Runninghub
HM-RunningHub/OpenClaw_RH_Skills
Generate images, videos, audio, and 3D models via RunningHub API (420 endpoints) and run any RunningHub AI Application (custom ComfyUI workflow) by webappId.
A skill your agent uses when the user wants to generate a cinematic still image on Higgsfield, asks about shot framing, camera angle, or composition for image prompts, needs a specific shot type…
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-image-shots -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-image-shots --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/higgsfield-image-shots .claude/skills/higgsfield-image-shots && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "higgsfield-image-shots" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-image-shots into .claude/skills/higgsfield-image-shots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-image-shots", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-image-shotsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-image-shots -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-image-shots --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/higgsfield-image-shots .agents/skills/higgsfield-image-shots && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "higgsfield-image-shots" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-image-shots into .agents/skills/higgsfield-image-shots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-image-shots", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-image-shots -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-image-shots --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/higgsfield-image-shots .cursor/skills/higgsfield-image-shots && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "higgsfield-image-shots" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-image-shots into .cursor/skills/higgsfield-image-shots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-image-shots", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git --path skills/higgsfield-image-shots--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-image-shots -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-image-shots --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/higgsfield-image-shots .gemini/skills/higgsfield-image-shots && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "higgsfield-image-shots" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-image-shots into .gemini/skills/higgsfield-image-shots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-image-shots", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-image-shotsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-image-shots -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/higgsfield-image-shots .github/skills/higgsfield-image-shots && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "higgsfield-image-shots" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-image-shots into .github/skills/higgsfield-image-shots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-image-shots", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-image-shots -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install OSideMedia/higgsfield-ai-prompt-skill higgsfield-image-shots --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/higgsfield-image-shots .opencode/skills/higgsfield-image-shots && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "higgsfield-image-shots" agent skill from https://github.com/OSideMedia/higgsfield-ai-prompt-skill/tree/main/skills/higgsfield-image-shots into .opencode/skills/higgsfield-image-shots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "higgsfield-image-shots", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
higgsfield-image-shotsA skill your agent uses when the user wants to generate a cinematic still image on Higgsfield, asks about shot framing, camera angle, or composition for image prompts, needs a specific shot type…
Higgsfield Image Shots is an agent skill from OSideMedia/higgsfield-ai-prompt-skill. Use when the user wants to generate a cinematic still image on Higgsfield, asks about shot framing, camera angle, or composition for image prompts, needs a specific shot type (close-up, wide shot, cowboy shot, etc.), or is working with [img] reference-based image generation. Covers distance & size shots, camera angles, and camera movement keywords optimized for AI image models (Soul 2.0, Nano Banana, Seedream, GPT Image, Flux, etc.).
Its SKILL.md is about 5.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative, covering Image generation, Diffusion and image models and AI video generation. It works with Google Gemini. The repository describes itself as: Claude AI skill for cinematic Higgsfield AI prompts — 32 sub-skills covering Seedance 2.5 (omni-reference, video edit + extend) and 2.0, the Hell Grind feature-film pipeline, an… The licence is MIT.
Read from SKILL.md and the folder at commit 7075497. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
snowFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Higgsfield Image Shots loads about 5.1k tokens when it runs. Until then it costs about 115 tokens; SKILL.md has 1,967 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from OSideMedia/higgsfield-ai-prompt-skill at commit 7075497, republished under its MIT licence (© OSideMedia). 1,967 words, ~5,129 tokens.
.claude/skills/higgsfield-image-shots/SKILL.md (or your agent's skills folder).Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.
[img 1] is the Soul ID / uploaded reference token — replace with a character description or @ Element when no reference is used →This skill covers still image shot composition — framing, angles, and implied camera movement for AI image generation. Use these keywords and patterns when building prompts for any Higgsfield image model.
Key difference from video camera controls: These are composition directives
for a single frame. The [img 1] token references a Soul ID character or
uploaded reference image. Replace it with your character description or @ Element
when no reference image is used.
