[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79GP9M82V134E82MWFGVJ27":3,"skill-same:01M79GP9M82V134E82MWFGVJ27":75},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":14,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M79GP9M82V134E82MWFGVJ27","short-videos",null,"Produce 90-second universal short-video scripts (HeyGen \u002F Instagram Reels \u002F LinkedIn Video \u002F YouTube Shorts) and standalone LinkedIn posts using native Hermes tools. No Claude Code dependency.","gyc567\u002Fgreat-skill-center","gyc567","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F265098?v=4","01M79FNR01T00G18Z13PVXWWVK","eric","01M79FNR0PB4VEDVF0VK18FX9M",0,"MIT","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity-pack\u002Fshort-videos\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: short-videos\ndescription: \"Produce 90-second universal short-video scripts (HeyGen \u002F Instagram Reels \u002F LinkedIn Video \u002F YouTube Shorts) and standalone LinkedIn posts using native Hermes tools. No Claude Code dependency.\"\nlicense: MIT\nmetadata:\n  version: \"1.2.0\"\n  tags: [video, linkedin, social-media, content, short-form, heygen]\n  platforms: [linux]\n  related_skills: [medium-story, technical-writing]\n---\n\n# Short Videos — Hermes-Native Video Script Pipeline\n\nProduce a 90-second universal short-video script and standalone LinkedIn post using Hermes tools directly. **No tmux, no Claude Code CLI.**\n\n## Configuration Variables\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `{{REPO_ROOT}}` | *(required)* | Path to your Git repository root, e.g. `~\u002Fprojects\u002Fmy-content-repo` |\n| `{{RP_VIDEO_DIR}}` | `{{REPO_ROOT}}\u002Fshort_videos` | Directory holding numbered video folders under the repo root |\n\nBefore running the pipeline, set `{{REPO_ROOT}}` to your actual content repository path. All file operations reference this variable — never hardcode absolute paths.\n\n## Prerequisites\n\n- **Hermes Agent** (runtime environment)\n- **Git repo** (your content repository — clone it to `{{REPO_ROOT}}`)\n- **GitHub \u002F Git remote** configured for push\n- **HeyGen** (optional) — scripts are HeyGen-ready but work on any teleprompter platform\n- Python 3 for word-count verification\n\n## When to Use\n\n- User says \"create a short video about...\" or \"make a reel on...\"\n- User wants a LinkedIn post that stands alone (not marketing for a video or article)\n- User needs a HeyGen script for their digital twin\n\n## Outputs Produced\n\n| File | Format | Description |\n|------|--------|-------------|\n| `video-script.md` | Markdown (90s, timestamped blocks) | Universal teleprompter script for HeyGen\u002FReels\u002FShorts\u002FLinkedIn Video |\n| `linkedin-post.md` | Markdown | Standalone LinkedIn post (no article link, ≤3,000 chars, 5 hashtags) |\n| `quality-report.md` | Markdown | Fact-check, word count, British English, hook strength, character count |\n\n## Repo & Conventions\n\n- **Repo path:** `{{REPO_ROOT}}`\n- **Video folders:** `{{RP_VIDEO_DIR}}\u002FNN_slug\u002F` — numbered sequentially, zero-padded to 2 digits (01, 02, 03...)\n- **Root files:** `CLAUDE.md` (project instructions), `techblogger.md` (writer persona), `md_to_html.py`\n- **Sibling pipeline:** `medium-story` writes to `unpublished_stories\u002F` — this pipeline writes to `{{RP_VIDEO_DIR}}\u002F` in the same repo\n\n## Pipeline Steps\n\n### Step 1: Sync the repo\n\n```bash\nterminal(command=\"git -C {{REPO_ROOT}} pull --ff-only origin main\", timeout=30)\n```\n\n### Step 2: Read context files and find next video number\n\nRead these files from the repo root:\n- `CLAUDE.md` — project-level instructions\n- `techblogger.md` — writer persona\n\nFind the next video number:\n```bash\nterminal(command=\"ls {{RP_VIDEO_DIR}}\u002F 2>\u002Fdev\u002Fnull | grep -E '^[0-9]+_' | sed 's\u002F_.*\u002F\u002F' | sort -n | tail -1\")\n```\nIf the folder doesn't exist yet, start at `01`. Otherwise next = that value + 1, zero-padded to 2 digits.