Update to Simplified for AI

{
  "description": "Build a renewable, long-lived content system that repeatedly turns durable brand expertise, customer questions, proof, and offers into channel-native social content. Use when the user asks for an evergreen strategy, always-on content engine, recurring content series, 60- or 90-day program, content bank, sustainable posting system, content recycling plan, or a way to keep publishing without chasing daily trends.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 513
    },
    {
      "relative_path": "references/content-system.md",
      "size_in_bytes": 2485
    }
  ],
  "name": "evergreen-content-engine",
  "skill_md_contents": "---\nname: evergreen-content-engine\ndescription: Build a renewable, long-lived content system that repeatedly turns durable brand expertise, customer questions, proof, and offers into channel-native social content. Use when the user asks for an evergreen strategy, always-on content engine, recurring content series, 60- or 90-day program, content bank, sustainable posting system, content recycling plan, or a way to keep publishing without chasing daily trends.\n---\n\n# Evergreen Content Engine\n\nDesign a compounding content program in which durable ideas become repeatable franchises, varied executions, and measurable learning—not a calendar filled with generic tips.\n\n## Guardrails\n\nExisting explicit authorization for unchanged content, accounts, timing, media, and comments is sufficient; ask only when that authorization is missing or the proposed effects change.\n\n- Do not label time-sensitive offers, statistics, platform features, event dates, seasonal advice, or changing regulations as evergreen.\n- Treat brand claims, customer proof, prices, outcomes, and quotations as source-dependent. Never manufacture authority or testimonials.\n- Separate planning, remote draft creation, scheduling, and publishing authorization.\n- Create remote posts only with `action: \"draft\"` unless the user explicitly approves a final schedule or queue action.\n- Do not automate indefinite recycling. Every reusable asset needs a review date, fatigue signal, and retirement rule.\n- Pause affected connected operations when Simplified is unauthorized. Planning and requested accountless drafts can proceed without connected accounts; publishing and account analytics require suitable accounts.\n\n## Workspace and handoff\n\nBefore connected operations, use `simplified-workspace` when the client/workspace/teamspace is named or uncertain. Resolve the exact numeric teamspace and carry its `space_id` on every related account, analytics, asset, generation, draft, tag, review, and continuation call. Re-list scoped resources after switching clients; stop on access failures rather than falling back to another space. Pass the resolved context to every delegated skill.\n\n## Workflow\n\n1. Define the business objective, audience segments, buying questions, offers, expertise, proof library, content capacity, channels, cadence, and measurement horizon. State assumptions rather than forcing a long intake.\n2. Call `social_getSocialMediaAccounts` once when connected-channel planning or drafting is requested.\n3. If the user wants an evidence-led engine, inspect recent aggregated, trend, and post analytics. Use `$social-performance-analyst` for a full diagnosis.\n4. Build a durable source map: customer questions, misconceptions, decision criteria, demonstrations, processes, founder/operator insight, customer evidence, and objection handling. Distinguish owned expertise from borrowed opinion.\n5. Define three to five content territories with a strategic job, audience problem, credible point of view, proof sources, conversion bridge, and exclusions.\n6. Turn territories into recurring franchises such as teardown, checklist, FAQ, myth, before/after process, decision guide, customer lesson, or behind-the-scenes operating principle.\n7. Create a content bank with atomic ideas. Score each for relevance, distinctiveness, evidence strength, reuse potential, production effort, and shelf life using [references/content-system.md](references/content-system.md).\n8. Build a 60- or 90-day sequence that balances discovery, trust, consideration, proof, and conversion. Rewrite ideas for each channel instead of duplicating captions.\n9. When drafts are requested, call `social_createSocialMediaPost` with `action: \"draft\"`, permanent asset IDs, and platform settings from `../simplified-social/references/platform-settings.md`.\n10. Define the renewal loop: review results, retain winners, vary one meaningful element, refresh changed claims, pause fatigued concepts, and feed learning back into the bank.\n\n## Marketing Standard\n\n- Start from audience decisions and recurring problems, not arbitrary posting categories.\n- Give each territory a defensible brand angle. “Educational content” is not a territory until it has a subject, viewpoint, and audience consequence.\n- Build memory through recognizable recurring formats while changing examples, hooks, proof, and creative treatment.\n- Maintain an intentional conversion bridge. Evergreen does not mean every post sells, but the program should make the next step obvious over time.\n- Protect production sustainability. A viable engine respects access to experts, customer proof, design/video capacity, approval time, and channel cadence.\n- Use performance as directional evidence; do not let one outlier post rewrite the entire strategy.\n\n## Media and write results\n\nUse `manage-assets` to find existing library media before generating copies. Resolve names/tags through exposed asset discovery, preserve pagination and scope, import accessible remote files, and require ready assets before generation or attaching media. Check byte access and HTTP PUT capability before signing a local/chat attachment upload; if unavailable, ask for a Simplified asset ID or downloadable URL. Pass permanent UUIDs into drafts. A missing required visual remains a stated production gap; do not report a media-ready post without it.\n\nFor a batch of drafts, retain each successful returned ID and report created, pending, and failed items. Continue only unfinished items; do not recreate successful drafts after a later failure. A plan or test design alone does not authorize remote writes.\n\n## Output\n\nLead with the evergreen thesis and audience value. Then provide territories, franchises, source requirements, content-bank priorities, cadence, a dated first cycle, refresh/retirement rules, success measures, and the exact authorized state: plan, drafts, or awaiting scheduling approval.\n"
}