{
  "manifest": {
    "id": "content",
    "name": "Content & Brand Voice",
    "description": "Content engine patterns, article writing workflows, brand voice consistency, editorial standards, and content strategy implementation",
    "version": "1.0.0",
    "author": "Adiuvo",
    "tags": [
      "content",
      "writing",
      "brand",
      "editorial",
      "marketing"
    ],
    "icon": "",
    "created_at": "2026-06-11T01:40:46Z",
    "updated_at": "2026-06-11T01:40:46Z",
    "category": "",
    "pack_type": "enhancement",
    "required_mcp_servers": [],
    "optional_mcp_servers": [],
    "on_install": null,
    "procedure_count": 0,
    "context_file_count": 3,
    "always_loaded": false
  },
  "index": "# Content & Brand Voice\n\nContent creation and brand voice patterns covering content engines, article writing, and editorial standards.\n\n## What's Included\n\n- **Content Engine** -- Content pipeline design, CMS integration, content scheduling, taxonomy management, and content lifecycle workflows\n- **Article Writing** -- Article structure, research workflows, SEO-optimized writing, editorial review processes, and publication standards\n- **Brand Voice** -- Voice and tone guidelines, messaging consistency, terminology management, and brand-aligned content creation\n\n## When to Use\n\nActivate this pack when:\n- Building content management systems\n- Writing technical or marketing content\n- Establishing brand voice guidelines\n- Designing content workflows and pipelines\n- Ensuring editorial consistency across content\n",
  "procedures": [],
  "commands": [],
  "context_files": [
    {
      "filename": "article-writing.md",
      "content": "---\nname: article-writing\ndescription: Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.\norigin: ECC\n---\n\n# Article Writing\n\nWrite long-form content that sounds like an actual person with a point of view, not an LLM smoothing itself into paste.\n\n## When to Activate\n\n- drafting blog posts, essays, launch posts, guides, tutorials, or newsletter issues\n- turning notes, transcripts, or research into polished articles\n- matching an existing founder, operator, or brand voice from examples\n- tightening structure, pacing, and evidence in already-written long-form copy\n\n## Core Rules\n\n1. Lead with the concrete thing: artifact, example, output, anecdote, number, screenshot, or code.\n2. Explain after the example, not before.\n3. Keep sentences tight unless the source voice is intentionally expansive.\n4. Use proof instead of adjectives.\n5. Never invent facts, credibility, or customer evidence.\n\n## Voice Handling\n\nIf the user wants a specific voice, run `brand-voice` first and reuse its `VOICE PROFILE`.\nDo not duplicate a second style-analysis pass here unless the user explicitly asks for one.\n\nIf no voice references are given, default to a sharp operator voice: concrete, unsentimental, useful.\n\n## Banned Patterns\n\nDelete and rewrite any of these:\n- \"In today's rapidly evolving landscape\"\n- \"game-changer\", \"cutting-edge\", \"revolutionary\"\n- \"here's why this matters\" as a standalone bridge\n- fake vulnerability arcs\n- a closing question added only to juice engagement\n- biography padding that does not move the argument\n- generic AI throat-clearing that delays the point\n\n## Writing Process\n\n1. Clarify the audience and purpose.\n2. Build a hard outline with one job per section.\n3. Start sections with proof, artifact, conflict, or example.\n4. Expand only where the next sentence earns space.\n5. Cut anything that sounds templated, overexplained, or self-congratulatory.\n\n## Structure Guidance\n\n### Technical Guides\n\n- open with what the reader gets\n- use code, commands, screenshots, or concrete output in major sections\n- end with actionable takeaways, not a soft recap\n\n### Essays / Opinion\n\n- start with tension, contradiction, or a specific observation\n- keep one argument thread per section\n- make opinions answer to evidence\n\n### Newsletters\n\n- keep the first screen doing real work\n- do not front-load diary filler\n- use section labels only when they improve scanability\n\n## Quality Gate\n\nBefore delivering:\n- factual claims are backed by provided sources\n- generic AI transitions are gone\n- the voice matches the supplied examples or the agreed `VOICE PROFILE`\n- every section adds something new\n- formatting matches the intended medium\n"
    },
    {
      "filename": "brand-voice.md",
      "content": "---\nname: brand-voice\ndescription: Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.\norigin: ECC\n---\n\n# Brand Voice\n\nBuild a durable voice profile from real source material, then use that profile everywhere instead of re-deriving style from scratch or defaulting to generic AI copy.\n\n## When to Activate\n\n- the user wants content or outreach in a specific voice\n- writing for X, LinkedIn, email, launch posts, threads, or product updates\n- adapting a known author's tone across channels\n- the existing content lane needs a reusable style system instead of one-off mimicry\n\n## Source Priority\n\nUse the strongest real source set available, in this order:\n\n1. recent original X posts and threads\n2. articles, essays, memos, launch notes, or newsletters\n3. real outbound emails or DMs that worked\n4. product docs, changelogs, README framing, and site copy\n\nDo not use generic platform exemplars as source material.\n\n## Collection Workflow\n\n1. Gather 5 to 20 representative samples when available.\n2. Prefer recent material over old material unless the user says the older writing is more canonical.\n3. Separate \"public launch voice\" from \"private working voice\" if the source set clearly splits.\n4. If live X access is available, use `x-api` to pull recent original posts before drafting.\n5. If site copy matters, include the current ECC landing page and repo/plugin framing.\n\n## What to Extract\n\n- rhythm and sentence length\n- compression vs explanation\n- capitalization norms\n- parenthetical use\n- question frequency and purpose\n- how sharply claims are made\n- how often numbers, mechanisms, or receipts show up\n- how transitions work\n- what the author never does\n\n## Output Contract\n\nProduce a reusable `VOICE PROFILE` block that downstream skills can consume directly. Use the schema in [references/voice-profile-schema.md](references/voice-profile-schema.md).