Skills Lllllllama

Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of `current_research` with auditable repo understanding, idea gating, fair comparison, and governed experiments written to `explore_outputs/`. Do not use for README-first trusted reproduction, open-ended direction finding,...

Orkestrator mode reproduksi RigorPilot untuk reproduksi repositori deep learning yang mengutamakan README. Gunakan saat pengguna menginginkan alur menyeluruh yang dapat dipercaya secara minimal, yang membaca repositori terlebih dahulu, memilih target inferensi atau evaluasi terdokumentasi terkecil, mengoordinasikan penerimaan, pengaturan, eksekusi tepercaya, pelatihan tepercaya opsional, analisis repositori opsional, dan resolusi celah makalah opsional, menerapkan aturan tambalan konservatif, mencatat bukti, asumsi, penyimpangan, dan titik keputusan manusia,...

Keterampilan hanya-baca Rigor Analyze / Rigor Audit untuk repositori riset pembelajaran mendalam. Gunakan ketika pengguna ingin membaca dan memahami repositori, memeriksa struktur model serta titik masuk pelatihan atau inferensi, meninjau konfigurasi dan titik penyisipan, atau menandai pola implementasi yang mencurigakan tanpa memodifikasi kode atau menjalankan pekerjaan berat. Jangan gunakan untuk eksekusi perintah aktif, refaktorisasi luas, adaptasi kode spekulatif, atau perbaikan bug otomatis.

Keterampilan Rigor Setup untuk reproduksi repositori deep learning yang mengutamakan README. Gunakan ketika tugas secara spesifik adalah menyiapkan lingkungan conda-first yang konservatif, asumsi jalur checkpoint dan dataset, petunjuk lokasi cache, serta catatan pengaturan sebelum menjalankan repositori yang didokumentasikan dengan README. Jangan gunakan untuk pemindaian repositori, orkestrasi penuh, interpretasi makalah, pelaporan hasil akhir, atau pengaturan lingkungan generik yang tidak terkait dengan target reproduksi tertentu.

Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together meaningful low-risk migration ideas with rollback-aware records in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted...

Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with fair-comparison caveats and no-overclaim summaries in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline...

Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.

Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or...

Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.

Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to standardized `train_outputs/`. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.

Keterampilan Rigor Debug / Rigor Audit untuk pekerjaan riset pembelajaran mendalam. Gunakan ketika pengguna menempelkan traceback, error terminal, CUDA OOM, kegagalan muat checkpoint, ketidakcocokan bentuk, gejala kehilangan NaN, atau kegagalan pelatihan dan menginginkan diagnosis konservatif sebelum melakukan penambalan apa pun, dengan perbaikan debug yang dipisahkan secara jelas dari kontribusi riset. Jangan gunakan untuk refaktorisasi luas, adaptasi spekulatif, penambalan eksploratif otomatis, atau pengenalan repositori umum.