qualit527/qec-ai-decoder

demo-presenter

Use when preparing an AutoQEC demo walkthrough, advisor presentation, hackathon pitch, recorded narration, or evidence-backed explanation of why the demos matter and why their outputs are correct.

لغة النص الأصلي: الإنجليزية

review-framework

Read the artifacts of a completed AutoQEC run and propose improvements to the framework code itself — DSL gaps, weak baselines, miscalibrated safety thresholds, prompt drift, env limitations, orchestration friction. Advisory only; never edits framework files.…

لغة النص الأصلي: الإنجليزية

autoqec-run

Run the AutoQEC research loop on a given env YAML. Orchestrates the autoqec-ideator / autoqec-coder / autoqec-analyst subagents via the Agent tool, invokes the Runner CLI for training + evaluation, and writes history.jsonl + pareto.json. Use when the user…

لغة النص الأصلي: الإنجليزية

read-zulip

Read Zulip stream/topic history for project context, summarize decisions, and recover requirements or action items. Use when task context may depend on prior Zulip discussion rather than only repository files.

لغة النص الأصلي: الإنجليزية

diagnose-failure

Inspect a stalled or failed run, identify root cause (bad hyperparameter / NaN pattern / OOM / env misconfig), and recommend a fix. Does NOT apply fixes autonomously.

لغة النص الأصلي: الإنجليزية

review-log

Read an entire runs/<id>/log.md and assess research narrative coherence, identify stuck hypotheses, detect overfitting signs, and write a review markdown. Use after a full run completes or when a loop has been stuck for many rounds.

لغة النص الأصلي: الإنجليزية

verify-decoder

Audit a predecoder checkpoint against holdout seeds. Runs independent_eval (3 fair-baseline guards) and interprets borderline cases with LLM reasoning. Use when a round produces a promising Δ_LER and the user wants to confirm it is not a reward-hacking…

لغة النص الأصلي: الإنجليزية