[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69B5YC45P39BX11JGAC2NGC":3,"skill-same:01M69B5YC45P39BX11JGAC2NGC":76},{"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":26,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M69B5YC45P39BX11JGAC2NGC","generating-podcast-script",null,"Use this skill whenever the user asks to write, generate, or create a podcast script or podcast episode — from a topic, or from source material such as a news digest, newsletter, email review, or set of articles — and optionally convert it to audio with Azure Text-to-Speech. Handles the initial request and every follow-up refinement (source, topic, length, cast, narration) in the same task.","microsoft\u002Fcopilot-studio-gallery","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69B5GK6Q5V7Q6S3Q3DAKAAB",16,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcopilot-studio-gallery\u002Fblob\u002Fmain\u002Fsubmissions\u002Fpodcast-generation-agent\u002Fsolution\u002Fbotcomponents\u002Fcr88d_podcastdemo_OMpe9u.file.skillmd_A9jgI\u002Ffiledata\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"generating podcast script","podcast script","script","podcast","narration","review","request","source","follow-up","azure","as","digest","create","generate","newsletter","up","write","text","Audio","SET","speech","2026-11-10 10:12:30",false,"---\nname: generating-podcast-script\ndescription: Use this skill whenever the user asks to write, generate, or create a podcast script or podcast episode — from a topic, or from source material such as a news digest, newsletter, email review, or set of articles — and optionally convert it to audio with Azure Text-to-Speech. Handles the initial request and every follow-up refinement (source, topic, length, cast, narration) in the same task.\n---\n\n# Podcast Script Generation\n\nProduces a two-host, NotebookLM-style conversational episode: a readable script\nplus a multi-voice SSML document ready for Azure Text-to-Speech.\n\n## Step 1 — Gather inputs\n\nAsk only for what is missing. Do not ask for optional fields that have safe\ndefaults.\n\n| Input | Required | Default |\n|---|---|---|\n| `source` or `topic` | Yes | — (source material such as a digest\u002Fnewsletter\u002Farticles, **or** a plain topic) |\n| `duration` | No | `medium` — `short` ≈ 3 min \u002F ~450 words, `medium` ≈ 6 min \u002F ~900 words, `long` ≈ 12 min \u002F ~1,800 words |\n| `language` | No | English |\n| `cast` | No | Two hosts, NOVA and MILES (see Step 4) |\n| `generate_audio` | No | Ask after the script is ready |\n\nAll word targets assume ~150 spoken words per minute. Stay within 10 percent of\ntarget.\n\nDerive a lowercase-hyphenated `\u003Cslug>` from the source or topic (max 6 words,\nASCII only).\n\n## Step 2 — Parse the source material\n\nSkip this step when the user gave a bare topic with no source material.\n\nExtract every distinct article or item. For each, capture:\n\n- headline\n- publication \u002F source\n- date, if present\n- the core factual claim\n- any figures or quotes\n- the \"so what\"\n\nMerge duplicates covering the same event. Discard boilerplate, footers,\ndisclaimers, legal notices, unsubscribe text, and image captions.\n\n## Step 3 — Editorial selection\n\nRank items by newsworthiness and reader impact. Keep the top 4 to 6 for full\ntreatment (fewer for `short`, more for `long`). Group the remainder into one\nfast **rapid fire** segment. If the material has a dominant theme, lead with it\nand thread it through the episode.\n\n## Step 4 — Cast\n\nTwo hosts, always the same personalities, always distinct voices:\n\n- **NOVA** — voice `en-US-AvaMultilingualNeural`. Lead host. Warm, curious,\n  quick. Drives the agenda, asks the question the listener is thinking, reacts\n  out loud, reframes jargon into plain language. Slightly faster cadence.