← DoublespeedCONTENT HISTORY

Update to Doublespeed

Snapshot Oct 6, 2026 · 00:02 UTC · version 1.0.4

Collection source: downloaded plugin package.

WHAT CHANGED · RULE-BASED ANALYSIS

First saved snapshot

No earlier snapshot is available to establish a change.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Analyze posting performance through the doublespeed MCP and turn it into decisions: exact aggregates, per-account and per-format breakdowns, winner/loser calls, and a written report. Use when the user asks what's working, for analytics, a performance report, account health, or what to post more of.\n",
  "included_files": [],
  "name": "performance-report",
  "skill_md_contents": "---\nname: performance-report\ndescription: |\n  Analyze posting performance through the doublespeed MCP and turn it into decisions: exact aggregates, per-account and per-format breakdowns, winner/loser calls, and a written report. Use when the user asks what's working, for analytics, a performance report, account health, or what to post more of.\n---\n\n# Performance Report via doublespeed\n\n## Setup\n\n1. `whoami` to confirm the active product; `list_products` + `set_product` if wrong or missing. Never switch products on your own initiative afterward.\n\n## Gather\n\n1. **Aggregates first.** `get_post_metrics` returns exact totals, averages, medians, maximums, engagement, and per-account performance across the full filtered post set in one call - use it for every numeric claim instead of paginating and summing yourself. Filter by date range to compare periods.\n2. **Ranked posts.** `list_posts` sorted by `viewsCount` (or date) for the top and bottom performers; pull `include_scene_data` only for the handful you'll dissect.\n3. **Per-account drilldown.** `list_account_posts` for one account's history; `get_account` / `list_accounts` for status (good, warming, burned) and profile setup.\n\n## Analyze\n\n- Judge on **engagement rate** (likes/saves/comments relative to views), not raw views: distribution is noisy and one lucky post is not a format.\n- Cut by format (slideshow vs video), hook style, account, and posting time. A format needs several reps before the algorithm catches - do not kill it on one flop.\n- Dissect the top 3-5 winners' actual structure (hook wording, slide order, audio) - that nuance is the actionable part, not the numbers.\n- Note account health: burned or inactive accounts drag averages; flag them rather than blending them in.\n\n## Report\n\n1. Write a short report: what won and why (with post links), what lost, per-account calls (double down / fix profile / rest), and 3-5 concrete next posts.\n2. Persist findings into the strategy and feedback files described in `doublespeed://skills/content-creator` so the next session builds on them.\n3. Turn \"more of what works\" into action with `doublespeed://skills/content-remixer`.\n\n## Notes\n\n- Repeat post and review links in your reply as short descriptive markdown links.\n- Numbers come from `get_post_metrics`; never estimate from a sampled page of posts.\n"
}

SHA-256 of public snapshot: d2b4fc4980c695e2e47b5b3c29fca5694d6ddce9b792e6f7aab1ea75161a8f0e