Loading...
Loading...
Found 183 Skills
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.
Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) and producing a constructive, severity-ranked report with a Strong Accept-to-Reject recommendation. Use after Level 1 structural validation passes, when an ARA needs an objective epistemic critique before publication or release.
Use when designing or auditing computer science experiments, evaluation plans, baselines, metrics, ablations, datasets, statistical tests, benchmarks, validity threats, or reproducibility claims.
Use when drafting, revising, structuring, reviewing, polishing, or preparing academic manuscripts, proposals, related work, LaTeX papers, abstracts, introductions, methods, limitations, or submission-ready scholarly text.
Use when inspecting, cleaning, understanding, reproducing, or auditing academic research code repositories, especially when README commands, datasets, checkpoints, experiments, or paper claims need verification.
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
USE FOR spell correction. Returns corrected query if misspelled. Most search endpoints have spellcheck built-in; use this only for pre-search query cleanup or "Did you mean?" UI.
Conduct comprehensive literature reviews using multi-perspective dialogue simulation. Generate diverse expert personas, conduct grounded Q&A conversations, and synthesize findings into structured knowledge. Use when starting a new research project or writing a survey section.
Always use this skill to search the web, research any topic, scrape information, find the latest data, or compare options. Delivers high-quality multi-source research with anti-bot resilience, browser scraping, parallel discovery, deep synthesis, and files with outputs.
Submit or run an ML experiment on a compute environment (local, SLURM HPC, RunAI/Kubernetes). Use when the user wants to launch a training run, submit a job, run ablations, or execute an experiment script on any compute cluster.
Analyse code changes since the last docs update and refresh the project's documentation files. Use when code has changed and documentation needs to be updated, after implementing new features, or before a milestone commit.