muapi-instagram-post
Create a polished, on-brand Instagram post — square or portrait hero image with matching caption and hashtags.
Paste into Claude, ChatGPT or Cursor.
Read the source58 lines
| 1 | |
| 2 | slug muapi-instagram-post |
| 3 | name muapi-instagram-post |
| 4 | version "1.0.0" |
| 5 | description Create a polished, on-brand Instagram post — square or portrait hero image with matching caption and hashtags. |
| 6 | acceptLicenseTerms true |
| 7 | |
| 8 | |
| 9 | |
| 10 | # Instagram Post |
| 11 | |
| 12 | **Create a polished, on-brand Instagram post — square or portrait hero image with matching caption and hashtags.** |
| 13 | |
| 14 | ## Inputs |
| 15 | |
| 16 | | Name | Type | Required | Default | Description | |
| 17 | |:---|:---|:---|:---|:---| |
| 18 | | `brief` | text | yes | — | What the post is about (e.g. "summer coffee launch at our café, warm golden vibes"). | |
| 19 | | `brand_style` | text | no | modern, vibrant, clean typography, lifestyle photography aesthetic | Brand personality and visual style tags. | |
| 20 | | `format` | text | no | 1:1 | Post format — "1:1" for feed square, "4:5" for portrait feed, "9:16" for Reels. | |
| 21 | |
| 22 | |
| 23 | ## Steps |
| 24 | |
| 25 | This skill produces one polished Instagram-ready visual + caption. Use the plan if generating more than one variant. |
| 26 | |
| 27 | ### Phase A — Generate the hero image |
| 28 | |
| 29 | Write a detailed, atmosphere-rich image prompt based on `{{brief}}` and `{{brand_style}}`: |
| 30 | Include lighting direction, color palette, mood, subject placement, and lens feel. |
| 31 | Optimize for Instagram aesthetics: clean, punchy, single focal point. |
| 32 | Append style tags: `{{brand_style}}, social media photography, highly detailed`. |
| 33 | Call `muapi image generate` (model=nano-banana-2, aspect_ratio=`{{format}}`). |
| 34 | If the user provided a product or subject image in the session, prefer `muapi image edit` instead to maintain visual consistency. |
| 35 | |
| 36 | ### Phase B — Caption & Hashtags |
| 37 | |
| 38 | After the image is generated, compose and return: |
| 39 | **Caption**: 2–4 lines. Hook line first (punchy, curiosity-driving), then brand message, then CTA. |
| 40 | **Hashtags**: 15–20 targeted hashtags (mix of niche, mid-tier, and broad). Format as a separate block. |
| 41 | |
| 42 | ## Notes |
| 43 | Prioritize scroll-stopping first impressions — the image must visually communicate the brief within 2 seconds. |
| 44 | If `format` is `9:16` (Reels cover), note that text overlays are common; include a suggestion for on-screen text placement. |
| 45 | Do NOT generate multiple variants unless the user explicitly asks. |
| 46 | |
| 47 | ## Trigger Keywords |
| 48 | |
| 49 | `instagram post`, `ig post`, `instagram`, `feed post`, `instagram creative` |
| 50 | |
| 51 | |
| 52 | |
| 53 | |
| 54 | ## Notes for the Executing Agent |
| 55 | |
| 56 | This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call `muapi` CLI commands. Use `muapi auth configure` first if `MUAPI_API_KEY` is unset. |
| 57 | For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with `muapi predict wait <request_id>`. |
| 58 | Substitute `{{input_name}}` placeholders with the user's actual inputs before issuing each call. |