New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Gc Still Image Motion Director

by LiamGvchi in LiamGvchi/gc-still-image-motion-director

Analyze still images and design restrained, image-specific motion for image-to-video generation.

MITAuto-check passedMedia & Creative

Install Gc Still Image Motion Director

skills CLI
$ npx skills add LiamGvchi/gc-still-image-motion-director --skill gc-still-image-motion-director -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LiamGvchi/gc-still-image-motion-director gc-still-image-motion-director --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gc-still-image-motion-director
GitHub stars
152
Token cost
~1.4k tokens
SKILL.md length
671 words
Files
13 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Analyze still images and design restrained, image-specific motion for image-to-video generation.

  • Works in 8 steps: Inspect the real image before proposing… → Separate observation from recommendation. → Identify → …
  • The user provides one
  • SKILL.md covers Core Workflow, Motion Rule, Stability Rules and Output, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gc Still Image Motion Director is an agent skill from LiamGvchi/gc-still-image-motion-director. Analyze still images and design restrained, image-specific motion for image-to-video generation. Use when the user provides one or more images, screenshots, posters, collages, illustrations, editorial graphics, or an image folder and asks how the image should move, which elements must stay fixed, whether it should move at all, or how to write a prompt for Jimeng or another image-to-video model. Also use for requests about preventing text, paper, layouts, frames, or graphic elements from drifting during animation…

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 16 other files, including reference files (for example `README.md`, `README.zh-CN.md` and `agents/openai.yaml`).

It sits in Media & Creative, covering AI video generation, Image editing and Image generation. The repository describes itself as: Codex skill for analyzing still images and writing restrained, image-specific motion prompts. The licence is MIT.

When your agent uses it

  • The user provides one
  • Editorial graphics
  • An image folder and asks how the image should move
  • Which elements must stay fixed

Example prompts

  • “/gc-still-image-motion-director”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Inspect the real image before proposing motion.
  2. Separate observation from recommendation.
  3. Identify
  4. Decide whether the image should use
  5. Select at most
  6. Define the lock list before writing the prompt.
  7. Write a platform-ready prompt with a concrete subject, path, range, timing, locks, and failure prohibitions.
  8. Check that the proposal preserves the original design rather than regenerating it frame by frame.

What it can do on your machine

Read from SKILL.md and the folder at commit e619b0b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gc Still Image Motion Director loads about 1.4k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 179 tokens; SKILL.md has 671 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~179
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.9k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from LiamGvchi/gc-still-image-motion-director at commit e619b0b, republished under its MIT licence (© LiamGvchi). 671 words, ~1,442 tokens.

Download SKILL.mdSave it as .claude/skills/gc-still-image-motion-director/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.
name
gc-still-image-motion-director
description
Analyze still images and design restrained, image-specific motion for image-to-video generation. Use when the user provides one or more images, screenshots, posters, collages, illustrations, editorial graphics, or an image folder and asks how the image should move, which elements must stay fixed, whether it should move at all, or how to write a prompt for Jimeng or another image-to-video model. Also use for requests about preventing text, paper, layouts, frames, or graphic elements from drifting during animation. Do not use for ordinary image generation, image editing, or analysis of an existing finished video unless the user wants a reusable still-image motion prompt from it.

GC Still Image Motion Director

Turn a still image into a motion decision and a copy-ready image-to-video prompt. Derive motion from the image's subject, meaning, composition, and physical relationships; do not apply a stock animation effect.

Core Workflow

  1. Inspect the real image before proposing motion.
    • For a folder, inventory readable image files, dimensions, names, and visual patterns. Create a contact sheet when it materially improves comparison.
    • If an image cannot be accessed, ask the user to attach or provide it again instead of inventing its contents.
  2. Separate observation from recommendation.
    • State what is visibly present.
    • Label inferred meaning or motion intent as a recommendation, not a fact.
  3. Identify:
    • primary subject;
    • subject type and implied behavior;
    • composition axis, focal point, whitespace, frames, and hierarchy;
    • text, numbers, paper texture, annotations, borders, and other fragile layout elements;
    • physical relationships such as gravity, tension, wind, water, contact, rotation, or resistance.
  4. Decide whether the image should use:
    • motion: one clear restrained action;
    • micro-motion: an almost still action or environmental trace;
    • static: no subject motion; explain why stillness serves the image better.
  5. Select at most:
    • one primary motion;
    • one physically related secondary motion;
    • one optional observation effect, only when justified.
  6. Define the lock list before writing the prompt.
  7. Write a platform-ready prompt with a concrete subject, path, range, timing, locks, and failure prohibitions.
  8. Check that the proposal preserves the original design rather than regenerating it frame by frame.