\n\n### Step 3: Research the topic\n\nSpawn a research subagent via `delegate_task`. The research must produce:\n- **One sharp angle \u002F thesis** — the single most provocative or useful truth about this topic\n- **3-5 concrete facts or statistics** (UK\u002FEU sources preferred; US only where no EU equivalent exists)\n- **One real-world example or incident** that makes the abstract tangible\n- **Quotable phrasing candidates** — short, punchy, tweetable sentences\n- **Audience relevance** — why does this matter right now to infrastructure and security professionals?\n\n### Step 4: Create video directory\n\n```bash\nterminal(command=\"mkdir -p {{RP_VIDEO_DIR}}\u002FNN_slug\u002F\")\n```\n\n### Step 5: Run three parallel agents\n\nUse `delegate_task` with `tasks: [...]` to spawn all three simultaneously. Pass research context to each.\n\n#### Agent A — Universal Video Script (`video-script.md`)\n\nWrite a 90-second teleprompter script for the presenter's HeyGen digital twin, designed for:\n- **Instagram Reels** (9:16, vertical, mobile-first, caption-dependent viewers)\n- **LinkedIn Video** (square or 9:16, professional audience, often watched muted)\n- **YouTube Shorts** (9:16, vertical, algorithm-driven discovery)\n\n**Script structure — use exactly this format:**\n\n```markdown\nTOPIC: [topic name]\nSPOKEN WORD COUNT TARGET: 200–230 words\nPLATFORMS: Instagram Reels · LinkedIn Video · YouTube Shorts\n\n---\n\n[HOOK] 00:00–00:05\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n[SETUP] 00:05–00:20\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n[INSIGHT 1] 00:20–00:40\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n[INSIGHT 2] 00:40–01:00\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n[PAYOFF] 01:00–01:20\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n[CTA] 01:20–01:30\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n---\n\nCAPTION (universal — use for all three platforms):\n[3-5 lines: hook, core insight, 5 hashtags. No \"link in bio\".]\n\nTHUMBNAIL CONCEPT:\n[One sentence describing a still frame that works as a cover image across all platforms.]\n```\n\n**Script rules:**\n- Hook lands within the first 3 seconds — bold claim, provocative question, or counterintuitive fact\n- Spoken text must sound natural read aloud at steady pace — no bullet points, no headers, no jargon dumps\n- On-screen text: max 6 words per frame — reinforce spoken word, don't duplicate verbatim\n- Stage directions: brief cues (e.g. \"lean forward slightly\", \"pause for emphasis\")\n- B-roll\u002Fgraphic: practical suggestions (e.g. \"terminal output animation\", \"NCSC logo fade in\")\n- British English throughout\n- No mid-sentence dashes — use commas, colons, or semicolons\n- No fluffy openers — do not start with \"I've been in infrastructure for X years\"\n- End CTA must be platform-neutral — no \"swipe up\", no \"link in bio\". Use \"follow for more\", \"drop a comment\", or \"save this one\"\n\n**Word count verification (mandatory after each draft):**\nAfter writing the script, extract and count the spoken words to verify the total is within 200–230:\n\n```bash\npython3 -c \"\nimport sys, re\ntext = open(sys.argv[1]).read()\n# Match 'Spoken: \u003Ctext>' lines in inline-colon format\nblocks = re.findall(r'^Spoken:\\\\s*(.*?)$', text, re.MULTILINE)\ntotal = sum(len(b.split()) for b in blocks)\nprint(f'Spoken word count: {total}')\nif total \u003C 200: print('TOO LOW — expand spoken sections')\nelif total > 230: print('TOO HIGH — trim spoken sections')\nelse: print('Within target range.')\n\"\n```\n\nRun this after every edit to the spoken text until the count is between 200 and 230. Do not guess — verify.\n\n#### Agent B — LinkedIn Post (`linkedin-post.md`)\n\nWrite a standalone LinkedIn post — **not** marketing for a video or article. It stands alone as a piece of insight content.\n\n- Hook line: must stop the scroll in the first sentence\n- Body: 3-6 short paragraphs, each punchy and self-contained\n- No \"link in comments\" — there is no link\n- No \"watch my video\" language — this post exists independently\n- 3,000 character hard limit (LinkedIn cap) — count carefully\n- End with a question or provocation that invites comments\n- Exactly 5 hashtags at the end\n- British English, no mid-sentence dashes\n- Do not open with \"I've been in infrastructure for X years\" or any years-of-experience framing\n\n#### Agent C — Quality Check (`quality-report.md`)\n\nReview both `video-script.md` and `linkedin-post.md` once drafted, producing a report covering:\n\n1. **Fact accuracy** — verify each statistic and claim; flag anything unverifiable or misleading\n2. **Spoken word count** — count spoken sections of video script; flag if outside 200-230 words\n3. **Timing sense-check** — does script feel paced correctly for 90 seconds at natural speech rate?