Generate image assets through iPolloWork's image service, whether Image Studio is open or closed.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Image generation
Use this Skill for a requested new image or a missing supporting image identified while authoring a PPT, website or video. Image Studio does not need to be open. Plan assets during initial creation/full redesign; preserve narrow edit scopes and explicit no-image requests. Reuse suitable assets first; visual clarity and context are valid reasons to generate, not only absolute necessity. Assess the visual purpose, existing assets and best medium internally; no separate assessment report is required. Keep diagrams editable, treat pure decoration as optional, and never present generated illustrative scenes as real evidence.
1. Preserve the user's subject, composition, text, brand, and format requirements.
…
The line at the top of this page pins the label git:20260923.0e1c557, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (3658 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
devin-axis/ipollowork · 7,331 stars · license a license file GitHub does not identify · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_p3okbjwt2nh5osun
GET https://markdownregistry.com/api/v1/resolve?ref=devin-axis/ipollowork/image-generation
GET https://markdownregistry.com/api/v1/blob/3db9ab9d629b60c148827c2ba7364854f93c68a9a2ce319d1efce71bd05081cb
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
devin-axis/ipollowork · .agents/skills/hyperframes-animation/SKILL.md · Create deterministic animation and transitions for the active iPollo Video project.
devin-axis/ipollowork · .agents/skills/hyperframes-cli/SKILL.md · Inspect, validate, preview, and render the active iPollo Video project with its bundled HyperFrames CLI.
devin-axis/ipollowork · .agents/skills/hyperframes-core/SKILL.md · Apply the core composition, timing, media, and determinism contract used by iPollo Video.
devin-axis/ipollowork · .agents/skills/hyperframes-creative/SKILL.md · Plan visual direction, typography, pacing, audio, and composition for iPollo Video projects.
devin-axis/ipollowork · .agents/skills/hyperframes-registry/SKILL.md · Reuse approved HyperFrames blocks and components inside the active iPollo Video project.
devin-axis/ipollowork · .agents/skills/hyperframes/SKILL.md · Route video creation and editing through the active iPollo Video project and its built-in HyperFrames runtime.
devin-axis/ipollowork · .agents/skills/image-editing/SKILL.md · Edit an image from the active iPolloWork Image Studio selection or mask without overwriting the source image.
devin-axis/ipollowork · .agents/skills/ipollowork-design-editorial/SKILL.md · Create or edit articles and reports in the current iPolloWork Design session.
devin-axis/ipollowork · .agents/skills/ipollowork-design-graphics/SKILL.md · Create or edit posters and social card series in the current iPolloWork Design session.
devin-axis/ipollowork · .agents/skills/ipollowork-design-web/SKILL.md · Create or edit websites and application interfaces in the current iPolloWork Design session.
bytedance/deer-flow · skills/public/image-generation/SKILL.md · Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes…
letta-ai/letta-code · src/skills/builtin/image-generation/SKILL.md · Generate images from text prompts (and optionally edit/remix input images). Use when the user asks to create, generate…
shinpr/mcp-image · skills/image-generation/SKILL.md · Writes prompts that make image models produce the image the user means. Use when generating or editing any image…
hyperfx-ai/marketing-skills · skills/image-generation/SKILL.md · Generate images through the Hyper MCP with the unified `images_generate` tool — text-to-image, image-to-image, and…
guinacio/claude-image-gen · skills/image-generation/SKILL.md · Generates professional AI images using Google Gemini. ALWAYS invoke this skill when building websites, landing pages…
jkitchin/knowhow · skills/creative/image-generation/SKILL.md · AI-powered image generation and editing using Google Gemini, Google Imagen, and OpenAI models.
Generate images from…
postplusai/postplus-skills · skills/10-routing/image-generation/SKILL.md · Plan image creation or edits from prompts, products, or references. Resolve task type, model, and reference rules…
event4u-app/agent-config · src/skills/image-generation/SKILL.md · Generate an image from a brief — provider-agnostic blueprint then provider-specific translation, with ref-image/seed…
