[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GCBYDBW96FC8PDE449SR40":3,"skill-same:01M6GCBYDBW96FC8PDE449SR40":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6GCBYDBW96FC8PDE449SR40","hermes-tts-plugin-providers",null,"Build, verify, and troubleshoot Hermes TTS providers implemented through the plugin harness rather than legacy command-provider blocks.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fa7\u002Fa7b2330519926e6c621ba96b0f492d22c08fed408c9acf223e4e454b4143983a\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"hermes","hermes tts plugin providers","tts","Providers","plugin","plugins","harness","verify","voice","troubleshoot","hermes agent","command","dispatch","Legacy","provider","build","hermes-agent","blocks","windows","2026-11-10 10:12:30",false,"---\r\nname: hermes-tts-plugin-providers\r\ndescription: Build, verify, and troubleshoot Hermes TTS providers implemented through the plugin harness rather than legacy command-provider blocks.\r\nversion: 1.0.0\r\nauthor: Hermes Agent\r\nlicense: MIT\r\nmetadata:\r\n  hermes:\r\n    tags: [hermes, tts, plugins, voice, windows, provider-dispatch]\r\n    related_skills: [hermes-agent]\r\n---\r\n\r\n# Hermes TTS Plugin Providers\r\n\r\nReference: for stabilizing the user-approved cute Hakua voice in Irodori-TTS, see `references\u002Ffixed-hakua-voice.md`.\r\n\r\nUse this skill when adding or debugging a Hermes Text-to-Speech provider that should be registered by the plugin harness and used by `tools.tts_tool.text_to_speech_tool`, gateway voice replies, or `hermes \u003Cplugin-command>` CLI commands.\r\n\r\nThis is for provider classes such as local TTS servers, GPU-backed voice engines, or offline synthesizers. Do **not** create a one-session skill for each engine; put engine-specific quirks in `references\u002F` and keep the workflow here generic.\r\n\r\n## Trigger Conditions\r\n\r\nLoad this skill when the task mentions any of:\r\n\r\n- Hermes TTS provider registration\r\n- `tts.provider`, `tts.providers`, or `tools.tts_tool`\r\n- plugin `register_tts_provider`, plugin CLI, plugin tools, or `plugins\u002F\u003Cname>\u002Fplugin.yaml`\r\n- local voice engines such as Irodori-TTS, VOICEVOX, Kokoro, sherpa-onnx, Piper, etc. being wired into Hermes\r\n- gateway voice output not using the expected provider\r\n\r\n## Core Principle\r\n\r\nPrefer a **plugin provider** when the integration is part of Hermes, needs tools\u002FCLI\u002Fstatus, or should be reusable across gateway and standard TTS paths. Use a legacy `tts.providers.\u003Cname>.type: command` block only for simple external command wrappers.\r\n\r\nImportant dispatch pitfall:\r\n\r\n- If `tts.providers.\u003Cprovider>.type: command` exists, Hermes may resolve that command provider before the plugin provider with the same name.\r\n- For a plugin-backed provider, remove the same-name command-provider block and set only the top-level provider selection, e.g.:\r\n\r\n```yaml\r\ntts:\r\n  provider: irodori\r\n  output_format: wav\r\n  voice: none\r\n  model: irodori-tts\r\n```\r\n\r\n## Expected Plugin Shape\r\n\r\nA complete Hermes TTS plugin usually has:\r\n\r\n```text\r\nplugins\u002F\u003Cprovider>_tts\u002F\r\n├── plugin.yaml\r\n├── __init__.py\r\n├── core.py\r\n└── cli.py\r\n```\r\n\r\nRecommended registrations:\r\n\r\n- TTS provider: `\u003Cprovider>`\r\n- status tool: `\u003Cprovider>_tts_status`\r\n- synthesize tool: `\u003Cprovider>_tts_synthesize`\r\n- CLI group: `hermes \u003Cprovider>-tts ...`\r\n  - `status`\r\n  - `start` if there is a local server process\r\n  - `synthesize`\r\n\r\nFor Windows\u002Flocal-server engines, prefer Hermes-side script harness wrappers under `scripts\u002Fwindows\u002F` so CLI\u002Ftools\u002Fprovider all share the same invocation behavior.\r\n\r\n## Implementation Checklist\r\n\r\n1. **Read current TTS dispatch code**\r\n   - Inspect `tools\u002Ftts_tool.py` and the plugin registration surfaces before editing.\r\n   - Confirm whether plugin providers and command providers share the same namespace.\r\n\r\n2. **Add plugin files**\r\n   - `plugin.yaml`: metadata, enabled defaults, commands\u002Ftools\u002Fproviders declared in the repo's current plugin format.