Loading...
Loading...
Found 137 Skills
Explore and analyze GitHub repositories related to a research topic. Reads deep-research output, discovers repos from multiple sources, deeply analyzes code, and produces integration blueprints.
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
Make every number in the final PDF traceable to the exact code line that produced it. Uses \hypertarget/\hyperlink LaTeX commands and \num{formula} evaluated at compile time. Use for reproducibility and data integrity verification.
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
Use this skill for "review this paper", "review this manuscript", "peer review", "review my paper", "critique this manuscript", "review this submission", "give me feedback on my paper", "check my methods", "review my statistics", "review as a peer reviewer", "evaluate this manuscript", "review this PDF", or mentions manuscript review, peer review, paper critique, or methodological review.
Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.
This skill should be used when executing the epic-dev workflow, creating epic branches, managing sprint phases, working with git worktrees for phased feature development, or when the user mentions "epic workflow", "sprint phases", "phased development", or "git worktree workflow".
Guide a focused CS or AI literature review sprint that turns a topic, idea, claim, or project direction into a ranked paper map, closest-work risk assessment, method taxonomy, novelty implications, baseline implications, and next actions. Use this skill whenever the user needs to survey a topic, check novelty, map related work, prepare a project, find canonical or recent papers, decide read/skim/ignore priority, or turn papers into a research direction.
Plan and write strategic rebuttals after real paper reviews arrive. Use this skill whenever the user has OpenReview reviews, reviewer comments, scores, confidence ratings, meta-reviews, author response windows, or wants to decide which experiments to run, infer reviewer intent, draft point-by-point responses, prepare follow-up discussion replies, or improve wording after reviews for ML/AI venues such as NeurIPS, ICML, ICLR, CVPR, ACL, EMNLP, or similar conferences.
Diagnose surprising, negative, unstable, or ambiguous ML/AI experiment results and decide whether to debug implementation, rerun experiments, change metrics or baselines, revise the algorithm, narrow the paper claim, park, or kill a direction. Use this skill whenever results do not match expectations, a method fails, metrics conflict, seeds vary, baselines beat the method, plots look suspicious, or the user asks what to do next after experimental results.