Every entry has:
Prompt pattern for image generation:
[Shot keyword] of [img 1 or character description] + [pose/action] + [environment detail] + [lighting/atmosphere]These control how much of the subject fills the frame and how much environment is visible. Choose based on whether the image is about the world, the character, or a detail.
AI Prompt Keyword: EWS, Vast, Landscape Definition: The subject is barely visible; emphasizes the vast landscape or location. Purpose: Establish vastness, show isolation, or emphasize scale. Prompt Example:
Extreme wide shot of [img 1] standing alone in a vast, empty frozen tundra.
The subject is small in the distance, surrounded by massive snowy mountains.
Cinematic lightingAI Prompt Keyword: Wide Shot, Full Body Definition: Shows the full subject within their environment. Purpose: Provide context and spatial awareness. Prompt Example:
Wide shot of [img 1] standing full body in a snowstorm. She is wearing fur armor,
boots visible, centered in a snowy forest clearing. Environmental context.AI Prompt Keyword: Full Shot, Framed Definition: Frames the subject from head to toe while filling more of the frame. Purpose: Balance character detail with environment. Prompt Example:
Full body shot of [img 1] from head to toe. She stands confidently in the snow,
holding a weapon at her side. Detailed costume designAI Prompt Keyword: Medium Long Shot Definition: Frames the subject from knees up. Purpose: Natural framing for movement or dialogue. Prompt Example:
Medium long shot of [img 1] framed from the knees up. She is walking through
deep snow, looking towards the horizon. 3/4 angle view.AI Prompt Keyword: Cowboy Shot Definition: Frames subject from mid-thigh up. Purpose: Emphasize posture, readiness, or action. Prompt Example:
Cowboy shot of [img 1] framed from mid-thigh up. Focus on her hands resting
on her belt, confident stance, snowy background with soft bokeh.AI Prompt Keyword: Medium Shot Definition: Frames the subject from the waist up. Purpose: Balanced emotional and physical framing. Prompt Example:
Medium shot of [img 1] from the waist up. She is looking directly at the camera
with a serious expression. Snowflakes falling in the foreground.AI Prompt Keyword: MCU Definition: Frames subject from chest or shoulders up. Purpose: Emotional connection without intensity. Prompt Example:
Medium close-up of [img 1] framed from chest up. Focus on her face and fur collar.
The wind is blowing her braided hair. Intimate and dramaticAI Prompt Keyword: Close-Up Definition: Tight framing on the face or a key detail. Purpose: Highlight emotion or detail. Prompt Example:
Close-up of [img 1], framing only her head and neck. Her piercing eyes looking
into the lens. Frosty breath visible in the cold air.AI Prompt Keyword: ECU Definition: Focuses on a very small detail. Purpose: Heighten tension or intimacy. Prompt Example:
Extreme close-up on the eyes of [img 1]. Macro detail of the iris, snowflakes
caught in her eyelashes, war paint texture. Intense gazeAI Prompt Keyword: Macro Definition: Ultra-close shot showing fine texture. Purpose: Emphasize detail and texture. Prompt Example:
Macro shot of the texture of [img 1]'s fur armor and the frost on her skin.
Microscopic details of snow crystals and leather grain| Shot | Frame content | AI Keyword | Best for |
|---|---|---|---|
| EWS | Subject tiny in vast landscape | EWS, Vast, Landscape | Scale, isolation, world-building |
| Wide / Long | Full body + full environment | Wide Shot, Full Body | Context, establishing |
| Full Shot | Head to toe, subject fills frame | Full Shot, Framed | Costume, character intro |
| Medium Long | Knees up | Medium Long Shot | Movement, dialogue |
| Cowboy | Mid-thigh up | Cowboy Shot | Posture, readiness, action |
| Medium | Waist up | Medium Shot | Balanced emotion + body |
| MCU | Chest/shoulders up | MCU | Connection, intimacy |
| Close-Up | Face | Close-Up | Emotion, expression |
| ECU | Single detail (eyes, hands) | ECU | Tension, intimacy, texture |
| Macro | Ultra-close texture | Macro | Detail, material, surface |
These control the camera's vertical and spatial relationship to the subject. Angle choice dramatically changes the emotional read of an image.