\n4. **British English** — flag any Americanisms\n5. **Dash check** — flag any mid-sentence em dashes or en dashes used as parenthetical breaks\n6. **LinkedIn character count** — report exact count and flag if over 3,000\n7. **Hook strength** — rate the video hook and LinkedIn hook on 1-5 scale with reasoning\n8. **CTA check** — confirm video CTA contains no platform-specific mechanics\n\nIf issues found, list as actionable items. Do not rewrite the files — report only.\n\n### Step 6: Commit and push\n\n```bash\nterminal(command=\"cd {{REPO_ROOT}} && git add {{RP_VIDEO_DIR}}\u002FNN_slug\u002F && git commit -m 'Add short video NN: [topic summary]' && git push\", timeout=30)\n```\n\nAlways push. Never leave new video content uncommitted.\n\n## Writer Voice & Style Guide\n\nThis section is derived from analysing a practitioner's published work across multiple platforms. The patterns below describe what the voice actually sounds like — not a theoretical style guide.\n\n### Core Voice\n\n- **Practitioner, not pundit.** Speaks from experience managing real infrastructure at scale.\n- **British English always.** -ise not -ize, colour, favour, behaviour, defence, whilst, amongst, licence, harbour, realise, analyse.\n- **Dry, understated wit.** Surfaces naturally when the situation is absurd. \"The catch, in this case, is that there is not one.\" \u002F \"I collect them the way people collect gym memberships: with great optimism and almost zero follow-through.\"\n- **Leads with impact, then explains mechanism.** The human\u002Foperational consequence first, the technical explanation second.\n\n### Short Video Script Voice (90 seconds, spoken)\n\nBecause the short video format compresses everything, the voice translates differently:\n\n- **Hook lands by reframing or surprising.** Not a question. Not a clickbait opener. A short, sharp statement of the unexpected truth.\n- **Sentences are shorter than in articles but maintain the same rhythm.** 15-25 words spoken per sentence. Still precise. Still British English. Still no filler.\n- **\"Here is the thing\" \u002F \"Here is what matters\"** are still banned. Say the thing. Don't announce you're about to say it.\n- **End CTA is direct and platform-neutral:** \"Follow for more.\" \u002F \"Drop a comment.\" \u002F \"Save this one.\" Never \"swipe up\", never \"link in bio.\"\n\n### LinkedIn Post Voice (standalone)\n\n- **Opens like telling a colleague what happened.** \"Ran the NCSC exercise with Rui this week.\" \u002F \"Microsoft Edge decrypts every single saved password the moment it launches.\"\n- **No emoji-headlines.** No \"🛑 What would you do if...?\" — that's ad copy, not the writer's voice.\n- **3-6 short paragraphs, each punchy.** 3,000 character hard limit. Every sentence earns its place.\n- **No \"with over 20 years of experience\"** framing — authority comes from the content, not the opener.\n- **Ends with a question or provocation** that invites comments.\n- **Exactly 5 hashtags.**\n\n### What NEVER Appears\n\n- ❌ Mid-sentence dashes (em dashes, en dashes) — use commas or parentheses\n- ❌ AI transition phrases: \"Here's what matters\", \"What this means is\", \"Here's the thing\"\n- ❌ Corporate jargon: \"data estate\", \"operational reality\", \"measured in inconvenience\"\n- ❌ Fluffy openers: \"In today's digital landscape\"\n- ❌ Credentials-first: \"With over 20 years of experience...\"\n- ❌ Ad-copy hooks: \"Not hypothetically. In the next 60 seconds.\"\n- ❌ Paired oppositions (language-model parallelism)\n- ❌ American spellings — ever\n- ❌ \"It is important to note that\" — just note it\n- ❌ \"Furthermore\", \"Moreover\", \"Additionally\" — use \"And\"\n\n### The Test\n\nRead it aloud. If it sounds like a LinkedIn post from someone trying to sound authoritative, cut it. If it sounds like someone who just got off a call with a vendor who overpromised and underdelivered — that is the voice.