职业分类
技术写作员制片人和导演
描述
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.
原文语言：英语
更新
qualit527/qec-ai-decoder
SkillsMP 已收集 qualit527/qec-ai-decoder 中的 7 个 Skill。打开任一 Skill 可查看来源和详情。
- 最近记录的来源活动
- SkillsMP 收录数据更新
- 已收集 skills
- 7
- GitHub 星标
- 3
- GitHub Forks
- 0
用 AI 助手安装
复制这段 Prompt，发给你正在使用的 AI 助手。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/qualit527/qec-ai-decoder.已展示 7 / 7 个已收集 Skill。
skill
职业分类
描述
更新
职业分类
软件开发工程师
描述
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.…
原文语言：英语
更新
职业分类
数据科学家
描述
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…
原文语言：英语
更新
职业分类
项目管理专家
描述
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.
原文语言：英语
更新
职业分类
软件开发工程师
描述
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.
原文语言：英语
更新
职业分类
高等院校社会学教师
描述
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.
原文语言：英语
更新
职业分类
数据科学家
描述
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…
原文语言：英语
更新
已展示 7 / 7 个已收集 Skill。