Venice Image Edit
nexu-io/open-design
Image edits, upscaling, and background removal via the Venice.ai API.
Explore image concepts and make faithful edits of accepted references for 3D or creative production, with explicit model choices and visual review.
MITAuto-check passed
Install Image Reference Workflow
$ npx skills add witnesstodark/mr-mak-workspace --skill image-reference-workflow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install witnesstodark/mr-mak-workspace image-reference-workflow --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/witnesstodark/mr-mak-workspace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/image-reference-workflow .claude/skills/image-reference-workflow && 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 "image-reference-workflow" agent skill from https://github.com/witnesstodark/mr-mak-workspace/tree/main/.agents/skills/image-reference-workflow into .claude/skills/image-reference-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-reference-workflow", 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/witnesstodark/mr-mak-workspace/tree/main/.agents/skills/image-reference-workflowType 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 witnesstodark/mr-mak-workspace --skill image-reference-workflow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install witnesstodark/mr-mak-workspace image-reference-workflow --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/witnesstodark/mr-mak-workspace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/image-reference-workflow .agents/skills/image-reference-workflow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "image-reference-workflow" agent skill from https://github.com/witnesstodark/mr-mak-workspace/tree/main/.agents/skills/image-reference-workflow into .agents/skills/image-reference-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-reference-workflow", 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 witnesstodark/mr-mak-workspace --skill image-reference-workflow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install witnesstodark/mr-mak-workspace image-reference-workflow --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/witnesstodark/mr-mak-workspace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/image-reference-workflow .cursor/skills/image-reference-workflow && 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 "image-reference-workflow" agent skill from https://github.com/witnesstodark/mr-mak-workspace/tree/main/.agents/skills/image-reference-workflow into .cursor/skills/image-reference-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-reference-workflow", 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/witnesstodark/mr-mak-workspace.git --path .agents/skills/image-reference-workflow--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 witnesstodark/mr-mak-workspace --skill image-reference-workflow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install witnesstodark/mr-mak-workspace image-reference-workflow --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/witnesstodark/mr-mak-workspace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/image-reference-workflow .gemini/skills/image-reference-workflow && 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 "image-reference-workflow" agent skill from https://github.com/witnesstodark/mr-mak-workspace/tree/main/.agents/skills/image-reference-workflow into .gemini/skills/image-reference-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-reference-workflow", 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 witnesstodark/mr-mak-workspace image-reference-workflowInstalls 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 witnesstodark/mr-mak-workspace --skill image-reference-workflow -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/witnesstodark/mr-mak-workspace.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/image-reference-workflow .github/skills/image-reference-workflow && 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 "image-reference-workflow" agent skill from https://github.com/witnesstodark/mr-mak-workspace/tree/main/.agents/skills/image-reference-workflow into .github/skills/image-reference-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-reference-workflow", 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 witnesstodark/mr-mak-workspace --skill image-reference-workflow -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install witnesstodark/mr-mak-workspace image-reference-workflow --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/witnesstodark/mr-mak-workspace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/image-reference-workflow .opencode/skills/image-reference-workflow && 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 "image-reference-workflow" agent skill from https://github.com/witnesstodark/mr-mak-workspace/tree/main/.agents/skills/image-reference-workflow into .opencode/skills/image-reference-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-reference-workflow", 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.
Facts
- Skill name
image-reference-workflow- GitHub stars
- 322
- Token cost
- ~527 tokens
- SKILL.md length
- 279 words
- Files
- 1
- Skills in repo
- 19
- Repo updated
- First seen
- Licence
- MIT
At a glance
Explore image concepts and make faithful edits of accepted references for 3D or creative production, with explicit model choices and visual review.
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Image Reference Workflow is an agent skill from witnesstodark/mr-mak-workspace. Explore image concepts and make faithful edits of accepted references for 3D or creative production, with explicit model choices and visual review.
Its SKILL.md is about 530 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: A local desktop workspace for Codex and Claude Code, with project reports, creative skills and optional voice. The licence is MIT.
Example prompts
- “/image-reference-workflow”
What it can do on your machine
Read from SKILL.md and the folder at commit 1e0c7c3. 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.
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
Image Reference Workflow loads about 527 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 279 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.
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 witnesstodark/mr-mak-workspace at commit 1e0c7c3, republished under its MIT licence (© witnesstodark). 279 words, ~527 tokens.
Download SKILL.mdSave it as
.claude/skills/image-reference-workflow/SKILL.md (or your agent's skills folder).- name
- image-reference-workflow
- description
- Explore image concepts and make faithful edits of accepted references for 3D or creative production, with explicit model choices and visual review.
Image references and faithful edits
Choose exploration or editing from the user's request. Exploration varies design dimensions; editing preserves an accepted asset and changes a named feature. Inspect supplied images before choosing the operation. Respect the requested provider, model, output count, aspect ratio and intended use.
For fal.ai execution, use the bundled fal skill. Another provider can be used when requested; inspect its live model schema.
For concepts, vary silhouette, construction, proportions or palette deliberately. Label candidates with stable names and keep each prompt. For an edit, identify what remains unchanged and the exact delta. Use the accepted image as input, not a reconstruction of it from text. A two-image merge must explain the role of each reference. Avoid injecting extra style adjectives that redesign the asset.
Choose the camera for the deliverable. A hero concept can use dramatic framing; a modeling sheet needs readable parts and neutral light. Do not force the same camera on every task. When extraction is requested, use the character-sheet module rather than treating a cinematic illustration as a complete parts pack.