\n\n### Pre-Publish Checklist\n\nBefore saving any script or LinkedIn post, run this check:\n\n| Pattern | Fix |\n|---------|-----|\n| \"delve\", \"tapestry\", \"realm\", \"leverage\" | Replace with plain English |\n| \"in order to\" | Replace with \"to\" |\n| \"it is worth [verb]ing\" | Replace with \"Let me [verb]\" |\n| \"it is important to note that\" | Delete |\n| \"Furthermore,\" \u002F \"Moreover,\" | Replace with \"And\" or nothing |\n| \"Not only... but also\" | Simplify |\n| \"By [verb]ing...\" (sentence opener) | Rephrase |\n| \"One of the most [adjective]\" | Be specific or delete |\n| \"In today's [X]\" \u002F \"In an era of\" | Delete entirely |\n| Contractions missing | Add don't\u002Fwon't\u002Fit's\u002Fcan't |\n\nRun this checklist before returning. If any pattern appears, rewrite.\n- **Authority** comes from tone and insight, not from stating credentials\n\n## Pitfalls\n\n- **Research agents may fabricate statistics.** The quality check agent catches these — trust but verify. The quality report is a genuine check, not a rubber stamp.\n- **LinkedIn post is standalone.** No \"link in bio\u002Fdescription\" CTA. The quality agent enforces this.\n- **Video script CTA must be platform-neutral.** No \"swipe up\", no \"link in bio\". Use \"follow for more\", \"drop a comment\", \"save this one\".\n- **Spoken word count target is 200-230 words.** Shorter scripts feel rushed or sparse; longer scripts exceed 90 seconds at natural speech rate.\n- **Hook must land within 3 seconds.** Vertical video viewers decide whether to watch in the first 1-2 seconds. The hook is the single most important element.\n- **Git authentication:** If `git push` fails, report the error. The files exist locally — don't lose them.\n- **Delegate_task context limits:** For the video script agent especially, the output format is very specific. Include the full script template in the context to ensure correct structure.\n","# Short Videos — Hermes-Native Video Script Pipeline\n\nProduce a 90-second universal short-video script and standalone LinkedIn post using Hermes tools directly. **No tmux, no Claude Code CLI.**\n\n## Configuration Variables\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `{{REPO_ROOT}}` | *(required)* | Path to your Git repository root, e.g. `~\u002Fprojects\u002Fmy-content-repo` |\n| `{{RP_VIDEO_DIR}}` | `{{REPO_ROOT}}\u002Fshort_videos` | Directory holding numbered video folders under the repo root |\n\nBefore running the pipeline, set `{{REPO_ROOT}}` to your actual content repository path. All file operations reference this variable — never hardcode absolute paths.\n\n## Prerequisites\n\n- **Hermes Agent** (runtime environment)\n- **Git repo** (your content repository — clone it to `{{REPO_ROOT}}`)\n- **GitHub \u002F Git remote** configured for push\n- **HeyGen** (optional) — scripts are HeyGen-ready but work on any teleprompter platform\n- Python 3 for word-count verification\n\n## When to Use\n\n- User says \"create a short video about...\" or \"make a reel on...\"\n- User wants a LinkedIn post that stands alone (not marketing for a video or article)\n- User needs a HeyGen script for their digital twin\n\n## Outputs Produced\n\n| File | Format | Description |\n|------|--------|-------------|\n| `video-script.md` | Markdown (90s, timestamped blocks) | Universal teleprompter script for HeyGen\u002FReels\u002FShorts\u002FLinkedIn Video |\n| `linkedin-post.md` | Markdown | Standalone LinkedIn post (no article link, ≤3,000 chars, 5 hashtags) |\n| `quality-report.md` | Markdown | Fact-check, word count, British English, hook strength, character count |\n\n## Repo & Conventions\n\n- **Repo path:** `{{REPO_ROOT}}`\n- **Video folders:** `{{RP_VIDEO_DIR}}\u002FNN_slug\u002F` — numbered sequentially, zero-padded to 2 digits (01, 02, 03...)