Update to Socialinsider

{
  "description": "Benchmark a brand against its competitors on social media using Socialinsider data — share of engagement, posting cadence, engagement rate and format mix side by side. Use when the user asks how they compare to competitors, wants a competitive or industry benchmark, share-of-voice analysis, or asks who is winning on a platform.",
  "included_files": [],
  "name": "competitor-benchmark",
  "skill_md_contents": "---\nname: competitor-benchmark\ndescription: Benchmark a brand against its competitors on social media using Socialinsider data — share of engagement, posting cadence, engagement rate and format mix side by side. Use when the user asks how they compare to competitors, wants a competitive or industry benchmark, share-of-voice analysis, or asks who is winning on a platform.\n---\n\n# Competitor benchmark\n\nCompare several profiles over the same window and say who is actually winning and why.\n\n## Rules\n\n1. **Call `socialinsider_get_date_context` first, always** — then reuse the exact same `date`\n   object for every profile. A benchmark across mismatched windows is worthless.\n2. **Same platform, same window.** Never compare an Instagram profile against a LinkedIn one in\n   the same table. Group by platform and produce one table per platform.\n3. **Never invent ids.** Resolve every profile through `socialinsider_list_profiles`. If the user\n   names a competitor that isn't tracked, say so and stop — do not silently drop it and do not add\n   it (adding profiles counts against their subscription; see the note at the end).\n4. **Read-only** unless the user explicitly asks to start tracking someone.\n\n## Steps\n\n1. `socialinsider_get_date_context`.\n2. Resolve the competitive set:\n   - `socialinsider_list_profiles` for the project.\n   - `socialinsider_list_brands` when the project is brand-grouped — brands are the intended unit\n     of benchmarking, so compare brand against brand rather than a single profile against a brand.\n3. Confirm the set with the user when it is ambiguous: list who you are about to compare, on which\n   platform, over which window. One line, then proceed.\n4. For every profile in the set, over the identical window:\n   - `socialinsider_get_posts_summary` — post count, total engagement, average per post,\n     engagement rate, post-type breakdown.\n   - `socialinsider_get_profile_data` — follower count and growth over the window.\n5. Optional, when the user wants to know *what* the competition is doing well:\n   `socialinsider_get_top_posts` with `limit: 3` for the leaders only.\n\n## Output\n\nOne table per platform, sorted by engagement rate (not by raw engagement — raw totals just\nrank by follower count):\n\n| Profile | Followers | Follower Δ | Posts | Total eng. | Eng./post | Eng. rate |\n\nThen:\n\n- **Ranking and gap** — where the user's brand sits, and the size of the gap to the leader in\n  percentage terms.\n- **Cadence versus efficiency** — separate the brands that win by posting more from the brands\n  that win per post. These need opposite responses.\n- **Format edge** — which post types the leaders use that the user's brand under-uses.\n- **Two moves** — the highest-leverage changes, each grounded in a number from the table.\n\nAlways normalise by follower count before declaring a winner, and say so. If a competitor's\nengagement rate is inflated by a single outlier post, name that post rather than the average.\n\nIf the user wants an untracked competitor added, state the exact profile URL, run\n`socialinsider_profile_search` to verify it, present what will be created, and wait for explicit\nconfirmation before calling `socialinsider_add_profile` — it consumes their profile limit.\n"
}