Keep prompt, endpoint, seed when available, request ID and downloaded outputs together. Review identity, framing, missing parts, unintended additions and the requested change. Compare at full size. Keep rejected takes with a short reason, and preserve the chosen take while making revisions. Present images with direct file access and a useful preview, using the recipient's existing report style.
Example: "Make two observatory robot concepts with different silhouettes." After a selection: "Keep B exactly; change only its blue paint to green." Expected review: the edit retains B's shape, camera, materials and small details. This is an agent workflow, not an automatic quality classifier.
© witnesstodark, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/image-reference-workflow of witnesstodark/mr-mak-workspace.
Open the folder on GitHubat commit 1e0c7c3
Compare with similar skills
Image Reference Workflow 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 |
|---|---|---|---|---|---|---|
| Image Reference Workflow this skillwitnesstodark/mr-mak-workspace | 322 | — | ~527 | Automated safety check: Pass | MIT | |
| Venice Image Editnexu-io/open-design | 100k | — | ~263 | Automated safety check: Pass | Apache-2.0 | |
| Fal Image Editnexu-io/open-design | 100k | — | ~301 | Automated safety check: Pass | Apache-2.0 | |
| Fal Video Editnexu-io/open-design | 100k | — | ~301 | Automated safety check: Pass | Apache-2.0 | |
| AI-Assisted Video Editingaffaan-m/ECC | 274k | 4 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Patch Editnexu-io/open-design | 100k | — | ~470 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Fal Image Edit
nexu-io/open-design
AI-powered image editing with style transfer, background removal, object removal, and inpainting via fal.ai hosted models.
Fal Video Edit
nexu-io/open-design
Edit existing videos using AI — remix style, upscale, remove background, and add audio via fal.ai's hosted video models.
AI-Assisted Video Editing
affaan-m/ECC
Lays out a layered workflow for editing real footage with AI, from raw capture through FFmpeg, Remotion, ElevenLabs and fal.ai to final polish in Descript or CapCut.
Patch Edit
nexu-io/open-design
Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.
QA Acceptance
paperclipai/paperclip
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
More from witnesstodark/mr-mak-workspace
All 19 skills in this repoFal AI Generation
witnesstodark/mr-mak-workspace
Generate and edit images, create video, audio, 3D assets or material maps through fal.ai MCP or the Python queue client.
Game Vfx Workflow
witnesstodark/mr-mak-workspace
Develop game effects from visual references and motion studies through an engine handoff, with event timing, lifecycle, readability and native review.
Game Audio Workflow
witnesstodark/mr-mak-workspace
Build and review game sound banks, map chosen takes to real events, and prepare or verify runtime playback with timing, repetition and mix limits.
Game Level Design
witnesstodark/mr-mak-workspace
Turn a game-level brief or existing scene snapshot into a reviewable spatial plan, then apply approved changes with coordinate, navigation and scene checks.
Game UI Workflow
witnesstodark/mr-mak-workspace
Design and implement game HUDs, menus, icons and portrait systems from visual proposals through reusable engine assets and input checks.
Gameplay Visual Review
witnesstodark/mr-mak-workspace
Verify a visual game change using controlled native captures, targeted behavioral checks and a reviewable evidence record.
Questions about Image Reference Workflow
What does Image Reference Workflow do?
Explore image concepts and make faithful edits of accepted references for 3D or creative production, with explicit model choices and visual review. Image Reference Workflow is an agent skill from witnesstodark/mr-mak-workspace. Explore image concepts and make faithful edits of accepted references for 3D or creative production, with explicit model choices and visual review.
How do I install Image Reference Workflow in Claude Code?
Run `npx skills add witnesstodark/mr-mak-workspace --skill image-reference-workflow -a claude-code`. Or copy the skill folder (.agents/skills/image-reference-workflow in witnesstodark/mr-mak-workspace) into .claude/skills/image-reference-workflow in your project. Claude Code loads it when a task matches its description.
How do I install Image Reference Workflow in Codex?
Run `npx skills add witnesstodark/mr-mak-workspace --skill image-reference-workflow -a codex`. Or copy the skill folder (.agents/skills/image-reference-workflow in witnesstodark/mr-mak-workspace) into .agents/skills/image-reference-workflow in your project. Codex loads it when a task matches its description.
Can I use Image Reference Workflow 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 witnesstodark/mr-mak-workspace --skill image-reference-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/image-reference-workflow, .gemini/skills/image-reference-workflow, .github/skills/image-reference-workflow and .opencode/skills/image-reference-workflow in your project.
What does Image Reference Workflow need to run?
SKILL.md names no scripts, command-line tools or credentials: Image Reference Workflow is instructions for the agent only.
Does Image Reference Workflow 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 Image Reference Workflow 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 Image Reference Workflow use?
Image Reference Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Image Reference Workflow use?
About 527 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Image Reference Workflow?
Skills that share tags, products or a category with Image Reference Workflow: Venice Image Edit (nexu-io/open-design, 100k stars), Fal Image Edit (nexu-io/open-design, 100k stars), Fal Video Edit (nexu-io/open-design, 100k stars) and AI-Assisted Video Editing (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Image Reference Workflow?
witnesstodark (a GitHub user) maintains it in witnesstodark/mr-mak-workspace, which has 322 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 5, 2026.
Source: witnesstodark/mr-mak-workspace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.