\n- **MILES** — voice `en-US-AndrewMultilingualNeural`. Analyst. Calm, dry,\n  precise. Supplies context, numbers, caveats, second-order implications.\n  Slightly slower, lower pitch. Occasionally pushes back on Nova.\n\nNeither host is a narrator. They talk **to each other**, not to the microphone.\n\n## Step 5 — Episode structure\n\n1. **Cold open** (15–20s) — Nova opens on the single most striking fact or\n   tension. No \"welcome to the podcast\", no channel branding, no music cues.\n2. **Agenda tease** (10s) — Miles lays out what they'll cover, casually.\n3. **Story segments** (60–90s each) — one item per segment. Pattern:\n   hook → the facts → why it matters → a short exchange of interpretation →\n   handoff line into the next story. Vary who leads each segment.\n4. **Rapid fire** (45s) — alternating one-liners on the leftover items, quick\n   tempo.\n5. **Close** (20–30s) — three concrete takeaways split between the two hosts,\n   then a short human sign-off. Alternate whether Nova or Miles ends.\n\n## Step 6 — Dialogue style\n\nThis is what makes it sound conversational rather than read-aloud.\n\n- Write spoken English, not written English. Contractions everywhere.\n- Keep most lines under 30 words. Break long explanations across two or three\n  turns with the other host interjecting.\n- Use real conversational connective tissue — \"okay so\", \"right\", \"wait, back\n  up\", \"here's the part I didn't expect\", \"yeah, and that's the thing\", \"hmm\".\n  Roughly one marker every 4 to 5 turns. Never let it become a tic.\n- One host regularly asks the naive clarifying question so the other can\n  explain.\n- Use one concrete analogy or comparison per complex item.\n- Genuine reactions are allowed (\"that number is wild\"). Invented opinions on\n  people, companies, or politics are not.\n- Never read a headline verbatim. Paraphrase it into speech.\n- Attribute clearly: \"according to the Financial Times\", \"Reuters is\n  reporting\".\n- If the source is ambiguous or a claim is unconfirmed, say so on air: \"the\n  report is careful to call that unconfirmed\".\n- No stage directions, no \"[laughs]\", no speaker labels, no markdown, no\n  emojis, no bullet points, and no URLs in the **spoken text**.\n\n## Step 7 — TTS hygiene\n\nApplies to every word that will be spoken.\n\n- Spell out anything a synthesizer would mangle: \"twenty twenty-six\" not\n  `2026`, \"three point two billion dollars\" not `$3.2B`, \"about fifteen\n  percent\" not `~15%`.\n- First mention of an acronym: expand it, then use the short form.\n- Letter-by-letter acronyms: `\u003Csay-as interpret-as=\"characters\">API\u003C\u002Fsay-as>`.\n- Odd proper nouns: `\u003Csub alias=\"phonetic spelling\">Name\u003C\u002Fsub>`.\n- A non-English name or phrase inside an English line:\n  `\u003Clang xml:lang=\"fr-FR\">...\u003C\u002Flang>`.\n- Escape XML entities in all spoken text: `&` → `&`, `\u003C` → `<`,\n  `>` → `>`.\n- Never emit smart quotes, em dashes, asterisks, or underscores.\n\n## Step 8 — Write the readable script\n\nWrite the human-readable transcript to:\n\n```text\n\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast_Script.txt\n```\n\nThis file — and only this file — may carry `NOVA:` \u002F `MILES:` speaker labels so\na person can follow along. It contains no stage directions and no markdown. The\nspoken text itself must already satisfy Steps 6 and 7 so it can be lifted into\nSSML unchanged.\n\n## Step 9 — SSML output contract\n\nProduce the SSML document and **nothing else** — no preamble, no explanation, no\ncode fences, no trailing notes inside the artifact. Write it verbatim to:\n\n```text\n\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast.ssml\n```\n\nRules:\n\n- Exactly one root `\u003Cspeak>` element with `version=\"1.0\"`,\n  `xmlns=\"http:\u002F\u002Fwww.w3.org\u002F2001\u002F10\u002Fsynthesis\"`,\n  `xmlns:mstts=\"http:\u002F\u002Fwww.w3.org\u002F2001\u002Fmstts\"`, `xml:lang=\"en-US\"`.