\r\n   - `__init__.py`: plugin entry point and registration hooks.\r\n   - `core.py`: provider implementation, status checks, synthesis call, output normalization.\r\n   - `cli.py`: human-friendly smoke commands.\r\n\r\n3. **Add script harness wrappers when needed**\r\n   - For Windows PowerShell wrappers, quote paths with spaces.\r\n   - Set environment defaults inside the script for cache paths, GPU\u002Fruntime flags, and known upstream quirks.\r\n   - Keep server start and synthesis invocation separate when possible.\r\n\r\n4. **Update config carefully**\r\n   - Set `tts.provider` to the plugin provider name.\r\n   - Set format\u002Fmodel\u002Fvoice defaults as needed.\r\n   - Add the plugin to `plugins.enabled`.\r\n   - Remove same-name legacy command-provider blocks unless the intent is to bypass the plugin.\r\n\r\n5. **Add tests at three layers**\r\n   - Plugin unit\u002Fstatus\u002Fsynthesis behavior.\r\n   - TTS dispatch selecting the plugin provider.\r\n   - CLI\u002Fplugin registration visibility.\r\n\r\n6. **Verify in the real checkout**\r\n   - Plugin list shows the plugin enabled.\r\n   - Plugin status returns `ok: true` or a precise reason it is unavailable.\r\n   - Plugin CLI synthesis writes an audio file.\r\n   - Standard `text_to_speech_tool(...)` returns `provider: \u003Cprovider>`.\r\n   - If voice delivery matters, verify the final file format is compatible with gateway\u002Fplatform expectations.\r\n\r\n## Verification Commands\r\n\r\nOn this Windows checkout the terminal tool uses bash\u002FMSYS, so POSIX syntax is usually safest inside Hermes tools. For user-facing PowerShell snippets, quote paths that include spaces.\r\n\r\n```bash\r\ncd \"\u002Fc\u002FUsers\u002Fdownl\u002FDocuments\u002FNew project\u002Fhermes-agent\"\r\nuv run python -m hermes_cli.main plugins list --plain | grep -i '\u003Cprovider>'\r\nuv run python -m hermes_cli.main \u003Cprovider>-tts status\r\nPYTHONUTF8=1 uv run --with pytest python -m pytest -o addopts='' \\\r\n  tests\u002Fplugins\u002Ftest_\u003Cprovider>_tts_plugin.py \\\r\n  tests\u002Ftools\u002Ftest_tts_plugin_dispatch.py \\\r\n  tests\u002Fhermes_cli\u002Ftest_plugins_tts_registration.py \\\r\n  -q\r\nPYTHONUTF8=1 uv run python - \u003C\u003C'PY'\r\nfrom pathlib import Path\r\nfrom tools.tts_tool import text_to_speech_tool\r\nout = Path.home() \u002F 'AppData' \u002F 'Local' \u002F 'hermes' \u002F 'audio_cache' \u002F '\u003Cprovider>_plugin_smoke.wav'\r\nprint(text_to_speech_tool('Hermes TTS plugin smoke test.', output_path=str(out)))\r\nPY\r\n```\r\n\r\n## Reference Voice Identity\r\n\r\nFor voice-cloning providers, do not leave the configured voice as `none` when the user expects a stable persona voice. `voice: none` is useful for bring-up, but it can produce a voice that sounds unlike the established assistant\u002Fpersona and may vary between generations.\r\n\r\nWhen a user approves a voice style:\r\n\r\n1. Save the approved sample under the provider's reference-voice directory with a stable persona ID (for example `voices\u002Fhakua.ogg`).\r\n2. Verify the server lists that ID via its voice-list\u002Fstatus endpoint.\r\n3. Set Hermes' default voice through the CLI\u002Fconfig path, not by hand-editing protected config when a CLI is available, e.g. `hermes config set tts.voice hakua`.\r\n4. Regenerate any already-produced audio\u002Fvideo assets using the fixed voice ID.\r\n5. Report both the correction and the new asset path so the user can compare.\r\n\r\nSee `references\u002Firodori-reference-voice-persona.md` for the session-proven Irodori\u002FHakua pattern.\r\n\r\n## Windows Pitfalls\r\n\r\n- Paths under `%USERPROFILE%\\Documents\\New project\\...` contain spaces; quote them in PowerShell and shell snippets.\r\n- Prefer `uv run python ...` from the Hermes checkout so plugin discovery uses the intended source tree.\r\n- Set `PYTHONUTF8=1` \u002F `$env:PYTHONUTF8='1'` for Japanese synthesis smoke tests.\r\n- Avoid filling the C drive with model downloads; local TTS scripts may need explicit cache directories.