Ecro/embedeval

LLM benchmark for embedded firmware development

11Stars on the repository
8Mods indexed here, across every type
26d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

execute

01

Ecro/embedeval

Command Claude Code

Implement the PLAN with continuous verification. Step 3 of the embedeval 5-stage workflow. Reports to screen only — no SESSION document.

11 26d ago A 0 tokens original Apache-2.0

myplan

02

Ecro/embedeval

Command Claude Code

Analyze, design, and write a PLAN document. Step 2 of the embedeval 5-stage workflow. The PLAN file is the only persistent artifact in this workflow — /execute, /review, and /wrapup all report to screen only.

11 26d ago A 0 tokens original Apache-2.0

negatives

03

Ecro/embedeval

Command Claude Code

Sequentially author negatives.py for every case that lacks one, with interactive judgment gates where LLM cannot reliably decide.

11 26d ago A 0 tokens original Apache-2.0

research

04

Ecro/embedeval

Command Claude Code

Gather information, explore options, recommend an approach. Step 1 of the embedeval 5-stage workflow. Informs /myplan — does not create any file.

11 26d ago A 0 tokens original Apache-2.0

review

05

Ecro/embedeval

Command Claude Code

Deep review of task changes. Step 4 of the embedeval 5-stage workflow. Reports to screen only — no ANALYSIS document.

11 26d ago A 0 tokens original Apache-2.0

test

06

Ecro/embedeval

Command Claude Code

Run LLM benchmark, save detailed results, generate failure analysis report.

11 26d ago C 0 tokens original Apache-2.0

wrapup

07

Ecro/embedeval

Command Claude Code

Final validation, docs sync, and commit. Step 5 of the embedeval 5-stage workflow. Reports to screen only — no WRAPUP/LEARNING document.

11 26d ago A 0 tokens original Apache-2.0