\n- One `\u003Cvoice>` element per conversational turn. Alternate speakers. Never put\n  both hosts inside one `\u003Cvoice>` element.\n- Vary delivery with `\u003Cprosody>` so it never sounds flat. Baselines: Nova\n  `rate=\"+6%\" pitch=\"+2%\"`, Miles `rate=\"-2%\" pitch=\"-4%\"`. Nudge per line to\n  match the emotion of the sentence.\n- Use `\u003Cmstts:express-as style=\"...\">` where the voice supports it. Preferred\n  styles: `chat` for banter, `friendly` for explanation,\n  `narration-professional` for the factual core of a story, `excited` sparingly\n  for the cold open. An unsupported style is ignored by the service, so keep\n  styles optional — never structural.\n- Pauses: `\u003Cbreak time=\"250ms\"\u002F>` between turns within a segment,\n  `\u003Cbreak time=\"700ms\"\u002F>` between segments, `\u003Cbreak time=\"400ms\"\u002F>` before a\n  punchline or a pivot. Never exceed `900ms`.\n- **Every `\u003Cbreak>` must sit inside a `\u003Cvoice>` element.** A `\u003Cbreak>` placed\n  between `\u003Cvoice>` elements — as a direct child of `\u003Cspeak>` — is invalid in a\n  multi-voice document and will fail synthesis. Two `\u003Cvoice>` elements may sit\n  directly next to each other with nothing between them. To pause *between*\n  turns, put the break at the **end of the preceding turn's** text, inside that\n  turn's `\u003Cprosody>`.\n- `\u003Cemphasis level=\"moderate\">` on at most one or two key terms per segment.\n- Keep the total document under 40,000 characters.\n\n### Shape\n\n```xml\n\u003Cspeak version=\"1.0\"\n       xmlns=\"http:\u002F\u002Fwww.w3.org\u002F2001\u002F10\u002Fsynthesis\"\n       xmlns:mstts=\"http:\u002F\u002Fwww.w3.org\u002F2001\u002Fmstts\"\n       xml:lang=\"en-US\">\n  \u003Cvoice name=\"en-US-AvaMultilingualNeural\">\n    \u003Cmstts:express-as style=\"excited\">\n      \u003Cprosody rate=\"+8%\" pitch=\"+3%\">Okay, so the number that stopped me cold\n      this morning was forty percent. \u003Cbreak time=\"300ms\"\u002F> Forty percent, in one\n      quarter. \u003Cbreak time=\"250ms\"\u002F>\u003C\u002Fprosody>\n    \u003C\u002Fmstts:express-as>\n  \u003C\u002Fvoice>\n  \u003Cvoice name=\"en-US-AndrewMultilingualNeural\">\n    \u003Cmstts:express-as style=\"chat\">\n      \u003Cprosody rate=\"-2%\" pitch=\"-4%\">Right, and the part everyone's skipping is\n      that it's off a very small base. \u003Cbreak time=\"250ms\"\u002F> Context matters\n      here. \u003Cbreak time=\"700ms\"\u002F>\u003C\u002Fprosody>\n    \u003C\u002Fmstts:express-as>\n  \u003C\u002Fvoice>\n\u003C\u002Fspeak>\n```\n\nNote the trailing `\u003Cbreak>` closing each turn: the 250ms is the gap before the\nnext turn, the 700ms is the longer gap before the next segment. Nothing sits\nbetween the two `\u003Cvoice>` elements.\n\n## Step 10 — Review, then generate audio\n\nShow the user a table summarising each segment (title, one-line description,\napproximate spoken duration), print both file paths, and ask:\n\n> Would you like me to convert this to an audio file?\n\nOnly if they say yes:\n\n1. Confirm the `ConverttexttospeechwithSSML` tool is available on the agent. If\n   it is not, tell the user how to add it and stop.\n2. Call `ConverttexttospeechwithSSML` with the SSML document from Step 9 and\n   `outputFormat: riff-24khz-16bit-mono-pcm`.\n3. Decode the base64 response and save to `\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast.wav`.\n\nIf the document is too large for a single call, split it at a segment boundary,\nsynthesize each part, and concatenate the decoded audio in order.