Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
yacey avatar

Agnes Ai Generation

  • 2k installs
  • 376 repo stars
  • Updated June 21, 2026
  • yacey/agnes-ai-generation-skill

Skill that calls Agnes AI text, image, and video generation models via authenticated API endpoints, returning generated content URLs and streaming responses.

About

Agnes AI Generation skill wraps the Agnes / Sapiens AI generation APIs at apihub.agnes-ai.com, enabling developers to generate and edit text, images, and videos programmatically. It supports text completions with streaming, text-to-image and image-to-image synthesis using agnes-image-2.1-flash, and asynchronous text-to-video, image-to-video, and keyframe animation via agnes-video-v2.0. The Python CLI validates parameters before API calls, handles async video polling, and normalizes streaming responses. Best for teams building AI-driven content workflows, image generation pipelines, and video synthesis applications. Requires an API key and supports smoke-test verification across all modalities.

  • Multi-modal generation: text, image (text-to-image, image-to-image), and video (text-to-video, image-to-video, keyframes
  • Streaming text responses with normalized content aggregation and raw prefix inspection
  • Asynchronous video task creation and polling-based retrieval with seed reproducibility
  • Built-in Python CLI (agnes_api.py) with parameter validation, smoke-test suite, and error reporting
  • Non-English prompt translation to fluent English for stable video generation output

Agnes Ai Generation by the numbers

  • 2,005 all-time installs (skills.sh)
  • +79 installs in the week ending Aug 4, 2026 (Skillselion tracking)
  • Ranked #149 of 1,335 Generative Media skills by installs in the Skillselion catalog
  • Security screen: MEDIUM risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/yacey/agnes-ai-generation-skill --skill agnes-ai-generation

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs2k
repo stars376
Security audit2 / 3 scanners passed
Last updatedJune 21, 2026
Repositoryyacey/agnes-ai-generation-skill

What it does

Generate text, images, and videos via Agnes AI APIs for content creation and media synthesis

Who is it for?

Teams building AI-driven content platforms, generative media workflows, multi-modal synthesis, and prompt-driven creative automation.

Skip if: Real-time synchronous video generation, multi-turn autonomous agent loops (function calling not reliable), or applications requiring offline inference.

When should I use this skill?

User requests text generation, image creation/editing, video synthesis, or Agnes model testing; when apihub.agnes-ai.com APIs must be called; when streaming output or async polling is needed.

What you get

Developers call agnes-ai-generation skill to create text, images, and videos at scale using fluent prompts, handle async video tasks, and inspect streaming output.

  • Generated images
  • Generated videos
  • API integration scripts

Files

SKILL.mdMarkdownGitHub ↗

Agnes AI Generation

Use this skill to call Agnes text, image, and video generation APIs through https://apihub.agnes-ai.com.

Quick Start

1. Read references/api.md when endpoint details, parameters, or response fields are needed. 2. Use scripts/agnes_api.py for real API calls instead of rewriting curl by hand. 3. Require an API key in AGNES_API_KEY, AGNES_API_TOKEN, or APIHUB_AGNES_API_KEY. Never print the key. 4. For light live verification, run smoke-test; it avoids video creation by default. Add --include-image-edit for image-to-image, and add --video-case <case> explicitly for video modes. Treat the skill as fully tested only when basic text, text streaming, text tool calling, text-to-image, image-to-image, text-to-video, image-to-video, multi-image video, keyframe video, and video retrieval return successful responses.

Commands

Text generation:

python scripts/agnes_api.py text --prompt "Write a concise product tagline for an AI assistant."

Streaming text:

python scripts/agnes_api.py text --prompt "Write a short product intro." --stream

Streaming output is normalized and includes aggregated content, events, done, and a short raw_prefix.

Image generation:

python scripts/agnes_api.py image --prompt "A luminous floating city above a misty canyon at sunrise, cinematic realism" --size 1024x768

Image-to-image:

python scripts/agnes_api.py image --prompt "Turn the scene into a rainy cyberpunk night while preserving composition" --image https://example.com/input.png --size 1024x768

Text-to-video with polling:

python scripts/agnes_api.py video --prompt "A cinematic shot of a cat walking on the beach at sunset" --poll

Image-to-video:

python scripts/agnes_api.py video --prompt "Animate subtle camera movement and natural lighting" --image https://example.com/image.png --poll

Keyframe / multi-image video:

python scripts/agnes_api.py video --prompt "Create a smooth cinematic transition between the two keyframes" --image https://example.com/a.png --image https://example.com/b.png --mode keyframes --poll

