Autograd Tutor
Teaches reverse-mode autodiff by building a 100-LOC engine.
Preview
What this package looks like once your agent has it.
$ npx super-agent install micrograd-tutor → resolving micrograd-tutor@0.1.0 → runtimes ......... any MCP client → scopes ........... agent:upgrade, registry:read → size ............. — ✓ Autograd Tutor is available to your agent # or point any MCP client at the gateway: # https://superagentskill.com/api/public/mcp
Previews are rendered from this package's published content (install commands, system prompt, examples) — not marketing screenshots.
Description
Teaches reverse-mode autodiff by building a 100-LOC engine.
System prompt
The exact instructions this package installs into your agent.
You teach autograd by building Value/Tensor with `.backward()` from scratch. Show the topological sort, gradient accumulation, and how PyTorch generalises it.Stats
Adoption, reception and performance for this package.
No published performance metrics yet.
Install instructions
Three ways in — pick the one your client supports.
Open Skills CLI (skills.sh)
Standard SKILL.md install for Claude Code, Cursor, Codex, Copilot, Windsurf, Gemini, Cline, Zed and more. No account needed.
npx skills add criptogus/agent-evolve-network/micrograd-tutornpx skills updateMCP gateway — always the current graded version
Add this URL as an MCP server in Claude, Hermes, Cursor or ChatGPT. This package is included automatically.
https://superagentskill.com/api/public/mcpSAK CLI
Install a pinned version into the current project.
npx super-agent install micrograd-tutornpx super-agent install micrograd-tutor@0.1.0Copy / paste
Paste the system prompt above into any assistant that has no MCP support.
Open in playground →Changelog
Every published release, newest first.
Versions
| Version | Status | Released | Notes | |
|---|---|---|---|---|
| 0.1.0 | stable | 3 months ago |
Compatibility
Compatibility is verified through the MCP gateway across major agent runtimes. Partial support means the package works but may need manual schema mapping or feature limitations.
Reviews
Reviews & ratings
Only verified buyers (paid) or users with at least one successful run (free) can rate.