\n\n```python\nimport base64\n\nwith open('\u003Ctool_output_file>', 'r') as f:\n    content = f.read().strip()\n\naudio_bytes = base64.b64decode(content)\n\nwith open('\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast.wav', 'wb') as f:\n    f.write(audio_bytes)\n```\n\n## Step 11 — Final report\n\nAlways end with:\n\n| Item | Details |\n|---|---|\n| Script file | `\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast_Script.txt` |\n| SSML file | `\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast.ssml` |\n| Word count \u002F estimated duration | actual vs. target at ~150 wpm |\n| Items covered | full segments + rapid-fire count |\n| Voices | `en-US-AvaMultilingualNeural` (Nova), `en-US-AndrewMultilingualNeural` (Miles) |\n| Audio file | `\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast.wav` *(only if audio generated)* |\n","# Podcast Script Generation\n\nProduces a two-host, NotebookLM-style conversational episode: a readable script\nplus a multi-voice SSML document ready for Azure Text-to-Speech.\n\n## Step 1 — Gather inputs\n\nAsk only for what is missing. Do not ask for optional fields that have safe\ndefaults.\n\n| Input | Required | Default |\n|---|---|---|\n| `source` or `topic` | Yes | — (source material such as a digest\u002Fnewsletter\u002Farticles, **or** a plain topic) |\n| `duration` | No | `medium` — `short` ≈ 3 min \u002F ~450 words, `medium` ≈ 6 min \u002F ~900 words, `long` ≈ 12 min \u002F ~1,800 words |\n| `language` | No | English |\n| `cast` | No | Two hosts, NOVA and MILES (see Step 4) |\n| `generate_audio` | No | Ask after the script is ready |\n\nAll word targets assume ~150 spoken words per minute. Stay within 10 percent of\ntarget.\n\nDerive a lowercase-hyphenated `\u003Cslug>` from the source or topic (max 6 words,\nASCII only).\n\n## Step 2 — Parse the source material\n\nSkip this step when the user gave a bare topic with no source material.\n\nExtract every distinct article or item. For each, capture:\n\n- headline\n- publication \u002F source\n- date, if present\n- the core factual claim\n- any figures or quotes\n- the \"so what\"\n\nMerge duplicates covering the same event. Discard boilerplate, footers,\ndisclaimers, legal notices, unsubscribe text, and image captions.\n\n## Step 3 — Editorial selection\n\nRank items by newsworthiness and reader impact. Keep the top 4 to 6 for full\ntreatment (fewer for `short`, more for `long`). Group the remainder into one\nfast **rapid fire** segment. If the material has a dominant theme, lead with it\nand thread it through the episode.\n\n## Step 4 — Cast\n\nTwo hosts, always the same personalities, always distinct voices:\n\n- **NOVA** — voice `en-US-AvaMultilingualNeural`. Lead host. Warm, curious,\n  quick. Drives the agenda, asks the question the listener is thinking, reacts\n  out loud, reframes jargon into plain language. Slightly faster cadence.\n- **MILES** — voice `en-US-AndrewMultilingualNeural`. Analyst. Calm, dry,\n  precise. Supplies context, numbers, caveats, second-order implications.\n  Slightly slower, lower pitch. Occasionally pushes back on Nova.\n\nNeither host is a narrator. They talk **to each other**, not to the microphone.\n\n## Step 5 — Episode structure\n\n1. **Cold open** (15–20s) — Nova opens on the single most striking fact or\n   tension. No \"welcome to the podcast\", no channel branding, no music cues.\n2. **Agenda tease** (10s) — Miles lays out what they'll cover, casually.\n3. **Story segments** (60–90s each) — one item per segment. Pattern:\n   hook → the facts → why it matters → a short exchange of interpretation →\n   handoff line into the next story. Vary who leads each segment.\n4. **Rapid fire** (45s) — alternating one-liners on the leftover items, quick\n   tempo.\n5. **Close** (20–30s) — three concrete takeaways split between the two hosts,\n   then a short human sign-off. Alternate whether Nova or Miles ends.\n\n## Step 6 — Dialogue style\n\nThis is what makes it sound conversational rather than read-aloud.\n\n- Write spoken English, not written English. Contractions everywhere.