← ClaudeAtlas

instagram-researchlisted

Researches other Instagram accounts and hashtags through the user's own web session (no Apify) to build a swipe file of outlier posts (posts beating their own account's median by 3x or more), extract the hook formulas and formats behind them, and turn that into content ideas. This skill should be used when the user asks to "research competitors on Instagram", "what's working in my niche", "find viral reels about X", "build a swipe file", "reverse engineer this account", "analyze these creators", "check the
proyecto26/instagram-ai-plugin · ★ 1 · Data & Documents · score 72
Install: claude install-skill proyecto26/instagram-ai-plugin
# Instagram research Find posts that beat their *own* account's normal performance, not posts that are merely big. A 3x post from a 5k account teaches more than a 1x post from a 5M account. ## Limits (account safety) - At most 12 accounts and 50 posts per account per run. The CLI enforces both and spaces requests at least 1.5 s apart. - One research run per session is plenty. On `rate_limited` or `checkpoint`, stop, report the hint, and do not continue with the remaining accounts. - Research is read-only: never follow, like or comment on researched accounts. ## 1. Pick the accounts Ask for 5 to 12 accounts in the same niche, ideally with similar or slightly larger audiences. If the user has none, find candidates (run from `../instagram`): ```bash npx -y bun scripts/main.ts search "<niche keyword>" --json npx -y bun scripts/main.ts hashtag <tag> --limit 24 --json # top and recent posts for a tag ``` Confirm the list with the user before pulling posts. ## 2. Build the swipe file ```bash npx -y bun scripts/main.ts swipe user1,user2,user3 --limit 24 --min 3 --json > "<project-dir>/instagram-swipe.json" ``` The output has `outliers[]` (username, url, format, multiple, engagement, and hook, which is the caption's first line), posts read per account, and `skipped` (private or missing accounts). An account with fewer than 6 posts read is too thin to judge. Say so. ## 3. Reverse-engineer the winners For each outlier, highest multiple first: 1. Classify the hook ag