\n- **Root files:** `CLAUDE.md` (project instructions), `techblogger.md` (writer persona), `md_to_html.py`\n- **Sibling pipeline:** `medium-story` writes to `unpublished_stories\u002F` — this pipeline writes to `{{RP_VIDEO_DIR}}\u002F` in the same repo\n\n## Pipeline Steps\n\n### Step 1: Sync the repo\n\n```bash\nterminal(command=\"git -C {{REPO_ROOT}} pull --ff-only origin main\", timeout=30)\n```\n\n### Step 2: Read context files and find next video number\n\nRead these files from the repo root:\n- `CLAUDE.md` — project-level instructions\n- `techblogger.md` — writer persona\n\nFind the next video number:\n```bash\nterminal(command=\"ls {{RP_VIDEO_DIR}}\u002F 2>\u002Fdev\u002Fnull | grep -E '^[0-9]+_' | sed 's\u002F_.*\u002F\u002F' | sort -n | tail -1\")\n```\nIf the folder doesn't exist yet, start at `01`. Otherwise next = that value + 1, zero-padded to 2 digits.\n\n### Step 3: Research the topic\n\nSpawn a research subagent via `delegate_task`. The research must produce:\n- **One sharp angle \u002F thesis** — the single most provocative or useful truth about this topic\n- **3-5 concrete facts or statistics** (UK\u002FEU sources preferred; US only where no EU equivalent exists)\n- **One real-world example or incident** that makes the abstract tangible\n- **Quotable phrasing candidates** — short, punchy, tweetable sentences\n- **Audience relevance** — why does this matter right now to infrastructure and security professionals?\n\n### Step 4: Create video directory\n\n```bash\nterminal(command=\"mkdir -p {{RP_VIDEO_DIR}}\u002FNN_slug\u002F\")\n```\n\n### Step 5: Run three parallel agents\n\nUse `delegate_task` with `tasks: [...]` to spawn all three simultaneously. Pass research context to each.\n\n#### Agent A — Universal Video Script (`video-script.md`)\n\nWrite a 90-second teleprompter script for the presenter's HeyGen digital twin, designed for:\n- **Instagram Reels** (9:16, vertical, mobile-first, caption-dependent viewers)\n- **LinkedIn Video** (square or 9:16, professional audience, often watched muted)\n- **YouTube Shorts** (9:16, vertical, algorithm-driven discovery)\n\n**Script structure — use exactly this format:**\n\n```markdown\nTOPIC: [topic name]\nSPOKEN WORD COUNT TARGET: 200–230 words\nPLATFORMS: Instagram Reels · LinkedIn Video · YouTube Shorts\n\n---\n\n[HOOK] 00:00–00:05\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n[SETUP] 00:05–00:20\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n[INSIGHT 1] 00:20–00:40\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n[INSIGHT 2] 00:40–01:00\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n[PAYOFF] 01:00–01:20\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n[CTA] 01:20–01:30\nSpoken: ...\nOn-screen text: ...\nStage direction: ...\nB-roll \u002F graphic: ...\n\n---\n\nCAPTION (universal — use for all three platforms):\n[3-5 lines: hook, core insight, 5 hashtags. No \"link in bio\".]\n\nTHUMBNAIL CONCEPT:\n[One sentence describing a still frame that works as a cover image across all platforms.]\n```\n\n**Script rules:**\n- Hook lands within the first 3 seconds — bold claim, provocative question, or counterintuitive fact\n- Spoken text must sound natural read aloud at steady pace — no bullet points, no headers, no jargon dumps\n- On-screen text: max 6 words per frame — reinforce spoken word, don't duplicate verbatim\n- Stage directions: brief cues (e.g. \"lean forward slightly\", \"pause for emphasis\")\n- B-roll\u002Fgraphic: practical suggestions (e.g. \"terminal output animation\", \"NCSC logo fade in\")\n- British English throughout\n- No mid-sentence dashes — use commas, colons, or semicolons\n- No fluffy openers — do not start with \"I've been in infrastructure for X years\"\n- End CTA must be platform-neutral — no \"swipe up\", no \"link in bio\". Use \"follow for more\", \"drop a comment\", or \"save this one\"\n\n**Word count verification (mandatory after each draft):**\nAfter writing the script, extract and count the spoken words to verify the total is within 200–230:\n\n```bash\npython3 -c \"\nimport sys, re\ntext = open(sys.argv[1]).read()\n# Match 'Spoken: \u003Ctext>' lines in inline-colon format\nblocks = re.findall(r'^Spoken:\\\\s*(.*?)$', text, re.MULTILINE)\ntotal = sum(len(b.split()) for b in blocks)\nprint(f'Spoken word count: {total}')\nif total \u003C 200: print('TOO LOW — expand spoken sections')\nelif total > 230: print('TOO HIGH — trim spoken sections')\nelse: print('Within target range.')