Menu
O SkillsMP coletou 7 skills de qualit527/qec-ai-decoder. Abra uma skill para revisar a origem e os detalhes.
Copie este prompt para o assistente de IA que você usa.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/qualit527/qec-ai-decoder.Mostrando 7 de 7 skills coletadas.
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.
Idioma do texto original: inglês
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.…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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…
Idioma do texto original: inglês