
Slideshow Producer
Produce TikTok or Instagram carousel slideshows end-to-end from slide manifests, GPT Image generation, optional localhost review, and text-overlay exports.
Install
npx skills add https://github.com/postplusai/postplus-skills --skill slideshow-producerWhat is this skill?
- End-to-end TikTok slideshow and Instagram carousel production with manifest JSON
- Default models: image-gpt-image-2-text and image-gpt-image-2-edit with reference slides
- Optional localhost review GUI for slide approval before batch generation
- Batch GPT Image 2 generation plus text overlay compositing to export-ready sequences
- Explicit boundary: does not write hook variants from scratch or replace final creative QA
Adoption & trust: 1 installs on skills.sh; 8 GitHub stars; 1/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
Recommended Skills
Journey fit
Grow/Content is the canonical shelf because the deliverable is social slideshow assets ready for publishing, not market validation or core product engineering. Content fits vibe-driven prompts, batch image generation, manifest JSON, and compositing called out for TikTok 9:16 and Instagram 4:5 carousels.
Common Questions / FAQ
Is Slideshow Producer safe to install?
skills.sh reports 1 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.
SKILL.md
READMESKILL.md - Slideshow Producer
# Slideshow Producer ## Use When - The user wants TikTok slideshow or Instagram carousel production from vibe, local images, slide prompts, reviewable manifest JSON, generated images, and final text overlays. - Use after script/hook strategy is clear enough to plan slides. This skill owns slide manifest, preview/review, generation orchestration, and compositing. ## Do Not Use When - The task belongs to ideation, QA, or another released skill listed in the handoff section. - Required inputs are missing and guessing would change the result. ## Execution Boundary - Do not write hook variants from scratch, call image providers directly, create persona packs, or replace final creative QA. - Default image models are `image-gpt-image-2-text` for slides without references and `image-gpt-image-2-edit` for slides with references. - Default quality is `medium`, resolution `1k`, output PNG. Default platform is TikTok `9:16`; Instagram carousel uses `4:5` unless the user asks otherwise. ## Manifest And Routing - The slide manifest is the routing source of truth. - `imageSource: "local"` uses `localImagePath` as the final image and must not call generation. - `imageSource: "generate"` with no reference paths/URLs must use `image-gpt-image-2-text`. - `imageSource: "generate"` with any reference path/URL must use `image-gpt-image-2-edit`. - Never send reference-backed slides through text-to-image. Fix the manifest before generation if routing is inconsistent. ## Source And Prompt - Ask for platform, slideshow count, vibe, source basis, output folder, and any local images. Classify local images as final slide images or generation references. - Prompts should be core scene plus vibe in two or three sentences. Add concrete product, environment, emotion, and prop details when they matter; avoid long negative-constraint walls. - Save a local manifest before generation. For three or more slideshows, split manifest drafting across parallel sub-agents, then the main agent reviews the collected manifests. ## Review And Handoff - Before generation, ask for explicit approval: number of slides, model, quality, resolution, and counts of text-to-image versus reference edits. - After compositing, hand off final image paths, updated manifest, and any `creative-qa` or publishing. ## Stop Conditions - Stop when required user intent, source evidence, or owned input artifacts are missing and guessing would change the result. - If an owned CLI or script command fails, report the exact error and stop. Do not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools. ## Public Command Boundary - Choose the smallest matching command or workflow from the user input and run it directly. - Readiness diagnostics: `postplus doctor --skill slideshow-producer`. - If an owned CLI or script command fails, report the exact error and stop. Do not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools. - Use `postplus media schema --json` only when constructing or repairing an unknown request shape. - Hosted media capability: `postplus media capability --request <hosted-capability-request.json> --output <result.json>`. - Use the capability request shape required by the selected workflow; do not call provider APIs directly. - If the CLI returns a quote-confirmation challenge, run `p