\r\n- If an upstream model downloader respects `HF_HUB_ENABLE_HF_TRANSFER`, disable it in scripts when `hf_transfer` is not installed, instead of letting first-run downloads fail.\r\n\r\n## Reference Notes\r\n\r\n- `references\u002Firodori-tts-plugin.md` — session-proven Irodori-TTS provider details, config, verification output, and pitfalls.\r\n- `references\u002Firodori-reference-voice-persona.md` — how to pin an approved Irodori reference voice as a stable persona voice and regenerate media.\r\n- `references\u002Firodori-runtime-recovery.md` — recovery pattern for already-configured Irodori\u002FHakua runtime failures such as JSON error files, CUDA\u002FOOM responses, duplicate server processes, or connection resets during voice-asset generation.\r\n\r\n## Reporting Pattern\r\n\r\nWhen reporting completion, include real verification evidence:\r\n\r\n- plugin list line\r\n- status summary with provider availability\u002Fdevice if relevant\r\n- pytest result\r\n- standard `text_to_speech_tool` result showing `provider: \u003Cprovider>`\r\n- any unrelated dirty\u002Funtracked files that were intentionally not touched\r\n","# Hermes TTS Plugin Providers\r\n\r\nReference: for stabilizing the user-approved cute Hakua voice in Irodori-TTS, see `references\u002Ffixed-hakua-voice.md`.\r\n\r\nUse this skill when adding or debugging a Hermes Text-to-Speech provider that should be registered by the plugin harness and used by `tools.tts_tool.text_to_speech_tool`, gateway voice replies, or `hermes \u003Cplugin-command>` CLI commands.\r\n\r\nThis is for provider classes such as local TTS servers, GPU-backed voice engines, or offline synthesizers. Do **not** create a one-session skill for each engine; put engine-specific quirks in `references\u002F` and keep the workflow here generic.\r\n\r\n## Trigger Conditions\r\n\r\nLoad this skill when the task mentions any of:\r\n\r\n- Hermes TTS provider registration\r\n- `tts.provider`, `tts.providers`, or `tools.tts_tool`\r\n- plugin `register_tts_provider`, plugin CLI, plugin tools, or `plugins\u002F\u003Cname>\u002Fplugin.yaml`\r\n- local voice engines such as Irodori-TTS, VOICEVOX, Kokoro, sherpa-onnx, Piper, etc. being wired into Hermes\r\n- gateway voice output not using the expected provider\r\n\r\n## Core Principle\r\n\r\nPrefer a **plugin provider** when the integration is part of Hermes, needs tools\u002FCLI\u002Fstatus, or should be reusable across gateway and standard TTS paths. Use a legacy `tts.providers.\u003Cname>.type: command` block only for simple external command wrappers.\r\n\r\nImportant dispatch pitfall:\r\n\r\n- If `tts.providers.\u003Cprovider>.type: command` exists, Hermes may resolve that command provider before the plugin provider with the same name.\r\n- For a plugin-backed provider, remove the same-name command-provider block and set only the top-level provider selection, e.g.:\r\n\r\n```yaml\r\ntts:\r\n  provider: irodori\r\n  output_format: wav\r\n  voice: none\r\n  model: irodori-tts\r\n```\r\n\r\n## Expected Plugin Shape\r\n\r\nA complete Hermes TTS plugin usually has:\r\n\r\n```text\r\nplugins\u002F\u003Cprovider>_tts\u002F\r\n├── plugin.yaml\r\n├── __init__.py\r\n├── core.py\r\n└── cli.py\r\n```\r\n\r\nRecommended registrations:\r\n\r\n- TTS provider: `\u003Cprovider>`\r\n- status tool: `\u003Cprovider>_tts_status`\r\n- synthesize tool: `\u003Cprovider>_tts_synthesize`\r\n- CLI group: `hermes \u003Cprovider>-tts ...`\r\n  - `status`\r\n  - `start` if there is a local server process\r\n  - `synthesize`\r\n\r\nFor Windows\u002Flocal-server engines, prefer Hermes-side script harness wrappers under `scripts\u002Fwindows\u002F` so CLI\u002Ftools\u002Fprovider all share the same invocation behavior.\r\n\r\n## Implementation Checklist\r\n\r\n1. **Read current TTS dispatch code**\r\n   - Inspect `tools\u002Ftts_tool.py` and the plugin registration surfaces before editing.\r\n   - Confirm whether plugin providers and command providers share the same namespace.\r\n\r\n2. **Add plugin files**\r\n   - `plugin.yaml`: metadata, enabled defaults, commands\u002Ftools\u002Fproviders declared in the repo's current plugin format.\r\n   - `__init__.py`: plugin entry point and registration hooks.