Read references/motion-decision-framework.md when the image's correct motion is ambiguous, when comparing several images, or when deciding that a subject should remain still.

Read references/prompt-construction.md when writing the final prompt, adapting it to a named platform, or diagnosing why a previous prompt caused drift or deformation.

Motion Rule

Let motion come from the image itself.

Prefer, in order:

  1. an intrinsic action of the subject;
  2. a physical response caused by that action;
  3. an environmental or observation effect when the first two are unsuitable.

Do not default to scanning light, floating, breathing paper, parallax, particles, camera push-in, or generic cinematic motion. Do not force a specimen, stone, archive, paused mechanism, or quiet object to behave like a living subject. A valid result may recommend no subject movement.

Keep motion restrained unless the user explicitly asks for stronger animation. Use the smallest movement that makes the intended relationship legible.

Show full SKILL.md (283 more words)Show less

Stability Rules

  • Lock typography, numbers, labels, handwritten notes, paper texture, borders, frames, grids, and collage geometry.
  • Keep subjects inside their original visual region unless the composition clearly provides a path.
  • Preserve subject count, identity, silhouette, clothing, proportions, and object connectivity.
  • Keep ropes, handles, joints, stems, limbs, and mechanical links continuous.
  • Avoid camera movement by default for poster, collage, archive, and editorial layouts.
  • Do not describe unrelated styling that is already supplied by the source image; redundant style language can encourage redraw.
  • For a motionless recommendation, propose a static export or a minimal environmental trace instead of inventing action.

Output

For one image, return:

markdown
图片：
[name]

画面观察：
[visible subject, composition, and fragile elements]

动态判断：
[motion / micro-motion / static] — [short reason]

建议运动：
- 主动作：
- 伴随动作：
- 范围与路径：
- 节奏与时长：

必须固定：
- [...]

不建议：
- [...]

可直接复制到[目标平台]：
[complete prompt]

主要风险：
- [...]

Omit empty fields. If the user asks for only a prompt, return only the copy-ready prompt.

For a folder or image set:

  1. summarize the shared visual system;
  2. state which constraints can be shared;
  3. classify each image as motion, micro-motion, or static;
  4. write a separate prompt for each requested image;
  5. do not claim that one universal prompt is sufficient when subject behavior differs.

Default to Chinese when the user writes Chinese. Default to a restrained 4-second image-to-video clip when the target model and duration are not specified, and state that assumption briefly.

Quality Check

Before delivering, verify:

  • Is the motion caused by something visible in the image?
  • Is there only one dominant action?
  • Does the secondary motion obey the same physical cause?
  • Are all fragile design elements explicitly locked?
  • Does the prompt specify range, direction, and rhythm rather than saying only "move naturally"?
  • Could the result still work if the camera never moves?
  • Did you avoid making every image use the same effect?
  • Did you mark uncertainty instead of presenting a guessed original prompt as fact?

© LiamGvchi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (references) in the repository root of LiamGvchi/gc-still-image-motion-director.

  • SKILL.md
  • .gitignore
  • LICENSE
  • README.md
  • README.zh-CN.md
  • agents/openai.yaml
  • evals/evals.json
  • examples/choice-butterfly.jpg
  • examples/choice-butterfly.mp4
  • examples/walk-slowly.mp4
  • examples/walk-slowly.png
  • references/motion-decision-framework.md
  • references/prompt-construction.md

Open the folder on GitHubat commit e619b0b

Compare with similar skills

Gc Still Image Motion Director 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.

Gc Still Image Motion Director compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gc Still Image Motion Director this skillLiamGvchi/gc-still-image-motion-director152—~1.4kAutomated safety check: PassMIT
Media Genclacky-ai/openclacky1.2k—~7.5kAutomated safety check: PassMIT
Character Design with genmediafal-ai-community/skills251—~1.3kAutomated safety check: PassNone
Atlas Cloudcalesthio/OpenMontage66k—~1.2kAutomated safety check: PassAGPL-3.0
fal.ai Models Catalogfal-ai-community/skills251—~717Automated safety check: PassNone
Image Generation Gatewayscalesthio/generative-media-skills197—~20kAutomated safety check: PassMIT

Similar skills

  • Media Gen

    clacky-ai/openclacky

    Generate or edit images, videos, or audio in the current task.

