Individual skill
canvas-cowork
Generate text, images and videos on Flowith's canvas from the CLI, headless or with a live cursor. Use for any image/video generation (Seedance, Veo, Kling, gpt-image, Gemini image), "canvas", "Flowith", "Neo", drawing/creating visual content, or past canvas work. /canvas-cowork
SKILL.md
Source commit 9b80a7fd33e039aa520707887d7ca23441546568
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 41
- Repository last updated
- Oct 20, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- flowith Repository topic
- spatial-canvas Repository topic
- ai-agent Repository topic
- canvas Repository topic
- claude-code Repository topic
- mcp Repository topic
- skills-sh Repository topic
- codex Repository topic
- openclaw Repository topic
- design Derived category
- writing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
LICENSEasset · 1,067 bytesREADME.mddoc · 3,076 bytesSKILL.mdcore · 4,079 bytesSKILL.mdcore · 4,079 bytesSKILL.mdcore · 4,079 bytesreferences/api.mddoc · 8,148 bytesreferences/cli.mddoc · 6,747 bytesreferences/creative-dream.mddoc · 5,823 bytesreferences/troubleshooting.mddoc · 3,559 bytesscripts/__tests__/canvas.test.tsruns · 2,546 bytesscripts/__tests__/ergonomics.test.tsruns · 5,910 bytesscripts/__tests__/generate.test.tsruns · 7,777 bytesscripts/__tests__/models.test.tsruns · 5,449 bytesscripts/index.tsruns · 92,053 bytesscripts/lib/canvas.tsruns · 9,276 bytesscripts/lib/download.tsruns · 1,575 bytesscripts/lib/generate.tsruns · 20,755 bytesscripts/lib/http.tsruns · 5,960 bytesscripts/lib/models.tsruns · 13,476 bytesscripts/lib/session.tsruns · 3,553 bytesscripts/lib/upload.tsruns · 4,022 bytes
Read excerpt
# Canvas Cowork
You are a collaborator on a shared spatial canvas. Everything you generate lands
as a node the user can open later; when a Flowith tab is open they also see your
cursor move. **Be their eyes and hands**: after every generation bring the result
back — images as `` with your honest read of what appeared, video as
`[Watch video](url)` plus what happens in it, text printed directly. Never say
"go look at the canvas." **Have taste**: say when a result misses, or when a
different angle would be better. `recall` is shared memory — use it.
Run from the skill directory with bun. Always pass `--bot <your-identity>`
(`claude-code` | `codex` | `openclaw` | `cursor` | `opencode` | `flowithos`).
## Cheat sheet (covers 95% of work — no browser needed)