\r\n   - `core.py`: provider implementation, status checks, synthesis call, output normalization.\r\n   - `cli.py`: human-friendly smoke commands.\r\n\r\n3. **Add script harness wrappers when needed**\r\n   - For Windows PowerShell wrappers, quote paths with spaces.\r\n   - Set environment defaults inside the script for cache paths, GPU\u002Fruntime flags, and known upstream quirks.\r\n   - Keep server start and synthesis invocation separate when possible.\r\n\r\n4. **Update config carefully**\r\n   - Set `tts.provider` to the plugin provider name.\r\n   - Set format\u002Fmodel\u002Fvoice defaults as needed.\r\n   - Add the plugin to `plugins.enabled`.\r\n   - Remove same-name legacy command-provider blocks unless the intent is to bypass the plugin.\r\n\r\n5. **Add tests at three layers**\r\n   - Plugin unit\u002Fstatus\u002Fsynthesis behavior.\r\n   - TTS dispatch selecting the plugin provider.\r\n   - CLI\u002Fplugin registration visibility.\r\n\r\n6. **Verify in the real checkout**\r\n   - Plugin list shows the plugin enabled.\r\n   - Plugin status returns `ok: true` or a precise reason it is unavailable.\r\n   - Plugin CLI synthesis writes an audio file.\r\n   - Standard `text_to_speech_tool(...)` returns `provider: \u003Cprovider>`.\r\n   - If voice delivery matters, verify the final file format is compatible with gateway\u002Fplatform expectations.\r\n\r\n## Verification Commands\r\n\r\nOn this Windows checkout the terminal tool uses bash\u002FMSYS, so POSIX syntax is usually safest inside Hermes tools. For user-facing PowerShell snippets, quote paths that include spaces.\r\n\r\n```bash\r\ncd \"\u002Fc\u002FUsers\u002Fdownl\u002FDocuments\u002FNew project\u002Fhermes-agent\"\r\nuv run python -m hermes_cli.main plugins list --plain | grep -i '\u003Cprovider>'\r\nuv run python -m hermes_cli.main \u003Cprovider>-tts status\r\nPYTHONUTF8=1 uv run --with pytest python -m pytest -o addopts='' \\\r\n  tests\u002Fplugins\u002Ftest_\u003Cprovider>_tts_plugin.py \\\r\n  tests\u002Ftools\u002Ftest_tts_plugin_dispatch.py \\\r\n  tests\u002Fhermes_cli\u002Ftest_plugins_tts_registration.py \\\r\n  -q\r\nPYTHONUTF8=1 uv run python - \u003C\u003C'PY'\r\nfrom pathlib import Path\r\nfrom tools.tts_tool import text_to_speech_tool\r\nout = Path.home() \u002F 'AppData' \u002F 'Local' \u002F 'hermes' \u002F 'audio_cache' \u002F '\u003Cprovider>_plugin_smoke.wav'\r\nprint(text_to_speech_tool('Hermes TTS plugin smoke test.', output_path=str(out)))\r\nPY\r\n```\r\n\r\n## Reference Voice Identity\r\n\r\nFor voice-cloning providers, do not leave the configured voice as `none` when the user expects a stable persona voice. `voice: none` is useful for bring-up, but it can produce a voice that sounds unlike the established assistant\u002Fpersona and may vary between generations.\r\n\r\nWhen a user approves a voice style:\r\n\r\n1. Save the approved sample under the provider's reference-voice directory with a stable persona ID (for example `voices\u002Fhakua.ogg`).\r\n2. Verify the server lists that ID via its voice-list\u002Fstatus endpoint.\r\n3. Set Hermes' default voice through the CLI\u002Fconfig path, not by hand-editing protected config when a CLI is available, e.g. `hermes config set tts.voice hakua`.\r\n4. Regenerate any already-produced audio\u002Fvideo assets using the fixed voice ID.\r\n5. Report both the correction and the new asset path so the user can compare.\r\n\r\nSee `references\u002Firodori-reference-voice-persona.md` for the session-proven Irodori\u002FHakua pattern.\r\n\r\n## Windows Pitfalls\r\n\r\n- Paths under `%USERPROFILE%\\Documents\\New project\\...` contain spaces; quote them in PowerShell and shell snippets.\r\n- Prefer `uv run python ...` from the Hermes checkout so plugin discovery uses the intended source tree.\r\n- Set `PYTHONUTF8=1` \u002F `$env:PYTHONUTF8='1'` for Japanese synthesis smoke tests.\r\n- Avoid filling the C drive with model downloads; local TTS scripts may need explicit cache directories.\r\n- If an upstream model downloader respects `HF_HUB_ENABLE_HF_TRANSFER`, disable it in scripts when `hf_transfer` is not installed, instead of letting first-run downloads fail.