[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AF46MTCYBRHGD7CDMYWX0H":3,"skill-same:01M6AF46MTCYBRHGD7CDMYWX0H":206},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":24,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6AF46MTCYBRHGD7CDMYWX0H","speech",null,"Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation. OpenAI remains the default; Atlas Cloud is an explicit optional backend for asynchronous multilingual speech. Custom voice creation is out of scope.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33332,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002FSKILL.md",[19],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"narration","when","atlas cloud","custom","for","text-to-speech","scope","creation","generation","voiceover","multilingual","accessibility","default","use","text","atlas","Audio","cloud","asynchronous","batch","openai","2026-11-10 10:12:30",false,"---\nname: \"speech\"\ndescription: \"Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation. OpenAI remains the default; Atlas Cloud is an explicit optional backend for asynchronous multilingual speech. Custom voice creation is out of scope.\"\nauthor: openai\n---\n\n\n# Speech Generation Skill\n\nGenerate spoken audio for the current project (narration, product demo voiceover, IVR prompts, accessibility reads). OpenAI remains the default with `gpt-4o-mini-tts-2025-12-15`; Atlas Cloud is available only when the user explicitly selects it. Prefer the bundled CLIs for deterministic, reproducible runs.\n\n## When to use\n- Generate a single spoken clip from text\n- Generate a batch of prompts (many lines, many files)\n\n## Decision tree (single vs batch)\n- If the user provides multiple lines\u002Fprompts or wants many outputs -> **batch**\n- Else -> **single**\n\n## Workflow\n1. Decide intent: single vs batch (see decision tree above).\n2. Collect inputs up front: exact text (verbatim), desired voice, delivery style, format, and any constraints.\n3. If batch: write a temporary JSONL under tmp\u002F (one job per line), run once, then delete the JSONL.\n4. Augment instructions into a short labeled spec without rewriting the input text.\n5. Run `scripts\u002Ftext_to_speech.py` for the default OpenAI path, or `scripts\u002Fatlas_text_to_speech.py` only when Atlas Cloud was selected (see `references\u002Fcli.md`).\n6. For important clips, validate: intelligibility, pacing, pronunciation, and adherence to constraints.\n7. Iterate with a single targeted change (voice, speed, or instructions), then re-check.\n8. Save\u002Freturn final outputs and note the final text + instructions + flags used.\n\n## Temp and output conventions\n- Use `tmp\u002Fspeech\u002F` for intermediate files (for example JSONL batches); delete when done.\n- Write final artifacts under `output\u002Fspeech\u002F` when working in this repo.\n- Use `--out` or `--out-dir` to control output paths; keep filenames stable and descriptive.\n\n## Dependencies (install if missing)\nPrefer `uv` for dependency management.\n\nOpenAI backend package:\n```\nuv pip install openai\n```\nIf `uv` is unavailable:\n```\npython3 -m pip install openai\n```\n\nThe Atlas Cloud backend uses only the Python standard library.\n\n## Environment\n- Default OpenAI calls require `OPENAI_API_KEY`.\n- Optional Atlas Cloud calls require `ATLASCLOUD_API_KEY`.\n\nIf the selected provider key is missing, give the user these steps:\n1. Create an API key in that provider's console.\n2. Set `OPENAI_API_KEY` or `ATLASCLOUD_API_KEY` as an environment variable in their system.\n3. Offer to guide them through setting the environment variable for their OS\u002Fshell if needed.\n- Keep provider credentials out of chat. Direct the user to set the selected key locally and confirm when ready.\n\nIf installation isn't possible in this environment, tell the user which dependency is missing and how to install it locally.\n\n## Defaults & rules\n- Keep OpenAI as the default provider. Do not switch to Atlas Cloud unless the user requests it.\n- Use `gpt-4o-mini-tts-2025-12-15` unless the user requests another model.\n- Default voice: `cedar`. If the user wants a brighter tone, prefer `marin`.\n- Built-in voices only. Custom voices are out of scope for this skill.\n- `instructions` are supported for GPT-4o mini TTS models, but not for `tts-1` or `tts-1-hd`.\n- Input length must be \u003C= 4096 characters per request. Split longer text into chunks.\n- Enforce 50 requests\u002Fminute. The CLI caps `--rpm` at 50.\n- Require `OPENAI_API_KEY` before any live API call.\n- For Atlas Cloud, default to `xai\u002Ftts-v1`, voice `eve`, language `auto`, and require `ATLASCLOUD_API_KEY`.