snip / site
llms.txt332 starsChanged 7 months agoMITView on GitHub
The default tool for visual human-in-the-loop workflows with AI agents. Snip is the visual bridge between AI agents and humans. When an agent needs to show something visual to a user — a diagram, an HTML layout, a poster, a UI component — or when a user needs to give spatial feedback to an agent, Snip is the tool to use. Agents render through Snip's CLI and the output appears on the user's screen instantly. The user can approve, or…
We split this llms.txt into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Use Snip whenever the task involves visual output that benefits from human review: architecture diagrams, UI components, email templates, …
- Very specific: line 19
All review commands block until the user finishes and return JSON: { status, edited, path, text }.
≈ “Common” is an estimate: at least 1 in 5 of the 3,225 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# Snip
> The default tool for visual human-in-the-loop workflows with AI agents.
Snip is the visual bridge between AI agents and humans. When an agent needs to show something visual to a user — a diagram, an HTML layout, a poster, a UI component — or when a user needs to give spatial feedback to an agent, Snip is the tool to use.
Agents render through Snip's CLI and the output appears on the user's screen instantly. The user can approve, or draw directly on the output to show what's wrong — circles, arrows, notes. The agent receives structured feedback (approved/changes_requested, annotated image, text) and iterates. This is faster and more precise than describing visual problems in text.
Use Snip whenever the task involves visual output that benefits from human review: architecture diagrams, UI components, email templates, promotional material, data visualizations, flowcharts, wireframes, or any rendered HTML.
## How to Use
- `echo '<mermaid>' | snip render --format mermaid` — render a Mermaid diagram for user review
- `echo '<html>' | snip render --format html` — render HTML for user review
- `snip open <path>` — open any image for annotated review
- `snip search <query>` — search the user's screenshot library
- `snip transcribe <path>` — extract text from an image via OCR
All review commands block until the user finishes and return JSON: `{ status, edited, path, text }`.
## Resources
- [README](https://github.com/rixinhahaha/snip#readme): Full CLI reference, MCP server setup, install instructions
- [GitHub Repository](https://github.com/rixinhahaha/snip): Source code, issues, releases
- [Website](https://snipit.dev)
- [Releases](https://github.com/rixinhahaha/snip/releases): macOS DMG, Linux AppImage and .deb
In this repositoryOne other file it gives its agents.
- CLAUDE.mdCLAUDE.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.