\n- Keep most lines under 30 words. Break long explanations across two or three\n  turns with the other host interjecting.\n- Use real conversational connective tissue — \"okay so\", \"right\", \"wait, back\n  up\", \"here's the part I didn't expect\", \"yeah, and that's the thing\", \"hmm\".\n  Roughly one marker every 4 to 5 turns. Never let it become a tic.\n- One host regularly asks the naive clarifying question so the other can\n  explain.\n- Use one concrete analogy or comparison per complex item.\n- Genuine reactions are allowed (\"that number is wild\"). Invented opinions on\n  people, companies, or politics are not.\n- Never read a headline verbatim. Paraphrase it into speech.\n- Attribute clearly: \"according to the Financial Times\", \"Reuters is\n  reporting\".\n- If the source is ambiguous or a claim is unconfirmed, say so on air: \"the\n  report is careful to call that unconfirmed\".\n- No stage directions, no \"[laughs]\", no speaker labels, no markdown, no\n  emojis, no bullet points, and no URLs in the **spoken text**.\n\n## Step 7 — TTS hygiene\n\nApplies to every word that will be spoken.\n\n- Spell out anything a synthesizer would mangle: \"twenty twenty-six\" not\n  `2026`, \"three point two billion dollars\" not `$3.2B`, \"about fifteen\n  percent\" not `~15%`.\n- First mention of an acronym: expand it, then use the short form.\n- Letter-by-letter acronyms: `\u003Csay-as interpret-as=\"characters\">API\u003C\u002Fsay-as>`.\n- Odd proper nouns: `\u003Csub alias=\"phonetic spelling\">Name\u003C\u002Fsub>`.\n- A non-English name or phrase inside an English line:\n  `\u003Clang xml:lang=\"fr-FR\">...\u003C\u002Flang>`.\n- Escape XML entities in all spoken text: `&` → `&`, `\u003C` → `<`,\n  `>` → `>`.\n- Never emit smart quotes, em dashes, asterisks, or underscores.\n\n## Step 8 — Write the readable script\n\nWrite the human-readable transcript to:\n\n```text\n\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast_Script.txt\n```\n\nThis file — and only this file — may carry `NOVA:` \u002F `MILES:` speaker labels so\na person can follow along. It contains no stage directions and no markdown. The\nspoken text itself must already satisfy Steps 6 and 7 so it can be lifted into\nSSML unchanged.\n\n## Step 9 — SSML output contract\n\nProduce the SSML document and **nothing else** — no preamble, no explanation, no\ncode fences, no trailing notes inside the artifact. Write it verbatim to:\n\n```text\n\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast.ssml\n```\n\nRules:\n\n- Exactly one root `\u003Cspeak>` element with `version=\"1.0\"`,\n  `xmlns=\"http:\u002F\u002Fwww.w3.org\u002F2001\u002F10\u002Fsynthesis\"`,\n  `xmlns:mstts=\"http:\u002F\u002Fwww.w3.org\u002F2001\u002Fmstts\"`, `xml:lang=\"en-US\"`.\n- One `\u003Cvoice>` element per conversational turn. Alternate speakers. Never put\n  both hosts inside one `\u003Cvoice>` element.\n- Vary delivery with `\u003Cprosody>` so it never sounds flat. Baselines: Nova\n  `rate=\"+6%\" pitch=\"+2%\"`, Miles `rate=\"-2%\" pitch=\"-4%\"`. Nudge per line to\n  match the emotion of the sentence.\n- Use `\u003Cmstts:express-as style=\"...\">` where the voice supports it. Preferred\n  styles: `chat` for banter, `friendly` for explanation,\n  `narration-professional` for the factual core of a story, `excited` sparingly\n  for the cold open. An unsupported style is ignored by the service, so keep\n  styles optional — never structural.\n- Pauses: `\u003Cbreak time=\"250ms\"\u002F>` between turns within a segment,\n  `\u003Cbreak time=\"700ms\"\u002F>` between segments, `\u003Cbreak time=\"400ms\"\u002F>` before a\n  punchline or a pivot. Never exceed `900ms`.\n- **Every `\u003Cbreak>` must sit inside a `\u003Cvoice>` element.