\n- Atlas generation submits exactly one POST. Only prediction GET requests may retry, and polling must stay finite.\n- Download Atlas outputs without an Authorization header and reject non-HTTPS or private-network targets.\n- Provide a clear disclosure to end users that the voice is AI-generated.\n- Use the OpenAI Python SDK (`openai` package) for default OpenAI calls; the dedicated Atlas CLI uses its asynchronous HTTP contract.\n- Prefer the matching bundled CLI over writing new one-off scripts.\n\n## Instruction augmentation\nReformat user direction into a short, labeled spec. Only make implicit details explicit; do not invent new requirements.\n\nQuick clarification (augmentation vs invention):\n- If the user says \"narration for a demo\", you may add implied delivery constraints (clear, steady pacing, friendly tone).\n- Do not introduce a new persona, accent, or emotional style the user did not request.\n\nTemplate (include only relevant lines):\n```\nVoice Affect: \u003Coverall character and texture of the voice>\nTone: \u003Cattitude, formality, warmth>\nPacing: \u003Cslow, steady, brisk>\nEmotion: \u003Ckey emotions to convey>\nPronunciation: \u003Cwords to enunciate or emphasize>\nPauses: \u003Cwhere to add intentional pauses>\nEmphasis: \u003Ckey words or phrases to stress>\nDelivery: \u003Ccadence or rhythm notes>\n```\n\nAugmentation rules:\n- Keep it short; add only details the user already implied or provided elsewhere.\n- Do not rewrite the input text.\n- If any critical detail is missing and blocks success, ask a question; otherwise proceed.\n\n## Examples\n\n### Single example (narration)\n```\nInput text: \"Welcome to the demo. Today we'll show how it works.\"\nInstructions:\nVoice Affect: Warm and composed.\nTone: Friendly and confident.\nPacing: Steady and moderate.\nEmphasis: Stress \"demo\" and \"show\".\n```\n\n### Batch example (IVR prompts)\n```\n{\"input\":\"Thank you for calling. Please hold.\",\"voice\":\"cedar\",\"response_format\":\"mp3\",\"out\":\"hold.mp3\"}\n{\"input\":\"For sales, press 1. For support, press 2.\",\"voice\":\"marin\",\"instructions\":\"Tone: Clear and neutral. Pacing: Slow.\",\"response_format\":\"wav\"}\n```\n\n## Instructioning best practices (short list)\n- Structure directions as: affect -> tone -> pacing -> emotion -> pronunciation\u002Fpauses -> emphasis.\n- Keep 4 to 8 short lines; avoid conflicting guidance.\n- For names\u002Facronyms, add pronunciation hints (e.g., \"enunciate A-I\") or supply a phonetic spelling in the text.\n- For edits\u002Fiterations, repeat invariants (e.g., \"keep pacing steady\") to reduce drift.\n- Iterate with single-change follow-ups.\n\nMore principles: `references\u002Fprompting.md`. Copy\u002Fpaste specs: `references\u002Fsample-prompts.md`.\n\n## Guidance by use case\nUse these modules when the request is for a specific delivery style. They provide targeted defaults and templates.\n- Narration \u002F explainer: `references\u002Fnarration.md`\n- Product demo \u002F voiceover: `references\u002Fvoiceover.md`\n- IVR \u002F phone prompts: `references\u002Fivr.md`\n- Accessibility reads: `references\u002Faccessibility.md`\n\n## CLI + environment notes\n- CLI commands + examples: `references\u002Fcli.md`\n- API parameter quick reference: `references\u002Faudio-api.md`\n- Atlas Cloud asynchronous workflow and safeguards: `references\u002Fatlas-cloud.md`\n- Instruction patterns + examples: `references\u002Fvoice-directions.md`\n- If network approvals \u002F sandbox settings are getting in the way: `references\u002Fcodex-network.md`\n\n## Reference map\n- **`references\u002Fcli.md`**: how to run speech generation\u002Fbatches via `scripts\u002Ftext_to_speech.py` (commands, flags, recipes).\n- **`references\u002Faudio-api.md`**: API parameters, limits, voice list.\n- **`references\u002Fatlas-cloud.md`**: optional Atlas Cloud model, CLI, polling, and download contract.\n- **`references\u002Fvoice-directions.md`**: instruction patterns and examples.\n- **`references\u002Fprompting.md`**: instruction best practices (structure, constraints, iteration patterns).\n- **`references\u002Fsample-prompts.md`**: copy\u002Fpaste instruction recipes (examples only; no extra theory).\n- **`references\u002Fnarration.md`**: templates + defaults for narration and explainers.\n- **`references\u002Fvoiceover.md`**: templates + defaults for product demo voiceovers.\n- **`references\u002Fivr.md`**: templates + defaults for IVR\u002Fphone prompts.\n- **`references\u002Faccessibility.md`**: templates + defaults for accessibility reads.\n- **`references\u002Fcodex-network.md`**: environment\u002Fsandbox\u002Fnetwork-approval troubleshooting.