\n\"\n```\n\nRun this after every edit to the spoken text until the count is between 200 and 230. Do not guess — verify.\n\n#### Agent B — LinkedIn Post (`linkedin-post.md`)\n\nWrite a standalone LinkedIn post — **not** marketing for a video or article. It stands alone as a piece of insight content.\n\n- Hook line: must stop the scroll in the first sentence\n- Body: 3-6 short paragraphs, each punchy and self-contained\n- No \"link in comments\" — there is no link\n- No \"watch my video\" language — this post exists independently\n- 3,000 character hard limit (LinkedIn cap) — count carefully\n- End with a question or provocation that invites comments\n- Exactly 5 hashtags at the end\n- British English, no mid-sentence dashes\n- Do not open with \"I've been in infrastructure for X years\" or any years-of-experience framing\n\n#### Agent C — Quality Check (`quality-report.md`)\n\nReview both `video-script.md` and `linkedin-post.md` once drafted, producing a report covering:\n\n1. **Fact accuracy** — verify each statistic and claim; flag anything unverifiable or misleading\n2. **Spoken word count** — count spoken sections of video script; flag if outside 200-230 words\n3. **Timing sense-check** — does script feel paced correctly for 90 seconds at natural speech rate?\n4. **British English** — flag any Americanisms\n5. **Dash check** — flag any mid-sentence em dashes or en dashes used as parenthetical breaks\n6. **LinkedIn character count** — report exact count and flag if over 3,000\n7. **Hook strength** — rate the video hook and LinkedIn hook on 1-5 scale with reasoning\n8. **CTA check** — confirm video CTA contains no platform-specific mechanics\n\nIf issues found, list as actionable items. Do not rewrite the files — report only.\n\n### Step 6: Commit and push\n\n```bash\nterminal(command=\"cd {{REPO_ROOT}} && git add {{RP_VIDEO_DIR}}\u002FNN_slug\u002F && git commit -m 'Add short video NN: [topic summary]' && git push\", timeout=30)\n```\n\nAlways push. Never leave new video content uncommitted.\n\n## Writer Voice & Style Guide\n\nThis section is derived from analysing a practitioner's published work across multiple platforms. The patterns below describe what the voice actually sounds like — not a theoretical style guide.\n\n### Core Voice\n\n- **Practitioner, not pundit.** Speaks from experience managing real infrastructure at scale.\n- **British English always.** -ise not -ize, colour, favour, behaviour, defence, whilst, amongst, licence, harbour, realise, analyse.\n- **Dry, understated wit.** Surfaces naturally when the situation is absurd. \"The catch, in this case, is that there is not one.\" \u002F \"I collect them the way people collect gym memberships: with great optimism and almost zero follow-through.\"\n- **Leads with impact, then explains mechanism.** The human\u002Foperational consequence first, the technical explanation second.\n\n### Short Video Script Voice (90 seconds, spoken)\n\nBecause the short video format compresses everything, the voice translates differently:\n\n- **Hook lands by reframing or surprising.** Not a question. Not a clickbait opener. A short, sharp statement of the unexpected truth.\n- **Sentences are shorter than in articles but maintain the same rhythm.** 15-25 words spoken per sentence. Still precise. Still British English. Still no filler.\n- **\"Here is the thing\" \u002F \"Here is what matters\"** are still banned. Say the thing. Don't announce you're about to say it.\n- **End CTA is direct and platform-neutral:** \"Follow for more.\" \u002F \"Drop a comment.\" \u002F \"Save this one.\" Never \"swipe up\", never \"link in bio.\"\n\n### LinkedIn Post Voice (standalone)\n\n- **Opens like telling a colleague what happened.** \"Ran the NCSC exercise with Rui this week.\" \u002F \"Microsoft Edge decrypts every single saved password the moment it launches.\"\n- **No emoji-headlines.** No \"🛑 What would you do if...?\" — that's ad copy, not the writer's voice.\n- **3-6 short paragraphs, each punchy.** 3,000 character hard limit. Every sentence earns its place.