video-analysis
Analyze local or downloaded social video files with the official Gemini API, especially for TikTok/Reels shot beats, timelines, voiceover or on-screen text capture, creative strategy, and natural Markdown outputs. Use this when you need video-level analysis beyond metadata, including uploading video files, prompting gemini-3.5-flash, and linking results back to source metadata.
What this skill does
# Video Analysis ## Use When - The user provides a local video file or video URL and asks to watch, inspect, break down, deconstruct, analyze hooks, understand shots, capture spoken lines, or explain why a video works. - Use this for video-level evidence beyond metadata. Do not answer actual video-understanding requests from transcript guesses or general marketing knowledge. ## 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 - Default model is `gemini-3.5-flash` through released model key `gemini-video-analysis`. - Supported local formats are `.mp4`, `.m4v`, `.mov`, and `.webm`. - Local videos are uploaded through the hosted `file_reference` path: signed upload URL, local byte upload, then Gemini `file_reference`. - The runner does not claim inline video bytes, compression, segmentation, resumable upload, or file URI reuse. If signed upload or `file_reference` analysis fails, stop on that error. ## Source And Path - A direct local file can be analyzed immediately. For a URL, first download or recover the local video, then build a download report. - Preserve `sourceId`, `sourceUrl`, `videoFilePath`, `sourceMetadataPath` or dataset path, model, prompt version, and source basis so results can be joined back to source metadata. - Keep downloaded videos when they are expensive to source. Keep analysis Markdown files and manifests under a stable workspace path. ## Analysis Scope - The default analysis is a single output per source video. - It covers practical short-form structure such as hook, pacing, shot beats, VO/on-screen text, product timing, and creative strategy. - It also asks for Visual & Brand Signals when visible: genre/mood, color palette, lighting, camera language, editing rhythm, brand feeling, and best-fit creative use cases. ## Output And Handoff - The runner writes one natural Markdown analysis file per source video plus `_batch-summary.json`. The analysis should cover useful video evidence such as shot beats, timeline, VO/on-screen text, reusable content structure, and creative strategy when those are relevant. - Provider text is normalized before writing: Markdown is preserved, Markdown wrapped in JSON is extracted, and structured JSON is rendered as readable Markdown. - Results should stay grounded in observable video evidence. Database fields, catalog frontmatter, or search indexes belong to a separate ingestion step, not to the general video-analysis boundary. ## Public Command Boundary - 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. - Use `postplus media schema --json` only when constructing or repairing an unknown request shape. - If the CLI returns a quote-confirmation challenge, run `postplus quote confirm --json --challenge-file <challenge.json>` and retry with the returned token. - Choose the smallest matching command from the user input and run it directly. - Readiness diagnostics: `postplus doctor --skill video-analysis`. If the runner fails, report the exact script error and stop. Do not bypass the failure by answering from metadata, base64-inlining video, readiness probing, or unowned fallbacks.
Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".