\r\n\r\n## Reference Notes\r\n\r\n- `references\u002Firodori-tts-plugin.md` — session-proven Irodori-TTS provider details, config, verification output, and pitfalls.\r\n- `references\u002Firodori-reference-voice-persona.md` — how to pin an approved Irodori reference voice as a stable persona voice and regenerate media.\r\n- `references\u002Firodori-runtime-recovery.md` — recovery pattern for already-configured Irodori\u002FHakua runtime failures such as JSON error files, CUDA\u002FOOM responses, duplicate server processes, or connection resets during voice-asset generation.\r\n\r\n## Reporting Pattern\r\n\r\nWhen reporting completion, include real verification evidence:\r\n\r\n- plugin list line\r\n- status summary with provider availability\u002Fdevice if relevant\r\n- pytest result\r\n- standard `text_to_speech_tool` result showing `provider: \u003Cprovider>`\r\n- any unrelated dirty\u002Funtracked files that were intentionally not touched\r\n",{"name":5,"author":43,"license":15,"version":44,"metadata":45,"description":7},"Hermes Agent","1.0.0",{"hermes":46},{"tags":47,"related_skills":49},[19,21,24,27,37,48],"provider-dispatch",[35],"main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002Fa7\u002Fa7b2330519926e6c621ba96b0f492d22c08fed408c9acf223e4e454b4143983a",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add zapabob\u002FSkills --skill hermes-tts-plugin-providers",{"tool":64,"command":65},"bunx","bunx skills add zapabob\u002FSkills --skill hermes-tts-plugin-providers",{"tool":67,"command":68},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill hermes-tts-plugin-providers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fa7\u002Fa7b2330519926e6c621ba96b0f492d22c08fed408c9acf223e4e454b4143983a\u002FSKILL.md",true,[],[73,108,143,170,197,214],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":92,"publishedAt":38},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[79,84,87],{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":85,"categoryName":86,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[75,93,94,95,96,97,37,98,99,100,101,102,103,19,29,104,50,105,106,107],"openclaw","macos","cli","github","linux","official","search","https","social-media","api","Media","twitter","social","via","post",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":125,"publishedAt":38},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[114,117,120,121,122],{"categoryNo":115,"categoryName":116,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":118,"categoryName":119,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":85,"categoryName":86,"taxonomyType":82,"taxonomyTypeDesc":83},{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},{"categoryNo":123,"categoryName":124,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000036","内容创作者",[126,127,128,129,94,130,97,131,37,132,133,134,135,136,137,138,139,140,141,142],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":152,"publishedAt":38},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[149],{"categoryNo":150,"categoryName":151,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000016","图像与多媒体",[145,94,97,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":179,"publishedAt":38},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[176],{"categoryNo":177,"categoryName":178,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000013","分析与可视化",[180,94,181,182,37,183,184,185,186,187,188,160,189,190,191,192,193,194,195,196],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":204,"publishedAt":38},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[203],{"categoryNo":85,"categoryName":86,"taxonomyType":82,"taxonomyTypeDesc":83},[199,94,205,96,97,206,207,208,209,210,211,19,29,212,213],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":222,"publishedAt":38},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[220,221],{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},[223,224,225,97,226,153,227,228,229,156,230,102,231,232,233,234,235,236,237,238],"llms","vLLM","serving llms vllm","research","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]