK、 大きい drift があれば warning。
フェーズ 5: HuggingFace upload (apply モードでのみ)
# config.json も同送 (model_resolution_vectors.json で alias を canonical 化)
uv run python scripts/upload_model_to_hf.py \
--onnx "$OUTPUT_ONNX" \
--config "$OUTPUT_ONNX.json" \
--repo "$HF_REPO" \
--license cc-by-nc-sa-4.0upload 後、 docs/spec/model-sha256-manifest.toml に新 entry を追加するための diff 提案 (sha256sum 値含む)。
フェーズ 6: 7-runtime load 確認 (optional / 軽量検証)
各 runtime で「model を load できるか」 だけ確認 (full inference は時間がかかる):
# Python
uv run python -c "from piper import PiperVoice; v = PiperVoice.load('$OUTPUT_ONNX', '$OUTPUT_ONNX.json'); print('Python: OK')"
# Rust
(cd src/rust && cargo run --release --bin piper-plus -- --model $OUTPUT_ONNX --text 'test' --output-file /tmp/r.wav 2>&1 | tail -3)
# Go / C# / C++ / WASM はオプション注意
- memory feedback_training_cost: 学習時間は見送り理由にならない。 benchmark で出る drift は publish 中止の理由にもならない (regression 報告)。
- memory feedback_data_asset_distribution: 新 voice 追加時は 7 manifest 同期が必要。 publish 後
check-new-runtime-assetskill を呼ぶ。 - memory feedback_merge_caution: HuggingFace push は
--apply指定時のみ。 default は dry-run。 --skip-benchmarkは CI 環境で RTF 測定が無意味な場合のみ使う (ローカル開発機推奨)。
使用例
# 通常のリリース前 publish
/publish-model /data/piper/output-tsukuyomi-finetune-6lang-v2/last.ckpt
# Benchmark をスキップして export + sanity だけ
/publish-model /data/piper/last.ckpt --skip-benchmark
# 確認後 HuggingFace へ実 publish
/publish-model /data/piper/last.ckpt --repo ayousanz/piper-plus-newvoice --apply期待効果
- 学習完了 → 公開までの 4-step 手動運用を 1 skill 化
- ONNX export 仕様 drift (opset / FP16 / EMA / emb_lang) の commit-before-export catch
- RTF benchmark の regression early detection
- model SHA256 manifest 更新の markdown diff 自動生成
- 7-runtime load 可否の publish 前 sanity
© ayutaz, 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/publish-model of ayutaz/piper-plus.
Open the folder on GitHubat commit 421d066
Compare with similar skills
Publish Model 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Publish Model this skillayutaz/piper-plus | 230 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Configure G1 Sim2realEGalahad/sim2real | 145 | — | ~1.5k | Automated safety check: Pass | None | |
| Xybrid Initxybrid-ai/xybrid | 467 | — | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Community Model ConversionRisorseArtificiali/anti-vocale | 117 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Quark Torch Exportamd/Quark | 181 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Quark Torch Ptqamd/Quark | 181 | — | ~2.3k | Automated safety check: Pass | MIT |
Similar skills
Xybrid Init
xybrid-ai/xybrid
Generate model metadata for an ML model so it works with xybrid.
Community Model Conversion
RisorseArtificiali/anti-vocale
Convert a HuggingFace ASR fine-tune into a sherpa-onnx external model, publish it, and add it to the Anti-Vocale community catalog.
Quark Torch Export
amd/Quark
Prepare export and downstream evaluation handoff for a planned or completed Quark PTQ run.
Quark Torch Ptq
amd/Quark
Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan, create reproducible artifacts, request…
- Official
Tao Port Huggingface Model
NVIDIA/skills
Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline).
More from ayutaz/piper-plus
All 20 skills in this repoSkill Health
ayutaz/piper-plus
.claude/skills//SKILL.md の frontmatter / referenced script 実在 / trigger 衝突 / .claude/hooks/.sh の executable+shebang を検査する meta-skill。
Bump Deps
ayutaz/piper-plus
ORT / openjtalk / ruff のような cross-runtime に canonical sync が必要な依存関係を 1 コマンドで bump する read-mostly skill。
Check Cross Runtime
ayutaz/piper-plus
Python canonical (src/pythonrun/piperplus/, src/python/pipertrain/, src/python/g2p/piperplusg2p/) を変更した PR で、 ONNX I/O 以外の追随漏れ (phonemizer / config schema / CLI flag / data 形式 / API 変更) を 7 ランタイム +…
Check Loanword
ayutaz/piper-plus
ZH-EN code-switching loanword の同期と forward-compat を 1 コマンドで検査。zhenloanword.json を編集したり 5 ランタイムのいずれかに新規エントリを追加する前後に呼ぶ。Python source を canonical とし、Rust×2 / Go / C / WASM / C++ の 6 mirror + Python…
Check New Runtime Asset
ayutaz/piper-plus
新規データアセット (JSON/TOML) を追加した PR で「7 箇所の package metadata 更新が全て揃っているか」を 1 コマンドで確認。MANIFEST.in / pyproject package-data / Cargo features / npm files / C Content / Android assets / SPM resources の更新漏れを…
Check PR Ready
ayutaz/piper-plus
PR 作成前の最終チェックリスト (lint/test/docs/CHANGELOG/未コミット確認)。/precheck の拡張版で、ドキュメント整合性も検証します。
Related
Works with
Categories
Questions about Publish Model
What does Publish Model do?
学習済み Lightning checkpoint (.ckpt) を ONNX export → sanity check → RTF benchmark → HuggingFace upload まで連鎖実行する read-mostly skill。. Publish Model is an agent skill from ayutaz/piper-plus.
When should I use Publish Model?
Publish Model fits situations like: tasks that involve Model hubs and datasets.
How do I install Publish Model in Claude Code?
Run `npx skills add ayutaz/piper-plus --skill publish-model -a claude-code`. Or copy the skill folder (.claude/skills/publish-model in ayutaz/piper-plus) into .claude/skills/publish-model in your project. Claude Code loads it when a task matches its description.
How do I install Publish Model in Codex?
Run `npx skills add ayutaz/piper-plus --skill publish-model -a codex`. Or copy the skill folder (.claude/skills/publish-model in ayutaz/piper-plus) into .agents/skills/publish-model in your project. Codex loads it when a task matches its description.
Can I use Publish Model 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 ayutaz/piper-plus --skill publish-model -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/publish-model, .gemini/skills/publish-model, .github/skills/publish-model and .opencode/skills/publish-model in your project.
What does Publish Model need to run?
Going by SKILL.md and its folder, Publish Model needs the command-line tools its instructions call (uv, cargo and git). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash(uv run *), Bash(ls *), Bash(stat *), Bash(sha256sum *), Bash(file *), Bash(git diff *), Bash(git status *), Read, Edit, Grep.
Does Publish Model access the network?
SKILL.md contains no URLs. Its commands use uv and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Publish Model 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 Publish Model use?
Publish Model 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 Publish Model use?
About 1.1k tokens (SKILL.md is roughly 4.4k 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 Publish Model?
Skills that share tags, products or a category with Publish Model: Configure G1 Sim2real (EGalahad/sim2real, 145 stars), Xybrid Init (xybrid-ai/xybrid, 467 stars), Community Model Conversion (RisorseArtificiali/anti-vocale, 117 stars) and Quark Torch Export (amd/Quark, 181 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Publish Model?
ayutaz (a GitHub user) maintains it in ayutaz/piper-plus, which has 230 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 8, 2026.
Source: ayutaz/piper-plus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.