Skip to main content
تشغيل أي مهارة في Manus
بنقرة واحدة
qualit527
ملف منشئ GitHub

qualit527

عرض على مستوى المستودعات لـ 7 skills مجمعة عبر 1 مستودعات GitHub.

skills مجمعة
7
مستودعات
1
محدث
2026-04-25
مستكشف المستودعات

المستودعات و skills الممثلة

demo-presenter
الكتّاب التقنيونالمنتجون والمخرجون

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.

2026-04-25
review-framework
مطوّرو البرمجيات

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. Use after a run completes when the user asks "what should we change before the next run?" or feels the system is plateauing.

2026-04-25
autoqec-run
علماء البيانات

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 asks "run AutoQEC on <env>", "start a research round", or provides an EnvSpec YAML.

2026-04-24
read-zulip
متخصصو إدارة المشاريع

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.

2026-04-23
diagnose-failure
مطوّرو البرمجيات

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.

2026-04-22
review-log
معلمو علم الاجتماع في التعليم العالي

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.

2026-04-22
verify-decoder
علماء البيانات

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 artifact.

2026-04-22
عرض 1 من أصل 1 مستودعات
تم تحميل كل المستودعات