Retrieve a video task:

python scripts/agnes_api.py video-get video_123456

Light live smoke test:

python scripts/agnes_api.py smoke-test

Image edit smoke test:

python scripts/agnes_api.py smoke-test --include-image-edit

Single video smoke test:

python scripts/agnes_api.py smoke-test --video-case text-to-video

Workflow

  • Prefer agnes-2.0-flash for text chat/completions.
  • Do not use Agnes Responses API multi-turn function calling for autonomous tool workflows. Live testing showed the provider can return function_call with overall status=completed, and submitting function_call_output with previous_response_id may fail. Use this skill's chat completions path for text generation and treat tool-calling as best-effort request-shape compatibility only.
  • Prefer agnes-image-2.1-flash for text-to-image, image-to-image, and high-information-density image generation. High-density generation is prompt-driven; include subject hierarchy, environment, secondary details, lighting, composition, and quality requirements.
  • Prefer agnes-video-v2.0 for text-to-video, image-to-video, multi-image video, keyframe animation, prompt-based motion and scene control, cinematic output, asynchronous task creation, polling-based result retrieval, and seed-based reproducibility.
  • For image and video generation, convert any non-English user prompt to a fluent English generation prompt before calling the image/video API. English prompts are more stable for Agnes video generation. Preserve concrete visual details, style, lighting, composition, motion, camera instructions, and constraints during translation.
  • For videos, remember the API is asynchronous: create a task first, then poll or retrieve by video_id when the create response includes it. The script falls back to legacy task_id lookup only when video_id is absent.
  • The script validates image sizes, video frame counts, frame rates, and dimensions before sending requests. num_frames must be 8n + 1 and <= 441; 81 or 121 are good short values.
  • The video command defaults to num_frames=121 and frame_rate=24 for more stable generation. Video smoke tests default to num_frames=81 and frame_rate=24.
  • Warn the user before costly or long-running live video generation unless they explicitly asked to test or generate video.
  • Test video capabilities one at a time with smoke-test --video-case <case> to avoid creating many tasks at once. Supported cases are text-to-video, image-to-video, multi-image, and keyframes.

Current Validation Notes

  • Confirmed locally: skill metadata validation and Python syntax.
  • Confirmed by live API: basic text, streaming text, tool-calling request shape, text-to-image, image-to-image, high-information-density text-to-image, Chinese prompt translation for image/video, completed text-to-video URL retrieval, and completed image-to-video URL retrieval.
  • Caveat: Agnes may accept tool-calling request parameters without consistently returning tool_calls; use smoke-test --strict-tools when strict tool-call validation is required.
  • Caveat: Agnes Responses API multi-turn function calling is not reliable for agent tool loops; do not rely on it for Codex/Claude-style automatic tool continuation.
  • Supported by the script and smoke-test selector, but not re-run end-to-end in the latest pass: multi-image video and keyframe animation.
  • Not yet confirmed end-to-end: completed URL retrieval for every multi-image video and keyframe animation task. A previous text-to-video task returned a provider-side division by zero error, so keep video retries visible and report provider errors clearly.

Output Handling

  • Return generated image/video URLs directly by default. Do not download, save, open, or inspect generated media unless the user explicitly asks for a local file or visual inspection.
  • For image responses, expect URL-style results when extra_body.response_format is url.
  • For video responses, extract URLs from video_url, url, or remixed_from_video_id when status is completed.
  • For video retrieval, prefer GET /agnesapi?video_id=...&model_name=agnes-video-v2.0; legacy GET /v1/videos/{task_id} remains a fallback.
  • If a request fails, report HTTP status and provider error body without exposing the API key.

Related skills

How it compares

Pick Agnes AI Generation for Agnes-specific API integration rather than local markitdown document conversion or Spring Boot codegen skills.

FAQ

What APIs does Agnes AI Generation call?

Agnes AI Generation calls Agnes and Sapiens text, image, and video endpoints at apihub.agnes-ai.com, including Agnes Image, Agnes Video, and Agnes 2.0 Flash, via scripts/agnes_api.py.

Does Agnes AI Generation require an API key?

Agnes AI Generation requires an API key for apihub.agnes-ai.com calls, using scripts/agnes_api.py and references/api.md to configure endpoints, parameters, and response fields.

Is Agnes Ai Generation safe to install?

skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Generative Mediallmautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.