Borrowing it
Nothing to install: this file belongs to QuickerHub/quicker-rpc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/QuickerHub/quicker-rpc/main/.cursor/skills/quicker-voice-runtime-publish/SKILL.mdgit clone --depth 1 https://github.com/QuickerHub/quicker-rpcWrote 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.
[](https://agentmods.dev/skills/quickerhub/quicker-rpc/quicker-voice-runtime-publish)<a href="https://agentmods.dev/skills/quickerhub/quicker-rpc/quicker-voice-runtime-publish"><img src="https://agentmods.dev/badge/skills/quickerhub/quicker-rpc/quicker-voice-runtime-publish/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.
<a href="https://agentmods.dev/skills/quickerhub/quicker-rpc/quicker-voice-runtime-publish"><img src="https://agentmods.dev/badge/skills/quickerhub/quicker-rpc/quicker-voice-runtime-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00088 | $0.02287 |
| Opus 5 | $0.00044 | $0.01144 |
| Sonnet 5 | $0.00018 | $0.00457 |
| Haiku 4.5 | $0.00009 | $0.00229 |
Grade A, and why
quicker-voice-runtime-publish 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
quicker-voice-runtime 发布
独立于 quicker-rpc：语音 Runtime 版本在
voice-asr-runtime/pyproject.toml，不要改根目录version.json。QuickerAgent 通过内嵌voice-plugin-channel.json指向 GitHub/Bitiful 上的 zip。
改什么（发布清单）
| 何时 | 必须改 / 检查 | 路径 |
|---|---|---|
| 每次 runtime 发布 | 版本号递增 | voice-asr-runtime/pyproject.toml → version |
| 每次 runtime 发布 | 同步安装渠道（两处都要一致） | agent-gui/src-tauri/resources/voice-plugin-channel.json |
agent-gui/src-tauri/voice-plugin-metadata/voice-plugin-channel.json |
||
| 模型文件变更 | 更新指纹 + 重新打 model tag | agent-gui/src-tauri/resources/voice-sensevoice-model-identity.json |
agent-gui/src-tauri/voice-plugin-metadata/voice-sensevoice-model-identity.json |
||
| CI / 镜像 | Release workflow（少见） | voice-asr-runtime/.github/workflows/release.yml |
| Bitiful 密钥 | voice-asr-runtime 仓库 Secrets | BITIFUL_ACCESS_KEY, BITIFUL_SECRET_KEY, BITIFUL_BUCKET_NAME |
不要改：version.json（QuickerRpc）、qkrpc 插件版本、除非语音协议/安装逻辑本身变更则无需为纯 runtime 发布跑 build.ps1 -t。
不要提交：voice-asr-runtime/publish/*.zip、voice-plugin-channel.generated.json（gitignore）。
版本与仓库
| 项目 | 值 |
|---|---|
| 源码（monorepo） | voice-asr-runtime/ |
| 远端仓库 | QuickerHub/voice-asr-runtime |
| Runtime tag | v0.1.2（与 pyproject.toml 一致，带 v 前缀） |
| Model tag | model-sensevoice（固定，无版本号；仅模型变更时 force-push） |
| Runtime zip | voice-asr-runtime-<ver>-win-x64.zip |
| Model zip | voice-asr-model-sensevoice.zip |
已安装用户：Tauri 从远程 gallery 拉取 channel（GitHub latest + Bitiful mirror），比对 runtime-version.txt 与 runtimeVersion，后台 staging 升级。纯 runtime 发布无需 QuickerAgent 发版；内嵌 fallback channel 仅离线兜底。
Agent 流程（runtime vX.Y.Z）
- 改代码（如有）→
voice-asr-runtime内跑测试：cd voice-asr-runtime uv sync uv run pytest - Bump 版本：
pyproject.tomlversion必须 大于 上一 GitHub Release（通常 patch +1）。 - Commit voice-asr-runtime 变更；若 monorepo 子目录需单独 push 到
QuickerHub/voice-asr-runtime，先同步远端再 tag。 - 打 tag 触发 CI（在 voice-asr-runtime 仓库）：
Workflow：git tag v0.1.3 git push origin v0.1.3.github/workflows/release.yml→ PyInstaller zip +voice-plugin-channel.generated.json→ GitHub Release；有 Bitiful secret 则上传镜像 +version.txt。 - 等待 CI 绿：
GitHub Release 成功但 job 黄/红：常见为 Bitiful 未配置（已改为 skip）；以 Release 资产为准。gh run list --repo QuickerHub/voice-asr-runtime --workflow release.yml --limit 3 gh run watch <run-id> --repo QuickerHub/voice-asr-runtime - 上传远程 channel mirror（推荐，在 quicker-rpc 根目录）：
GitHub Release 已附带pwsh -NoProfile -File ./publish/Sync-VoicePluginChannel.ps1 -Version 0.1.3 -FromGitHubRelease -UploadRemote -SkipLocalSyncvoice-plugin-channel.generated.json时，已安装 QuickerAgent 会通过releases/latest自动发现新版本。 - （可选，低频） 更新内嵌 offline fallback：
仅当需要刷新pwsh -NoProfile -File ./publish/Sync-VoicePluginChannel.ps1 -Version 0.1.3 -FromGitHubReleasevoice-plugin-channel.json离线兜底时 commit monorepo；不是每次 runtime 发布的必做项。 - （可选）本地补传 runtime zip Bitiful（CI 未配 secret 时）：
凭证：pwsh -NoProfile -File ./publish/Upload-VoiceAsrToBitiful.ps1 -Version 0.1.3publish/.env（见publish/.env.example）。 - 汇报：GitHub Release URL、channel
runtimeVersion、Bitiful channel mirror 是否已上传。
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.
- 10d ago First seen · 155 lines · 88 tokens per session scan A 3e6de0c6310e
quicker-voice-runtime-publish is a skill published in the GitHub repository QuickerHub/quicker-rpc (13 stars, last pushed 27d ago), licensed MIT. It adds 88 tokens to every session and 2,287 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
vs-crawler
Crawl websites (news, blogs, papers, GitHub, product docs, RSS feeds) into a fixed-schema JSONL file, then create a dataset and a searchable application in Viking AI Search. Supports one-time crawl and scheduled recurring crawl with automatic incremental sync.
atmos-pro
Atmos Pro setup and workflows: settings.pro, GitHub OIDC, affected and inventory uploads, stack locks, pro commit, workflow dispatch, merge queues, and drift detection.
atmos-git
Atmos Git and GitOps: git.repositories, clone/pull/status/diff/commit/push/clean, local Git hook shims, signed commits, managed workdirs, fork-PR trust gate, and auth via identities or github/sts.
safe-extraction
Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.
vs-search-tuning
Use when a user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.