** A `\u003Cbreak>` placed\n  between `\u003Cvoice>` elements — as a direct child of `\u003Cspeak>` — is invalid in a\n  multi-voice document and will fail synthesis. Two `\u003Cvoice>` elements may sit\n  directly next to each other with nothing between them. To pause *between*\n  turns, put the break at the **end of the preceding turn's** text, inside that\n  turn's `\u003Cprosody>`.\n- `\u003Cemphasis level=\"moderate\">` on at most one or two key terms per segment.\n- Keep the total document under 40,000 characters.\n\n### Shape\n\n```xml\n\u003Cspeak version=\"1.0\"\n       xmlns=\"http:\u002F\u002Fwww.w3.org\u002F2001\u002F10\u002Fsynthesis\"\n       xmlns:mstts=\"http:\u002F\u002Fwww.w3.org\u002F2001\u002Fmstts\"\n       xml:lang=\"en-US\">\n  \u003Cvoice name=\"en-US-AvaMultilingualNeural\">\n    \u003Cmstts:express-as style=\"excited\">\n      \u003Cprosody rate=\"+8%\" pitch=\"+3%\">Okay, so the number that stopped me cold\n      this morning was forty percent. \u003Cbreak time=\"300ms\"\u002F> Forty percent, in one\n      quarter. \u003Cbreak time=\"250ms\"\u002F>\u003C\u002Fprosody>\n    \u003C\u002Fmstts:express-as>\n  \u003C\u002Fvoice>\n  \u003Cvoice name=\"en-US-AndrewMultilingualNeural\">\n    \u003Cmstts:express-as style=\"chat\">\n      \u003Cprosody rate=\"-2%\" pitch=\"-4%\">Right, and the part everyone's skipping is\n      that it's off a very small base. \u003Cbreak time=\"250ms\"\u002F> Context matters\n      here. \u003Cbreak time=\"700ms\"\u002F>\u003C\u002Fprosody>\n    \u003C\u002Fmstts:express-as>\n  \u003C\u002Fvoice>\n\u003C\u002Fspeak>\n```\n\nNote the trailing `\u003Cbreak>` closing each turn: the 250ms is the gap before the\nnext turn, the 700ms is the longer gap before the next segment. Nothing sits\nbetween the two `\u003Cvoice>` elements.\n\n## Step 10 — Review, then generate audio\n\nShow the user a table summarising each segment (title, one-line description,\napproximate spoken duration), print both file paths, and ask:\n\n> Would you like me to convert this to an audio file?\n\nOnly if they say yes:\n\n1. Confirm the `ConverttexttospeechwithSSML` tool is available on the agent. If\n   it is not, tell the user how to add it and stop.\n2. Call `ConverttexttospeechwithSSML` with the SSML document from Step 9 and\n   `outputFormat: riff-24khz-16bit-mono-pcm`.\n3. Decode the base64 response and save to `\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast.wav`.\n\nIf the document is too large for a single call, split it at a segment boundary,\nsynthesize each part, and concatenate the decoded audio in order.\n\n```python\nimport base64\n\nwith open('\u003Ctool_output_file>', 'r') as f:\n    content = f.read().strip()\n\naudio_bytes = base64.b64decode(content)\n\nwith open('\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast.wav', 'wb') as f:\n    f.write(audio_bytes)\n```\n\n## Step 11 — Final report\n\nAlways end with:\n\n| Item | Details |\n|---|---|\n| Script file | `\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast_Script.txt` |\n| SSML file | `\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast.ssml` |\n| Word count \u002F estimated duration | actual vs. target at ~150 wpm |\n| Items covered | full segments + rapid-fire count |\n| Voices | `en-US-AvaMultilingualNeural` (Nova), `en-US-AndrewMultilingualNeural` (Miles) |\n| Audio file | `\u002Fapp\u002Fcreated\u002F\u003Cslug>_Podcast.wav` *(only if audio generated)* |\n",{"name":5,"description":7},"main","61fc526426f0f3638ce793490e5032ee247c0cb0","submissions\u002Fpodcast-generation-agent\u002Fsolution\u002Fbotcomponents\u002Fcr88d_podcastdemo_OMpe9u.file.skillmd_A9jgI\u002Ffiledata",25,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcopilot-studio-gallery","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-15 02:44:12",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add microsoft\u002Fcopilot-studio-gallery --skill