AI Prompt Keyword: Eye-Level Definition: Camera is level with the subject's eyes. Purpose: Neutral, realistic perspective. Prompt Example:
Eye-level shot of [img 1] facing the camera. Neutral perspective, realistic
documentary style portrait in the snow.AI Prompt Keyword: Low Angle Definition: Camera looks up at the subject. Purpose: Convey power or dominance. Prompt Example:
Low angle shot looking up at [img 1]. She towers over the camera, looking powerful
and dominant against a stormy sky.AI Prompt Keyword: High Angle Definition: Camera looks down at the subject. Purpose: Convey vulnerability or insignificance. Prompt Example:
High angle shot looking down at [img 1]. She is looking up towards the camera,
snow falling onto her face. Vulnerable perspective.AI Prompt Keyword: Overhead Definition: Shot from directly above. Purpose: Abstract or strategic perspective. Prompt Example:
Direct overhead bird's eye view of [img 1] standing in the snow. Top-down angle
showing her shadow stretching on the white ground.AI Prompt Keyword: Worm's Eye Definition: Shot from ground level looking straight up. Purpose: Extreme power or surreal scale. Prompt Example:
Worm's eye view from the ground looking up at [img 1]'s boots and legs, with
her face distant in the sky. Ant-man perspectiveAI Prompt Keyword: Dutch Angle, Canted Angle Definition: The camera is tilted sideways (tilted horizon). Purpose: Creates unease, disorientation, or chaos. Prompt Example:
Dutch angle shot of [img 1], tilted horizon line. Disorienting and chaotic
atmosphere, battle ready pose, dynamic compositionAI Prompt Keyword: Over-the-Shoulder, OTS Definition: Looking past one person's shoulder at another. Purpose: Essential for dialogue, grounds the conversation. Prompt Example:
Over-the-shoulder shot looking past a blurry Viking warrior in the foreground,
focusing on [img 1] who is staring back at them.AI Prompt Keyword: POV, First Person Perspective Definition: The camera is the character's eyes. Purpose: Viewer experiences what the character sees, high immersion. Prompt Example:
First person POV shot of someone approaching [img 1]. She is looking directly
at the viewer, hand extended as if greeting the camera.AI Prompt Keyword: Selfie Angle, Arm's Length Definition: High angle, arm's length, facing the subject. Purpose: Common in social media aesthetics, informal, close. Prompt Example:
Handheld selfie angle of [img 1] looking into the lens, arm extended.
Casual vlog style, snowy mountains in the immediate background.AI Prompt Keyword: Ground Level, Surface View Definition: Camera sits directly on the floor/surface, often with shallow depth of field. Purpose: Immersive close-up of the ground or environment. Prompt Example:
Ground level shot, camera resting on the snow. Shallow depth of field with snow
crystals in foreground, [img 1] walking in the background.| Angle | Camera position | AI Keyword | Emotional effect |
|---|---|---|---|
| Eye-Level | Level with eyes | Eye-Level | Neutral, realistic |
| Low Angle | Below, looking up | Low Angle | Power, dominance |
| High Angle | Above, looking down | High Angle | Vulnerability, insignificance |
| Overhead | Directly above | Overhead | Abstract, strategic |
| Worm's Eye | Ground, looking straight up | Worm's Eye | Extreme power, surreal |
| Dutch Angle | Tilted horizon | Dutch Angle, Canted Angle | Unease, chaos, tension |
| OTS | Past shoulder | Over-the-Shoulder, OTS | Dialogue, confrontation |
| POV | Character's eyes | POV, First Person Perspective | Immersion |
| Selfie | Arm's length, high | Selfie Angle, Arm's Length | Social media, casual |
| Ground Level | On the surface | Ground Level, Surface View | Environmental immersion |
For image generation, camera movement keywords create the feeling of motion in a single frame — motion blur, composition that implies movement, or a frozen moment mid-movement.
