Menü
Generate AI image prompts for blog post hero images with a consistent TechHive Labs visual style
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Run the full TechHive Labs blog post cycle: source brief → voice-matched draft → data charts → hero image → SEO-audited publish to production → distribution variants (LinkedIn, dev.to, X) with a branded stats card. Use whenever Tony wants to write and publish a new blog post, turn a brief/brain-dump into a post, "do the full cycle", "post like last time", cross-post an existing article, or produce any distribution deliverable (LinkedIn post, dev.to variant, tweet, stats image). Also consult it when doing just ONE phase — it maps each phase to the specialist skill and records the conventions and gotchas learned from real cycles.
Browser-test this site (techhivelabs.net portfolio) with playwright-cli — verify pages render, MDC components behave (modals, players), and interactions work in the real app. Use whenever a change needs visual or interactive verification in the browser: new/changed components, blog post layout checks, screenshot requests, or E2E flows like the contact form.
Build a branded LinkedIn document carousel (a multi-slide PDF) from a blog post, announcement, or set of findings, styled in the TechHive Labs identity and exported print-ready. Use this whenever Tony wants a "carousel", "document post", "PDF slides", "swipeable slides", "slide deck for LinkedIn", or wants to turn a blog post / set of stats into something visual to drive LinkedIn reach — even if he doesn't say the word "carousel". The output is a 4:5 (1080x1350) PDF rendered from an HTML template via headless Chrome.
Complete workflow for publishing blog posts — image processing, SEO audit, schema verification, and Vercel deployment
Write or rewrite blog posts matching Tony's personal writing voice -- self-deprecating, conversational, narrative-driven technical storytelling
General-purpose X/Twitter research agent. Searches X for real-time perspectives, dev discussions, product feedback, cultural takes, breaking news, and expert opinions. Works like a web research agent but uses X as the source. Use when: (1) user says "x research", "search x for", "search twitter for", "what are people saying about", "what's twitter saying", "check x for", "x search", "/x-research", (2) user is working on something where recent X discourse would provide useful context (new library releases, API changes, product launches, cultural events, industry drama), (3) user wants to find what devs/experts/community thinks about a topic. NOT for: posting tweets or account management. Note: currently uses recent search (last 7 days). Full-archive search is available on the same pay-per-use X API plan but not yet implemented in this skill.
| name | blog-image-generator |
| description | Generate AI image prompts for blog post hero images with a consistent TechHive Labs visual style |
| user_invocable | true |
Generate image prompts for the user's blog posts that maintain a consistent visual identity across the TechHive Labs portfolio site.
Read the blog post. If the user provides a slug or filename, read the markdown file from content/blog/. If no specific post is given, ask which post they need an image for.
Identify the core themes. Extract the 2-3 central topics or narratives from the post (e.g., "AI coding assistant + roguelike game dev + hitting limits").
Compose prompts using the base prompt. Always start with this exact base prompt, then append a scene description:
Base prompt:
Isometric low-poly digital illustration, dark matte background with soft green (#39a10e) accent lighting, clean geometric shapes, subtle glowing circuit-board traces in the background, tech-forward minimal aesthetic, no text, no people, sharp edges with soft shadows, 16:9 aspect ratio
Generate exactly 3 variant prompts. Each variant should:
Present the output as:
For a post about hitting deployment walls with an AI app:
Variant 2: Isometric low-poly digital illustration, dark matte background with soft green (#39a10e) accent lighting, clean geometric shapes, subtle glowing circuit-board traces in the background, tech-forward minimal aesthetic, no text, no people, sharp edges with soft shadows, 16:9 aspect ratio, a split architecture diagram — a sleek glowing edge node on one side connected by a luminous bridge to a heavy industrial server on the other, data packets flowing across the bridge