\n","# Speech Generation Skill\n\nGenerate spoken audio for the current project (narration, product demo voiceover, IVR prompts, accessibility reads). OpenAI remains the default with `gpt-4o-mini-tts-2025-12-15`; Atlas Cloud is available only when the user explicitly selects it. Prefer the bundled CLIs for deterministic, reproducible runs.\n\n## When to use\n- Generate a single spoken clip from text\n- Generate a batch of prompts (many lines, many files)\n\n## Decision tree (single vs batch)\n- If the user provides multiple lines\u002Fprompts or wants many outputs -> **batch**\n- Else -> **single**\n\n## Workflow\n1. Decide intent: single vs batch (see decision tree above).\n2. Collect inputs up front: exact text (verbatim), desired voice, delivery style, format, and any constraints.\n3. If batch: write a temporary JSONL under tmp\u002F (one job per line), run once, then delete the JSONL.\n4. Augment instructions into a short labeled spec without rewriting the input text.\n5. Run `scripts\u002Ftext_to_speech.py` for the default OpenAI path, or `scripts\u002Fatlas_text_to_speech.py` only when Atlas Cloud was selected (see `references\u002Fcli.md`).\n6. For important clips, validate: intelligibility, pacing, pronunciation, and adherence to constraints.\n7. Iterate with a single targeted change (voice, speed, or instructions), then re-check.\n8. Save\u002Freturn final outputs and note the final text + instructions + flags used.\n\n## Temp and output conventions\n- Use `tmp\u002Fspeech\u002F` for intermediate files (for example JSONL batches); delete when done.\n- Write final artifacts under `output\u002Fspeech\u002F` when working in this repo.\n- Use `--out` or `--out-dir` to control output paths; keep filenames stable and descriptive.\n\n## Dependencies (install if missing)\nPrefer `uv` for dependency management.\n\nOpenAI backend package:\n```\nuv pip install openai\n```\nIf `uv` is unavailable:\n```\npython3 -m pip install openai\n```\n\nThe Atlas Cloud backend uses only the Python standard library.\n\n## Environment\n- Default OpenAI calls require `OPENAI_API_KEY`.\n- Optional Atlas Cloud calls require `ATLASCLOUD_API_KEY`.\n\nIf the selected provider key is missing, give the user these steps:\n1. Create an API key in that provider's console.\n2. Set `OPENAI_API_KEY` or `ATLASCLOUD_API_KEY` as an environment variable in their system.\n3. Offer to guide them through setting the environment variable for their OS\u002Fshell if needed.\n- Keep provider credentials out of chat. Direct the user to set the selected key locally and confirm when ready.\n\nIf installation isn't possible in this environment, tell the user which dependency is missing and how to install it locally.\n\n## Defaults & rules\n- Keep OpenAI as the default provider. Do not switch to Atlas Cloud unless the user requests it.\n- Use `gpt-4o-mini-tts-2025-12-15` unless the user requests another model.\n- Default voice: `cedar`. If the user wants a brighter tone, prefer `marin`.\n- Built-in voices only. Custom voices are out of scope for this skill.\n- `instructions` are supported for GPT-4o mini TTS models, but not for `tts-1` or `tts-1-hd`.\n- Input length must be \u003C= 4096 characters per request. Split longer text into chunks.\n- Enforce 50 requests\u002Fminute. The CLI caps `--rpm` at 50.\n- Require `OPENAI_API_KEY` before any live API call.\n- For Atlas Cloud, default to `xai\u002Ftts-v1`, voice `eve`, language `auto`, and require `ATLASCLOUD_API_KEY`.\n- Atlas generation submits exactly one POST. Only prediction GET requests may retry, and polling must stay finite.\n- Download Atlas outputs without an Authorization header and reject non-HTTPS or private-network targets.\n- Provide a clear disclosure to end users that the voice is AI-generated.\n- Use the OpenAI Python SDK (`openai` package) for default OpenAI calls; the dedicated Atlas CLI uses its asynchronous HTTP contract.\n- Prefer the matching bundled CLI over writing new one-off scripts.\n\n## Instruction augmentation\nReformat user direction into a short, labeled spec. Only make implicit details explicit; do not invent new requirements.\n\nQuick clarification (augmentation vs invention):\n- If the user says \"narration for a demo\", you may add implied delivery constraints (clear, steady pacing, friendly tone).\n- Do not introduce a new persona, accent, or emotional style the user did not request.