generating-podcast-script",{"tool":68,"command":69},"bunx","bunx skills add microsoft\u002Fcopilot-studio-gallery --skill generating-podcast-script",{"tool":71,"command":72},"pnpm","pnpm dlx skills add microsoft\u002Fcopilot-studio-gallery --skill generating-podcast-script","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcopilot-studio-gallery\u002Fblob\u002Fmain\u002Fsubmissions\u002Fpodcast-generation-agent\u002Fsolution\u002Fbotcomponents\u002Fcr88d_podcastdemo_OMpe9u.file.skillmd_A9jgI\u002Ffiledata\u002FSKILL.md",true,[],[77,94,111,137,162,195],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":86,"publishedAt":48},"01M69B6A39RF106PPXC8V5DD32","dock-assignment-pass-pdf","Render the completed truck loading-dock assignment as a driver-facing one-page PDF.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcopilot-studio-gallery\u002Fblob\u002Fmain\u002Fsubmissions\u002Fwandelay-loading-bay-pickup\u002Fsolution\u002Fbotcomponents\u002Fcrf98_curbsidepickupassistant_Q0mRmz.file.skillmd_gYycZ\u002Ffiledata\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",[87,88,89,37,90,91,92,93],"PDF","dock assignment pass pdf","page","driver","render","loading","one-page",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":48},"01M69B687V6ME6HZZKTPPRHBXT","loading-dock-selector","Reason over weather, one current dock snapshot, optional ETA, and verified Drive Priority Pass to select and explain one loading dock.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcopilot-studio-gallery\u002Fblob\u002Fmain\u002Fsubmissions\u002Fwandelay-loading-bay-pickup\u002Fsolution\u002Fbotcomponents\u002Fcrf98_curbsidepickupassistant_Q0mRmz.file.skillmd_FPadO\u002Ffiledata\u002FSKILL.md",[],[101,92,102,103,104,105,106,107,108,109,110],"loading dock selector","selector","weather","explain","select","snapshot","drive","eta","verified","reason",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":119,"publishedAt":48},"01M69B6435KYGSK2AV9QKDDWFP","newsletter-style-email-composer","Use when the user asks to email a report, findings, or metrics to someone as a polished, newsletter-style message. Builds an Outlook-safe HTML email from figures that already exist (headline, KPI tiles, up to two bar charts drawn with HTML table cells so they render in classic Outlook, Gmail and dark mode, short findings, data notes and the non-audit disclaimer) using the shared brand tokens, attaches the PDF report, and creates a draft for the user to review. Do NOT use for a short plain-text status update, or for building the underlying analysis, charts, or report itself -- this skill only composes the email.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcopilot-studio-gallery\u002Fblob\u002Fmain\u002Fsubmissions\u002Fsales-analyser\u002Fsolution\u002Fbotcomponents\u002Fcrf9c_salesanalyser_WEs93i.file.skillmd_oCdhy\u002Ffiledata\u002FSKILL.md",[117,118],{"categoryNo":84,"categoryName":85,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[120,121,122,41,123,124,87,125,32,126,127,128,129,130,44,131,132,42,133,91,134,135,136],"newsletter style email composer","email","email composer","style","composer","gmail","safe","status","notes","analysis","Charts","short","only","shared","plain-text","mode","when",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":149,"publishedAt":48},"01M69B6247HGXJN2SMMXSZ6RA9","polished-report-builder","Use when the user asks to turn analysis results, metrics, or findings into a polished, presentation-ready report, one-pager, or executive summary -- especially when existing analysis (e.g. from the spreadsheet analysis skill) needs to become a document someone will actually read. Builds a branded PDF with reportlab from a short content file (headline, KPI tiles, one chart per point, data notes and the non-audit disclaimer) using the shared brand tokens, and runs a QA pass before delivery to catch walls of text, chart clutter, low-resolution charts, missing data notes or poor contrast. Do NOT use for a quick inline chat answer, a single ad-hoc chart with no report structure around it, a raw data export with no narrative, or to compute the figures themselves.