\n- **No \"with over 20 years of experience\"** framing — authority comes from the content, not the opener.\n- **Ends with a question or provocation** that invites comments.\n- **Exactly 5 hashtags.**\n\n### What NEVER Appears\n\n- ❌ Mid-sentence dashes (em dashes, en dashes) — use commas or parentheses\n- ❌ AI transition phrases: \"Here's what matters\", \"What this means is\", \"Here's the thing\"\n- ❌ Corporate jargon: \"data estate\", \"operational reality\", \"measured in inconvenience\"\n- ❌ Fluffy openers: \"In today's digital landscape\"\n- ❌ Credentials-first: \"With over 20 years of experience...\"\n- ❌ Ad-copy hooks: \"Not hypothetically. In the next 60 seconds.\"\n- ❌ Paired oppositions (language-model parallelism)\n- ❌ American spellings — ever\n- ❌ \"It is important to note that\" — just note it\n- ❌ \"Furthermore\", \"Moreover\", \"Additionally\" — use \"And\"\n\n### The Test\n\nRead it aloud. If it sounds like a LinkedIn post from someone trying to sound authoritative, cut it. If it sounds like someone who just got off a call with a vendor who overpromised and underdelivered — that is the voice.\n\n### Pre-Publish Checklist\n\nBefore saving any script or LinkedIn post, run this check:\n\n| Pattern | Fix |\n|---------|-----|\n| \"delve\", \"tapestry\", \"realm\", \"leverage\" | Replace with plain English |\n| \"in order to\" | Replace with \"to\" |\n| \"it is worth [verb]ing\" | Replace with \"Let me [verb]\" |\n| \"it is important to note that\" | Delete |\n| \"Furthermore,\" \u002F \"Moreover,\" | Replace with \"And\" or nothing |\n| \"Not only... but also\" | Simplify |\n| \"By [verb]ing...\" (sentence opener) | Rephrase |\n| \"One of the most [adjective]\" | Be specific or delete |\n| \"In today's [X]\" \u002F \"In an era of\" | Delete entirely |\n| Contractions missing | Add don't\u002Fwon't\u002Fit's\u002Fcan't |\n\nRun this checklist before returning. If any pattern appears, rewrite.\n- **Authority** comes from tone and insight, not from stating credentials\n\n## Pitfalls\n\n- **Research agents may fabricate statistics.** The quality check agent catches these — trust but verify. The quality report is a genuine check, not a rubber stamp.\n- **LinkedIn post is standalone.** No \"link in bio\u002Fdescription\" CTA. The quality agent enforces this.\n- **Video script CTA must be platform-neutral.** No \"swipe up\", no \"link in bio\". Use \"follow for more\", \"drop a comment\", \"save this one\".\n- **Spoken word count target is 200-230 words.** Shorter scripts feel rushed or sparse; longer scripts exceed 90 seconds at natural speech rate.\n- **Hook must land within 3 seconds.** Vertical video viewers decide whether to watch in the first 1-2 seconds. The hook is the single most important element.\n- **Git authentication:** If `git push` fails, report the error. The files exist locally — don't lose them.\n- **Delegate_task context limits:** For the video script agent especially, the output format is very specific. Include the full script template in the context to ensure correct structure.\n",{"name":5,"license":15,"metadata":24,"description":7},{"tags":25,"version":32,"platforms":33,"related_skills":35},[26,27,28,29,30,31],"video","linkedin","social-media","content","short-form","heygen","1.2.0",[34],"linux",[36,37],"medium-story","technical-writing","main","6612bed4902342e57e7f68416c67ee822f3816f3","skills\u002Fproductivity-pack\u002Fshort-videos","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center","https:\u002F\u002Fgithub.com\u002Fgyc567","love hacking and hiking! \r\n技术博客：https:\u002F\u002Fwww.cnblogs.com\u002Fgyc567","2026-11-10 15:55:55",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add gyc567\u002Fgreat-skill-center --skill short-videos",{"tool":51,"command":52},"bunx","bunx skills add gyc567\u002Fgreat-skill-center --skill short-videos",{"tool":54,"command":55},"pnpm","pnpm dlx skills add gyc567\u002Fgreat-skill-center --skill short-videos","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity-pack\u002Fshort-videos\u002FSKILL.md",true,[59,65,71],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},".gitignore","OTHER","其他",370,"https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity-pack\u002Fshort-videos\u002F.gitignore",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"README.md","REFERENCE","参考文档",7307,"https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity-pack\u002Fshort-videos\u002FREADME.md",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"VIDEO_FORMAT.md",8550,"https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity-pack\u002Fshort-videos\u002FVIDEO_FORMAT.md",[76,84,92,100,108,116],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M79GXESPRPQND3ZW1FKKWCF5","writing-dna-skill","从至少 20 篇完整文章中蒸馏可复用的写作 DNA，分析语言、文章结构、选题逻辑、素材策略、认知框架和视觉风格，并生成 Writing-DNA.md；按该 DNA 写作时会读取全部蒸馏产物和 5 篇相关原文。