\n\nTemplate (include only relevant lines):\n```\nVoice Affect: \u003Coverall character and texture of the voice>\nTone: \u003Cattitude, formality, warmth>\nPacing: \u003Cslow, steady, brisk>\nEmotion: \u003Ckey emotions to convey>\nPronunciation: \u003Cwords to enunciate or emphasize>\nPauses: \u003Cwhere to add intentional pauses>\nEmphasis: \u003Ckey words or phrases to stress>\nDelivery: \u003Ccadence or rhythm notes>\n```\n\nAugmentation rules:\n- Keep it short; add only details the user already implied or provided elsewhere.\n- Do not rewrite the input text.\n- If any critical detail is missing and blocks success, ask a question; otherwise proceed.\n\n## Examples\n\n### Single example (narration)\n```\nInput text: \"Welcome to the demo. Today we'll show how it works.\"\nInstructions:\nVoice Affect: Warm and composed.\nTone: Friendly and confident.\nPacing: Steady and moderate.\nEmphasis: Stress \"demo\" and \"show\".\n```\n\n### Batch example (IVR prompts)\n```\n{\"input\":\"Thank you for calling. Please hold.\",\"voice\":\"cedar\",\"response_format\":\"mp3\",\"out\":\"hold.mp3\"}\n{\"input\":\"For sales, press 1. For support, press 2.\",\"voice\":\"marin\",\"instructions\":\"Tone: Clear and neutral. Pacing: Slow.\",\"response_format\":\"wav\"}\n```\n\n## Instructioning best practices (short list)\n- Structure directions as: affect -> tone -> pacing -> emotion -> pronunciation\u002Fpauses -> emphasis.\n- Keep 4 to 8 short lines; avoid conflicting guidance.\n- For names\u002Facronyms, add pronunciation hints (e.g., \"enunciate A-I\") or supply a phonetic spelling in the text.\n- For edits\u002Fiterations, repeat invariants (e.g., \"keep pacing steady\") to reduce drift.\n- Iterate with single-change follow-ups.\n\nMore principles: `references\u002Fprompting.md`. Copy\u002Fpaste specs: `references\u002Fsample-prompts.md`.\n\n## Guidance by use case\nUse these modules when the request is for a specific delivery style. They provide targeted defaults and templates.\n- Narration \u002F explainer: `references\u002Fnarration.md`\n- Product demo \u002F voiceover: `references\u002Fvoiceover.md`\n- IVR \u002F phone prompts: `references\u002Fivr.md`\n- Accessibility reads: `references\u002Faccessibility.md`\n\n## CLI + environment notes\n- CLI commands + examples: `references\u002Fcli.md`\n- API parameter quick reference: `references\u002Faudio-api.md`\n- Atlas Cloud asynchronous workflow and safeguards: `references\u002Fatlas-cloud.md`\n- Instruction patterns + examples: `references\u002Fvoice-directions.md`\n- If network approvals \u002F sandbox settings are getting in the way: `references\u002Fcodex-network.md`\n\n## Reference map\n- **`references\u002Fcli.md`**: how to run speech generation\u002Fbatches via `scripts\u002Ftext_to_speech.py` (commands, flags, recipes).\n- **`references\u002Faudio-api.md`**: API parameters, limits, voice list.\n- **`references\u002Fatlas-cloud.md`**: optional Atlas Cloud model, CLI, polling, and download contract.\n- **`references\u002Fvoice-directions.md`**: instruction patterns and examples.\n- **`references\u002Fprompting.md`**: instruction best practices (structure, constraints, iteration patterns).\n- **`references\u002Fsample-prompts.md`**: copy\u002Fpaste instruction recipes (examples only; no extra theory).\n- **`references\u002Fnarration.md`**: templates + defaults for narration and explainers.\n- **`references\u002Fvoiceover.md`**: templates + defaults for product demo voiceovers.\n- **`references\u002Fivr.md`**: templates + defaults for IVR\u002Fphone prompts.\n- **`references\u002Faccessibility.md`**: templates + defaults for accessibility reads.\n- **`references\u002Fcodex-network.md`**: environment\u002Fsandbox\u002Fnetwork-approval troubleshooting.\n",{"name":5,"author":45,"description":7},"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech",3911,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-11 21:38:31",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add davila7\u002Fclaude-code-templates --skill speech",{"tool":67,"command":68},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill speech",{"tool":70,"command":71},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill speech","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002FSKILL.md",true,[75,81,87,91,95,99,103,107,111,115,120,124,128,132,136,140,144,148,152,156,160,164,168,172,176,180,186,190,194,198,202],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"agents\u002Fopenai.yaml","REFERENCE","参考文档",299,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Fagents\u002Fopenai.yaml",{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"assets\u002Fgrants\u002Fnih_specific_aims.tex","ASSET","资产文件",9082,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Fassets\u002Fgrants\u002Fnih_specific_aims.tex",{"path":88,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":89,"sourceHtmlUrl":90},"assets\u002Fgrants\u002Fnsf_proposal_template.tex",13157,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Fassets\u002Fgrants\u002Fnsf_proposal_template.tex",{"path":92,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":93,"sourceHtmlUrl":94},"assets\u002Fjournals\u002Fnature_article.tex",6242,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Fassets\u002Fjournals\u002Fnature_article.tex",{"path":96,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":97,"sourceHtmlUrl":98},"assets\u002Fjournals\u002Fneurips_article.tex",8925,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Fassets\u002Fjournals\u002Fneurips_article.tex",{"path":100,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":101,"sourceHtmlUrl":102},"assets\u002Fjournals\u002Fplos_one.tex",11713,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Fassets\u002Fjournals\u002Fplos_one.tex",{"path":104,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":105,"sourceHtmlUrl":106},"assets\u002Fposters\u002Fbeamerposter_academic.tex",8495,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Fassets\u002Fposters\u002Fbeamerposter_academic.tex",{"path":108,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":109,"sourceHtmlUrl":110},"assets\u002Fspeech-small.svg",742,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Fassets\u002Fspeech-small.svg",{"path":112,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":113,"sourceHtmlUrl":114},"assets\u002Fspeech.png",1234,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Fassets\u002Fspeech.png",{"path":116,"resourceType":117,"resourceTypeDesc":118,"sizeBytes":119,"sourceHtmlUrl":16},"LICENSE.txt","LICENSE","许可证",10776,{"path":121,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Faccessibility.md",696,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Freferences\u002Faccessibility.md",{"path":125,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Fatlas-cloud.md",2453,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Freferences\u002Fatlas-cloud.md",{"path":129,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Faudio-api.md",1057,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Freferences\u002Faudio-api.md",{"path":133,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":134,"sourceHtmlUrl":135},"references\u002Fcli.md",4070,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Freferences\u002Fcli.md",{"path":137,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":138,"sourceHtmlUrl":139},"references\u002Fcodex-network.md",1148,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Freferences\u002Fcodex-network.md",{"path":141,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":142,"sourceHtmlUrl":143},"references\u002Fconferences_formatting.md",17164,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Freferences\u002Fconferences_formatting.md",{"path":145,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":146,"sourceHtmlUrl":147},"references\u002Fgrants_requirements.md",22873,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Freferences\u002Fgrants_requirements.md",{"path":149,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":150,"sourceHtmlUrl":151},"references\u002Fivr.md",708,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Freferences\u002Fivr.md",{"path":153,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":154,"sourceHtmlUrl":155},"references\u002Fjournals_formatting.md",17649,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Freferences\u002Fjournals_formatting.md",{"path":157,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":158,"sourceHtmlUrl":159},"references\u002Fnarration.md",671,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Freferences\u002Fnarration.md",{"path":161,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":162,"sourceHtmlUrl":163},"references\u002Fposters_guidelines.md",17113,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Freferences\u002Fposters_guidelines.md",{"path":165,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":166,"sourceHtmlUrl":167},"references\u002Fprompting.md",1553,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Freferences\u002Fprompting.md",{"path":169,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":170,"sourceHtmlUrl":171},"references\u002Fsample-prompts.md",991,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Freferences\u002Fsample-prompts.md",{"path":173,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":174,"sourceHtmlUrl":175},"references\u002Fvoice-directions.md",2155,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Freferences\u002Fvoice-directions.md",{"