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcopilot-studio-gallery\u002Fblob\u002Fmain\u002Fsubmissions\u002Fsales-analyser\u002Fsolution\u002Fbotcomponents\u002Fcrf9c_salesanalyser_WEs93i.file.skillmd_k_QDN\u002Ffiledata\u002FSKILL.md",[143,144],{"categoryNo":84,"categoryName":85,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":145,"categoryName":146,"taxonomyType":147,"taxonomyTypeDesc":148},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[150,151,152,153,87,128,154,155,156,129,130,44,131,157,133,158,159,160,161,136],"polished report builder","report","builder","report builder","executive summary","qa","spreadsheet","ready","chart","quick","catch","data export",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":177,"publishedAt":48},"01M69B5ZZQAN0F4G895841974H","spreadsheet-data-analysis-reporting","Use for any request that needs figures from the sales spreadsheets (Excel\u002FCSV), even a single file or a single period - e.g. 'analyse Q4', 'how did sales do last month', 'compare regions', YoY\u002FMoM\u002FQoQ\u002FYTD growth, top products, share of revenue, trends, outliers, currency-converted totals, or building\u002Fupdating a consolidated master file. Finds and loads the relevant files, cleans and normalises them, computes metrics with standard definitions and edge-case handling, flags outliers and data issues, explains every transformation, and produces on-brand charts. Use this before the report or email skills whenever numbers must be computed. Do NOT use for questions that need no data (e.g. 'what does YoY mean') or for re-formatting results already computed in this conversation.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcopilot-studio-gallery\u002Fblob\u002Fmain\u002Fsubmissions\u002Fsales-analyser\u002Fsolution\u002Fbotcomponents\u002Fcrf9c_salesanalyser_WEs93i.file.skillmd_6IAVT\u002Ffiledata\u002FSKILL.md",[168,171,174],{"categoryNo":169,"categoryName":170,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000004","电子表格",{"categoryNo":172,"categoryName":173,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":175,"categoryName":176,"taxonomyType":147,"taxonomyTypeDesc":148},"01JBSEEDCAT000000000000033","数据分析师",[178,179,180,181,156,129,182,183,184,130,185,186,187,188,189,190,191,192,193,33,194],"data analysis","spreadsheet data analysis reporting","reporting","data","xlsx","spreadsheets","issues","how","files","conversation","flags","currency","revenue","relevant","re","top","analyse",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":204,"publishedAt":48},"01M69B5WQ38T2TR7RRP84SHRAX","internal-consistency-review","Use when the user asks for the Internal Consistency Review of a contract, or asks to check a contract for internal conflicts, inconsistencies between sections, or gaps and unfilled elements. Do NOT use for comparing the contract against external law - that is the separate Legal Compliance Review skill.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcopilot-studio-gallery\u002Fblob\u002Fmain\u002Fsubmissions\u002Fcontract-compliance-reviewer\u002Fsolution\u002Fbotcomponents\u002FDefault_Contract_Compliance_Reviewer_8c0b11.file.skillmd_maMHB\u002Ffiledata\u002FSKILL.md",[201],{"categoryNo":202,"categoryName":203,"taxonomyType":147,"taxonomyTypeDesc":148},"01JBSEEDCAT000000000000037","律师与法务",[32,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,136],"internal consistency review","consistency","legal compliance review","compliance","check","user","use","legal compliance","conflicts","legal","do","review skill","contract","elements","compliance review","for","gaps"]