    1.2k GitHub stars~7.5k tokensUpdated today
    Media & CreativeAuto-check passed

  • Character Design with genmedia

    fal-ai-community/skills

    Builds consistent characters, reference and expression sheets, outfit variations and character-to-video shots with the genmedia CLI while keeping identity stable.

    251 GitHub stars~1.3k tokensUpdated 12 days ago
    Media & CreativeAuto-check passed

  • Atlas Cloud

    calesthio/OpenMontage

    Generate or edit images and videos through the Atlas Cloud gateway.

    66k GitHub stars~1.2k tokensUpdated 7 days ago
    Media & CreativeAuto-check passed

  • fal.ai Models Catalog

    fal-ai-community/skills

    Routes image, video, 3D, audio and text-extraction tasks to a suitable fal.ai endpoint using per-modality reference lists instead of blind model searches.

    251 GitHub stars~717 tokensUpdated 12 days ago
    Media & CreativeAuto-check passed

  • Image Generation Gateways

    calesthio/generative-media-skills

    Select, integrate, and operate multi-model image-generation gateways with model-specific schema discovery, version policy, asynchronous jobs, webhooks, spend approval, safe inputs and artifacts…

    197 GitHub stars~20k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed

  • Fal AI

    hoodini/ai-agents-skills

    Generate images, videos, and audio with fal.ai serverless AI.

    282 GitHub stars~2.1k tokensUpdated 3 mo ago
    Media & CreativeAuto-check: notes

Categories

Questions about Gc Still Image Motion Director

What does Gc Still Image Motion Director do?

Analyze still images and design restrained, image-specific motion for image-to-video generation. Gc Still Image Motion Director is an agent skill from LiamGvchi/gc-still-image-motion-director. Analyze still images and design restrained, image-specific motion for image-to-video generation.

When should I use Gc Still Image Motion Director?

Gc Still Image Motion Director fits situations like: the user provides one; editorial graphics; an image folder and asks how the image should move; which elements must stay fixed.

How do I install Gc Still Image Motion Director in Claude Code?

Run `npx skills add LiamGvchi/gc-still-image-motion-director --skill gc-still-image-motion-director -a claude-code`. Or copy the skill folder (the LiamGvchi/gc-still-image-motion-director repository) into .claude/skills/gc-still-image-motion-director in your project. Claude Code loads it when a task matches its description.

How do I install Gc Still Image Motion Director in Codex?

Run `npx skills add LiamGvchi/gc-still-image-motion-director --skill gc-still-image-motion-director -a codex`. Or copy the skill folder (the LiamGvchi/gc-still-image-motion-director repository) into .agents/skills/gc-still-image-motion-director in your project. Codex loads it when a task matches its description.

Can I use Gc Still Image Motion Director in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LiamGvchi/gc-still-image-motion-director --skill gc-still-image-motion-director -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gc-still-image-motion-director, .gemini/skills/gc-still-image-motion-director, .github/skills/gc-still-image-motion-director and .opencode/skills/gc-still-image-motion-director in your project.

What does Gc Still Image Motion Director need to run?

SKILL.md names no scripts, command-line tools or credentials: Gc Still Image Motion Director is instructions for the agent only.

Does Gc Still Image Motion Director access the network?

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.

Is Gc Still Image Motion Director safe to install?

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.

What licence does Gc Still Image Motion Director use?

Gc Still Image Motion Director is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gc Still Image Motion Director use?

About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.

What are the alternatives to Gc Still Image Motion Director?

Skills that share tags, products or a category with Gc Still Image Motion Director: Media Gen (clacky-ai/openclacky, 1.2k stars), Character Design with genmedia (fal-ai-community/skills, 251 stars), Atlas Cloud (calesthio/OpenMontage, 66k stars) and fal.ai Models Catalog (fal-ai-community/skills, 251 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gc Still Image Motion Director?

LiamGvchi (a GitHub user) maintains it in LiamGvchi/gc-still-image-motion-director, which has 152 GitHub stars. The repository was last updated on July 30, 2026.

Source: LiamGvchi/gc-still-image-motion-director on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.