用于中英文作者、账号、品牌或出版物的风格分析与一致性写作。 Distill reusable Writing DNA from at least 20 complete articles for Chinese or English authors, publications, brands, and accounts; use for language, structure, topic logic, source strategy, cognitive-frame, and visual-style analysis.","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-dna-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-dna-skill\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M79GW2HHGV5RE1YWP7ANQ9JA","ub-quality-gates","Uncle Bob 编程纪律与确定性质量门工具链。写代码或改代码时使用：先让它能跑，再让它正确，最后守纪律。 当用户要求 \u002Fub-mode、需要代码质量门禁、CRAP 评分、重复代码检测、变异测试、 或抱怨代码难懂\u002F难测\u002F有重复时触发。覆盖 Clojure\u002FJava\u002FGo\u002FTypeScript\u002FRust\u002FPython。","0BSD","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fub-quality-gates\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M79GVTKM2QWEG8R6VTKDSD0V","tweet-composer","Score and optimize tweets based on X's real open-source ranking algorithm. Analyzes draft tweets against the actual ranking code — not generic tips. Use when: composing tweets, optimizing drafts for reach, planning threads, analyzing why a tweet performed well\u002Fpoorly, or asking for posting strategy advice.","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Ftweet-composer\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Ftweet-composer\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":104,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M79GR8RYEV0YXBS536MF99JN","short-video-scripter","Use when the user asks to \"script this short video\", \"write a TikTok \u002F Reels \u002F Shorts script\", \"给这条抖音或视频号视频写脚本\", or \"fix the hook — viewers drop off in the first seconds\"; produces timestamped beat-sheet scripts on the retention-gate model (0-2s hook \u002F 2-5s confirmation \u002F 5-15s payoff \u002F loop-or-CTA) with per-scene script lines, on-screen text for muted viewing, asset keywords, and 9:16 format-param rows per platform norm card for TikTok, Reels, Shorts, 抖音, and 视频号 — plus 2-3 hook options from named hook families and an AI-content disclosure line by default on realistic synthetic media. Spec-only: rendering, TTS, and publishing stay with the user's own tools — no pipelines, no upload automation. Not for creator video briefs — use brief-generator; long-form video SEO belongs to content-writer. 短视频脚本\u002F抖音分镜\u002F开头钩子\u002F竖屏9:16","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fshort-video-scripter\u002FSKILL.md",[],[],{"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":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M79GQ5XG8TY96C8HMG5W9FA5","remotion-video-master","Remotion 视频编程大师 — 用 React 组件以编程方式创建 MP4 视频。支持动画、字幕、音乐可视化、 AI 配音（TTS）与场景自动配时。触发词：用代码做视频、编程视频、React 视频、Remotion、 \u002Fremotion-video。适用场景：程序化视频（批量生成、数据驱动如年度总结、音乐可视化、自动字幕）、 教程讲解视频（技术概念可视化如 CNN 与算法、分层递进讲解、AI 配音教程）、 3D 视频（产品展示与模型动画、卡通角色讲解、3D 数据可视化、Logo 动画）。","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fremotion-video-master\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fremotion-video-master\u002FSKILL.md",[],[],{"skillNo":117,"name":36,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M79GP11FPAVGESW5VE3NGXR1","Full Medium article pipeline using native Hermes tools. Research → write → 4 parallel output agents → HTML conversion → git commit\u002Fpush. Includes pre-flight infrastructure verification step, revisor-methodology fact-checking, and an anti-AI-slop writing pass (banned vocabulary, structural variety, accuracy rules).","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity-pack\u002Fmedium-story\u002FSKILL.md",[],[]]