| Movement | AI Keyword | Definition | Purpose | Prompt Example |
|---|---|---|---|---|
| Static Shot | Static | Camera does not move | Stability and focus | "Static camera shot of [img 1]. She stands perfectly still while snow falls heavily around her and the wind moves her hair. Tripod shot." |
| Pan Left/Right | Pan | Camera rotates horizontally | Reveal or follow action | "Camera pans slowly from left to right, starting on a snowy tree and revealing [img 1] standing in the distance." |
| Tilt Up/Down | Tilt | Camera tilts vertically | Reveal height or depth | "Camera tilts up, starting at [img 1]'s boots in the snow and moving up to reveal her face and the mountain peak behind her." |
| Zoom In | Zoom In, Lens Zoom | Camera slowly moves toward subject | Increase emotional intensity | "Slow zoom in on [img 1]'s face. The background compresses as the camera gets tighter on her expression." |
| Zoom Out | Zoom Out, Wide Reveal | Camera moves away from subject | Reveal environment or isolation | "Zoom out from [img 1]'s eye to reveal she is standing on the edge of a massive cliff. Establishing the environment." |
| Pedestal Up/Down | Pedestal Up, Pedestal Down | Entire camera physically moves up or down (elevator motion) | Change subject's relationship to ground | "Camera pedestals up, rising from the snow level to eye-level with [img 1], revealing her stature against the mountains." |
| Movement | AI Keyword | Definition | Purpose | Prompt Example |
|---|---|---|---|---|
| Dolly In | Dolly In | Camera moves forward on a track | Controlled cinematic intimacy | "Smooth cinematic dolly in towards [img 1]. The camera physically pushes forward through the snow, getting closer to her." |
| Dolly Out | Dolly Out | Camera moves backward on a track | Reveal scale or emotional distance | "Cinematic dolly out from [img 1]. The camera physically moves backward, starting close to her face and retreating to show her alone." |
| Truck Left/Right | Truck Left | Camera moves horizontally left or right | Add parallax and motion | "Truck right camera movement. The camera slides sideways parallel to [img 1] as she stands in profile, revealing the army behind her." |
| Orbit Shot | Orbit | Camera circles the subject | Dramatic emphasis and energy | "Camera orbits 360 degrees around [img 1]. She stands still in the center while the snowy background spins slowly behind her." |
| Crane Shot | Crane | Camera moves vertically on a crane | Grand reveal or epic scale | "Crane shot starting low on [img 1] and sweeping high up into the air, looking down at the snowy valley below." |
| Movement | AI Keyword | Definition | Purpose | Prompt Example |
|---|---|---|---|---|
| Dolly Zoom | Dolly Zoom, Vertigo Effect | Camera moves backward while zooming in (or vice versa) | Background warps while subject stays the same size — disorientation | "Dolly zoom effect on [img 1]. The background mountains appear to warp and grow larger while she stays the same size. Vertigo effect." |
| Crash Zoom | Crash Zoom | Fast aggressive zoom | Shock or sudden emphasis | "Sudden crash zoom into [img 1]'s face. The camera snaps from a wide shot to an extreme close-up instantly. Dramatic impact." |
| FPV Drone Shot | FPV | Fast, immersive flying camera movement | High energy and immersion | "Fast FPV drone shot flying through a snowy canyon and swooping past [img 1]. High speed, dynamic motion blur." |
| Bullet Time | Bullet Time | Time appears frozen while camera moves | Stylized dramatic emphasis | "Bullet time effect. Time is frozen with snowflakes suspended in mid-air, while the camera smoothly rotates 180 degrees around [img 1]." |
| Handheld Follow | Handheld Follow | Handheld camera follows subject | Urgency and realism | "Handheld camera movement following [img 1]. The image has slight shake and organic motion, documentary war reporter style." |
| Camera Roll | Camera Roll | Camera rotates on its axis | Disorientation or intensity | "Camera roll. The horizon line spins 360 degrees while focused on [img 1], turning the snowy world upside down and back again." |