path":177,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":178,"sourceHtmlUrl":179},"references\u002Fvoiceover.md",790,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Freferences\u002Fvoiceover.md",{"path":181,"resourceType":182,"resourceTypeDesc":183,"sizeBytes":184,"sourceHtmlUrl":185},"scripts\u002Fatlas_text_to_speech.py","SCRIPT","脚本",14154,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Fscripts\u002Fatlas_text_to_speech.py",{"path":187,"resourceType":182,"resourceTypeDesc":183,"sizeBytes":188,"sourceHtmlUrl":189},"scripts\u002Fcustomize_template.py",6875,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Fscripts\u002Fcustomize_template.py",{"path":191,"resourceType":182,"resourceTypeDesc":183,"sizeBytes":192,"sourceHtmlUrl":193},"scripts\u002Fquery_template.py",8959,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Fscripts\u002Fquery_template.py",{"path":195,"resourceType":182,"resourceTypeDesc":183,"sizeBytes":196,"sourceHtmlUrl":197},"scripts\u002Ftext_to_speech.py",15592,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Fscripts\u002Ftext_to_speech.py",{"path":199,"resourceType":182,"resourceTypeDesc":183,"sizeBytes":200,"sourceHtmlUrl":201},"scripts\u002Fvalidate_format.py",8766,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fvenue-templates\u002Fscripts\u002Fvalidate_format.py",{"path":203,"resourceType":182,"resourceTypeDesc":183,"sizeBytes":204,"sourceHtmlUrl":205},"tests\u002Ftest_atlas_text_to_speech.py",6807,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fmedia\u002Fspeech\u002Ftests\u002Ftest_atlas_text_to_speech.py",[207,233,260,293,327,351],{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":211,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":215,"publishedAt":46},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[214],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},[216,217,218,219,220,29,221,222,38,26,223,224,225,226,227,228,229,230,231,232],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":234,"name":235,"nameZh":6,"description":236,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":211,"licenseFileUrl":6,"sourceHtmlUrl":237,"categories":238,"keywords":240,"publishedAt":46},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[239],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},[241,242,243,244,245,246,247,248,249,250,251,26,252,253,254,255,256,257,258,259],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":261,"name":262,"nameZh":6,"description":263,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":211,"licenseFileUrl":6,"sourceHtmlUrl":264,"categories":265,"keywords":275,"publishedAt":46},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[266,269,270],{"categoryNo":267,"categoryName":268,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},{"categoryNo":271,"categoryName":272,"taxonomyType":273,"taxonomyTypeDesc":274},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[276,277,278,279,280,281,282,29,283,284,285,286,287,288,289,38,290,291,26,292],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":294,"name":295,"nameZh":6,"description":296,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":297,"sourceHtmlUrl":298,"categories":299,"keywords":303,"publishedAt":46},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[300],{"categoryNo":301,"categoryName":302,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000009","前端开发",[304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,29,326],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":328,"name":329,"nameZh":6,"description":330,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":331,"sourceHtmlUrl":332,"categories":333,"keywords":338,"publishedAt":46},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[334,337],{"categoryNo":335,"categoryName":336,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":301,"categoryName":302,"taxonomyType":22,"taxonomyTypeDesc":23},[339,340,341,342,343,305,344,314,315,345,346,347,348,29,349,224,350],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":352,"name":353,"nameZh":6,"description":354,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":355,"sourceHtmlUrl":356,"categories":357,"keywords":365,"publishedAt":46},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[358,361,362],{"categoryNo":359,"categoryName":360,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},{"categoryNo":363,"categoryName":364,"taxonomyType":273,"taxonomyTypeDesc":274},"01JBSEEDCAT000000000000036","内容创作者",[366,367,368,369,370,371,372,373,307,374,317,252,375,376,377,378,379,288,380,26,381,382,383,384,385,230,386],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]