michailbul/laniameda-instagram-carousel-extract
skills/marketing/laniameda-instagram-carousel-extract/SKILL.md
Extract content from Instagram carousel posts (image slides) using browser-use-cloud with visual reading. Read text overlaid on slides, extract prompts, workflows, checklists — and save to KB. Not for reels (video) — use laniameda-instagram-reel-digest for those. Keywords: instagram carousel, extract slides, read carousel, save carousel.
testing
Updated Apr 19, 2026
$ install --global
skillsauthnpx skillsauth add michailbul/laniameda-skills laniameda-instagram-carousel-extractInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 19, 2026, 4:13 AM5.2s1 file scanned
SKILL.md
- name:
- laniameda-instagram-carousel-extract
- description:
- >
- Keywords:
- instagram carousel, extract slides, read carousel, save carousel.
- version:
- 1.0.0
- status:
- active
- created:
- 2026-03-25
- updated:
- 2026-03-25
- owner:
- Lani
- agents:
- [Lani, Meda]
- departments:
- [Marketing, Operations]
- purposes:
- [Ingestion, Research, Knowledge Base]
- depends_on:
- [browser-use-cloud, supadata]
- replaces:
- [instagram-extract]
laniameda-instagram-carousel-extract
Purpose: Extract content from Instagram carousel posts (image slides). Read text overlaid on slides, extract prompts, workflows, checklists, or frameworks — and save to KB.
Source: Instagram carousels (multi-image posts, slides with text).
Not for: Instagram reels (video) → use laniameda-instagram-reel-digest.
Triggers
- Instagram carousel post URL pasted
- "extract this carousel"
- "what's in these slides"
- "save this carousel"
- "get the prompts from this post"
- "extract the workflow from this"
Workflow
Step 1 — Check caption via Supadata metadata first (fast)
curl -s "https://api.supadata.ai/v1/metadata?url=<POST_URL>" \
-H "x-api-key: $SUPADATA_API_KEY"
Caption often contains the full text of the slides. If caption is complete → no need for browser.
Step 2 — If caption is truncated or slides have visual text
Use browser-use-cloud to scroll through slides:
Task prompt template:
Go to [URL]. This is an Instagram carousel. Scroll through EVERY slide one by one.
For EACH slide: VISUALLY READ any text shown in the image and transcribe it exactly.
These may contain prompts, steps, frameworks, or tips overlaid on the image.
Also extract the full caption and any links mentioned.
Use bu-mini model. Set maxCostUsd: 0.50. Use BROWSER_USE_PROFILE_ID if available.
Step 3 — Classify content
Decide what this is:
- A prompt → save to
laniameda-kbwith correct pillar - A workflow/tutorial → save to
content-kb/sources/instagram/YYYY-MM-DD-<slug>/ - A framework/checklist → save as notes + optionally draft a skill
Step 4 — Deliver
[Author] — Instagram Carousel ([X] slides)
What it is: [one sentence]
Key content:
• [slide 1 summary or exact text]
• [slide 2 summary or exact text]
• ...
Worth saving as: [prompt / workflow / reference / skill]
Then save based on Michael's direction or your judgment.
Hard Rules
- Always check caption via Supadata first — saves a browser call.
- Tell the browser agent to VISUALLY READ text in images — not just extract HTML alt text.
- If slides are all images with no text → report that and save image URLs for reference.
- Classify and route to the right save destination, don't just dump raw text.
Related Skills
michailbul/seedance-higgsfield
development
VerifiedTrustedCommunity
Seedance 2.0 video prompt director. Converts plain-text scene descriptions into production-ready bilingual EN+ZH video prompts optimized for the Seedance 2.0 video generator. Handles all Seedance work — action (combat, pursuit, stunts), general (landscapes, journeys, atmosphere), dialogue (confrontations, negotiations, interrogations), and non-narrative commercial work (ad spots, music videos, fashion films, automotive inserts, product shots, pet/character demos, cutaway montages, social reels for TikTok / Reels / YouTube Shorts). Use whenever the user wants to create a Seedance video prompt, mentions Seedance, or describes a cinematic scene for video generation. For NARRATIVE screenplay-integrated work, use seedance-screenwriter instead.
1SKILL.mdUpdated May 9, 2026
michailbul/seedance-screenwriter
development
VerifiedTrustedCommunity
Write Seedance 2.0 prompts in screenplay format for narrative storytelling — when the prompts will be cut into a film, short, or scene. Use whenever you're generating shots that will be edited into a continuous story with dialogue, character beats, scene continuity, or coverage. Pairs with the screenwriter skill — read the scene's screenplay first (or the project's `scene.md` if it exists), then translate each shot into a Seedance prompt that reads as a screenplay page, not as an engineering spec.
SKILL.mdUpdated May 4, 2026
michailbul/screenwriter
documentation
VerifiedTrustedCommunity
Скилл-инструмент для сценариста полнометражного фильма или сериала. Используй всегда, когда пользователь хочет писать сценарий, поэпизодник, разрабатывать сцены, бит-шит, диалоги, делать ревизии, считать экранное время, резать длину, работать с персонажами или мифологией истории. Скилл работает на основе методологий Макки, Кэмпбелла и Аристотеля, выдаёт Hollywood-формат .docx, поддерживает билингвальные сценарии (диалог на одном языке + перевод в скобках под ним), и помогает аудитировать структуру по причинности и движению ценности. Скилл не привязан к конкретной истории — пользователь приносит свою.
SKILL.mdUpdated May 3, 2026
michailbul/car-angle-extractor
development
VerifiedTrustedCommunity
Extract shot composition DNA from any car photograph into structured JSON — camera angle, lens, framing, lighting — stripped of car-specific details. Then reuse extracted angles with any car identity to generate new images at scale. Use when: extracting angles from reference photos, building a shot library, batch-analyzing car photography, replicating a great angle with a different car, running extraction pipelines in Freepik or Flora. Triggers: "extract this angle", "steal this composition", "shot DNA", "analyze this car photo", "replicate this shot with my car", "batch extract angles", "car photography analysis", "angle extraction", "build a shot library".
SKILL.mdUpdated Apr 22, 2026