| Rack Focus | Rack Focus | Focus shifts between subjects | Guide viewer attention | "Rack focus shot. Starts focused on a sword in the foreground, then shifts focus to [img 1]'s face in the background." |
| Pull Back Reveal | Reveal | Camera pulls back to reveal new context | Surprise or scale reveal | "Pull back reveal. Camera starts on the detail of [img 1]'s eye, then pulls back rapidly to show she is standing on top of a burning village." |
| Fly-Through | Fly-Through | Camera moves through environment elements | Immersion and momentum | "Camera flies through a gap in the trees and past falling snow to land on a medium shot of [img 1]." |
The strongest image prompts layer all three:
Pattern: [Distance/Size] + [Angle] + [Movement hint] + [Subject] + [Environment] + [Lighting]
Examples:
Low angle medium close-up of [img 1], camera dolly zooming in slowly.
She towers over the frame against a blood-red sunset, wind whipping her cloak.
Cinematic lighting, high contrast.Overhead extreme wide shot, static camera. [img 1] is a tiny figure at the center
of a vast frozen lake, her shadow stretching long. Blue hour lighting, desolate.Ground level close-up, rack focus. Snow crystals sharp in the foreground,
[img 1]'s boots blurred behind them, then focus shifts to her face looking down.
Shallow depth of field, cold blue tones.Dutch angle cowboy shot, handheld feel. [img 1] stands mid-thigh up in a
burning village, tilted horizon, smoke swirling. War paint on her face,
weapon drawn. Chaotic, urgent composition.[Shot size] + [Angle] + [Movement keyword] of [img 1 / character description].
[Pose, expression, or action].
[Environment — location, weather, atmosphere].
[Lighting — time of day, source, quality].
[Style — cinematic, film stock, color grade].Full example:
Medium close-up, low angle, slow dolly in toward [img 1].
She stares past the camera with narrowed eyes, jaw set, braids falling over
one shoulder. A frozen battlefield stretches behind her, smoke rising from
distant fires. Golden hour backlight rims her silhouette.
Style: Cinematic, Kodak Vision3 500T, desaturated teal shadows, warm highlights.Negative constraints: For face/identity and texture/lighting artifacts in image generation, see
../shared/negative-constraints.md.
higgsfield-camera — Video camera controls (this skill covers still-image composition)higgsfield-style — Visual styles and lighting techniqueshiggsfield-soul — Soul ID for character-consistent image serieshiggsfield-cinema — Cinema Studio optical physics engine for image generationhiggsfield-models — Image model selection (Soul 2.0, Nano Banana, Seedream, etc.)templates/ — Annotated genre-specific prompt templates© OSideMedia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/higgsfield-image-shots of OSideMedia/higgsfield-ai-prompt-skill.
Open the folder on GitHubat commit 7075497
Higgsfield Image Shots next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Higgsfield Image Shots this skillOSideMedia/higgsfield-ai-prompt-skill | 713 | — | ~5.1k | Automated safety check: Pass | MIT | |
| RunninghubHM-RunningHub/OpenClaw_RH_Skills | 142 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Retail Virtual Try-On Agentgoogle/adk-recipes | 10k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| ComfyUI Local DriverSlavaSexton/ComfyUI-Agent-Kit | 105 | — | ~12k | Automated safety check: Pass | Apache-2.0 | |
| Google Gemini Mediasundial-org/awesome-openclaw-skills | 663 | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Mulerouteraiskillstore/marketplace | 433 | — | ~714 | Automated safety check: Notes | None |
HM-RunningHub/OpenClaw_RH_Skills
Generate images, videos, audio, and 3D models via RunningHub API (420 endpoints) and run any RunningHub AI Application (custom ComfyUI workflow) by webappId.
google/adk-recipes
Sets up a virtual try-on agent on Google Cloud that generates image and catwalk-video try-ons with Gemini, from first setup through local testing.