\n\nKeep the profile structured and short enough to reuse in session context. The point is not literary criticism. The point is operational reuse.\n\n## Affaan / ECC Defaults\n\nIf the user wants Affaan / ECC voice and live sources are thin, start here unless newer source material overrides it:\n\n- direct, compressed, concrete\n- specifics, mechanisms, receipts, and numbers beat adjectives\n- parentheticals are for qualification, narrowing, or over-clarification\n- capitalization is conventional unless there is a real reason to break it\n- questions are rare and should not be used as bait\n- tone can be sharp, blunt, skeptical, or dry\n- transitions should feel earned, not smoothed over\n\n## Hard Bans\n\nDelete and rewrite any of these:\n\n- fake curiosity hooks\n- \"not X, just Y\"\n- \"no fluff\"\n- forced lowercase\n- LinkedIn thought-leader cadence\n- bait questions\n- \"Excited to share\"\n- generic founder-journey filler\n- corny parentheticals\n\n## Persistence Rules\n\n- Reuse the latest confirmed `VOICE PROFILE` across related tasks in the same session.\n- If the user asks for a durable artifact, save the profile in the requested workspace location or memory surface.\n- Do not create repo-tracked files that store personal voice fingerprints unless the user explicitly asks for that.\n\n## Downstream Use\n\nUse this skill before or inside:\n\n- `content-engine`\n- `crosspost`\n- `lead-intelligence`\n- article or launch writing\n- cold or warm outbound across X, LinkedIn, and email\n\nIf another skill already has a partial voice capture section, this skill is the canonical source of truth.\n"
    },
    {
      "filename": "content-engine.md",
      "content": "---\nname: content-engine\ndescription: Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.\norigin: ECC\n---\n\n# Content Engine\n\nBuild platform-native content without flattening the author's real voice into platform slop.\n\n## When to Activate\n\n- writing X posts or threads\n- drafting LinkedIn posts or launch updates\n- scripting short-form video or YouTube explainers\n- repurposing articles, podcasts, demos, docs, or internal notes into public content\n- building a launch sequence or ongoing content system around a product, insight, or narrative\n\n## Non-Negotiables\n\n1. Start from source material, not generic post formulas.\n2. Adapt the format for the platform, not the persona.\n3. One post should carry one actual claim.\n4. Specificity beats adjectives.\n5. No engagement bait unless the user explicitly asks for it.\n\n## Source-First Workflow\n\nBefore drafting, identify the source set:\n- published articles\n- notes or internal memos\n- product demos\n- docs or changelogs\n- transcripts\n- screenshots\n- prior posts from the same author\n\nIf the user wants a specific voice, build a voice profile from real examples before writing.\nUse `brand-voice` as the canonical workflow when voice consistency matters across more than one output.\n\n## Voice Handling\n\n`brand-voice` is the canonical voice layer.\n\nRun it first when:\n\n- there are multiple downstream outputs\n- the user explicitly cares about writing style\n- the content is launch, outreach, or reputation-sensitive\n\nReuse the resulting `VOICE PROFILE` here instead of rebuilding a second voice model.\nIf the user wants Affaan / ECC voice specifically, still treat `brand-voice` as the source of truth and feed it the best live or source-derived material available.\n\n## Hard Bans\n\nDelete and rewrite any of these:\n- \"In today's rapidly evolving landscape\"\n- \"game-changer\", \"revolutionary\", \"cutting-edge\"\n- \"here's why this matters\" unless it is followed immediately by something concrete\n- ending with a LinkedIn-style question just to farm replies\n- forced casualness on LinkedIn\n- fake engagement padding that was not present in the source material\n\n## Platform Adaptation Rules\n\n### X\n\n- open with the strongest claim, artifact, or tension\n- keep the compression if the source voice is compressed\n- if writing a thread, each post must advance the argument\n- do not pad with context the audience does not need\n\n### LinkedIn\n\n- expand only enough for people outside the immediate niche to follow\n- do not turn it into a fake lesson post unless the source material actually is reflective\n- no corporate inspiration cadence\n- no praise-stacking, no \"journey\" filler\n\n### Short Video\n\n- script around the visual sequence and proof points\n- first seconds should show the result, problem, or punch\n- do not write narration that sounds better on paper than on screen\n\n### YouTube\n\n- show the result or tension early\n- organize by argument or progression, not filler sections\n- use chaptering only when it helps clarity\n\n### Newsletter\n\n- open with the point, conflict, or artifact\n- do not spend the first paragraph warming up\n- every section needs to add something new\n\n## Repurposing Flow\n\n1. Pick the anchor asset.\n2. Extract 3 to 7 atomic claims or scenes.\n3. Rank them by sharpness, novelty, and proof.\n4. Assign one strong idea per output.\n5. Adapt structure for each platform.\n6. Strip platform-shaped filler.\n7. Run the quality gate.\n\n## Deliverables\n\nWhen asked for a campaign, return:\n- a short voice profile if voice matching matters\n- the core angle\n- platform-native drafts\n- posting order only if it helps execution\n- gaps that must be filled before publishing\n\n## Quality Gate\n\nBefore delivering:\n- every draft sounds like the intended author, not the platform stereotype\n- every draft contains a real claim, proof point, or concrete observation\n- no generic hype language remains\n- no fake engagement bait remains\n- no duplicated copy across platforms unless requested\n- any CTA is earned and user-approved\n\n## Related Skills\n\n- `brand-voice` for source-derived voice profiles\n- `crosspost` for platform-specific distribution\n- `x-api` for sourcing recent posts and publishing approved X output\n"
    }
  ]
}