SlavaSexton/ComfyUI-Agent-Kit
Drives a local ComfyUI install over its HTTP API to generate and edit images, video and audio, with per-model prompt recipes and workflow guidance.
sundial-org/awesome-openclaw-skills
Use the Gemini API (Nano Banana image generation, Veo video, Gemini TTS speech and audio understanding) to deliver end-to-end multimodal media workflows and code templates for "generation +…
aiskillstore/marketplace
Generates images and videos using MuleRouter or MuleRun multimodal APIs.
liangdabiao/Seedance2-Storyboard-Generator
专业的Seedance 2.0平台AI视频脚本和分镜生成器。当用户要求:(1) 将文章/故事转换为视频脚本,(2) 生成Seedance 2.0分镜提示词,(3) 规划多集AI视频系列,(4) 为GPT-Image-2、Seedream、Nano Banana…
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano…
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses when the user asks about Higgsfield Assist (the built-in GPT-5 copilot), how to use the platform's native AI assistant, credit optimization strategies, plan selection, how to…
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses when the user asks about Mixed Media, wants to apply artistic preset styles to an image (Noir, Sketch, Paper, Canvas, Particles, Neon, etc.), combine multiple artistic…
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses when the user asks about Moodboard, building a moodboard from reference images, curated moodboard presets, Soul Hex color transfer, applying a visual style direction to…
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses when the user wants to apply a named Higgsfield motion preset, asks about VFX presets, transformation effects, elemental effects, or transition presets.
OSideMedia/higgsfield-ai-prompt-skill
End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector.
Works with
Categories
A skill your agent uses when the user wants to generate a cinematic still image on Higgsfield, asks about shot framing, camera angle, or composition for image prompts, needs a specific shot type…. Higgsfield Image Shots is an agent skill from OSideMedia/higgsfield-ai-prompt-skill.), or is working with [img] reference-based image generation.
Higgsfield Image Shots fits situations like: the user wants to generate a cinematic still image on Higgsfield; asks about shot framing; composition for image prompts; needs a specific shot type (close-up.
Run `npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-image-shots -a claude-code`. Or copy the skill folder (skills/higgsfield-image-shots in OSideMedia/higgsfield-ai-prompt-skill) into .claude/skills/higgsfield-image-shots in your project. Claude Code loads it when a task matches its description.
Run `npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-image-shots -a codex`. Or copy the skill folder (skills/higgsfield-image-shots in OSideMedia/higgsfield-ai-prompt-skill) into .agents/skills/higgsfield-image-shots in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-image-shots -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/higgsfield-image-shots, .gemini/skills/higgsfield-image-shots, .github/skills/higgsfield-image-shots and .opencode/skills/higgsfield-image-shots in your project.
Going by SKILL.md and its folder, Higgsfield Image Shots needs the command-line tools its instructions call (snow).
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Higgsfield Image Shots is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.1k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Higgsfield Image Shots: Runninghub (HM-RunningHub/OpenClaw_RH_Skills, 142 stars), Retail Virtual Try-On Agent (google/adk-recipes, 10k stars), ComfyUI Local Driver (SlavaSexton/ComfyUI-Agent-Kit, 105 stars) and Google Gemini Media (sundial-org/awesome-openclaw-skills, 663 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
OSideMedia (a GitHub user) maintains it in OSideMedia/higgsfield-ai-prompt-skill, which has 713 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on September 27, 2026.
Source: OSideMedia/higgsfield-ai-prompt-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.