238 skills · sorted by relevance
Help a long-running agent reconnect with the intended product outcome after context compaction or a major work transition. Trace the current work hierarchy and read relevant source files to rebuild grounding before the next consequential action.
Check deliverables before marking a task complete. Review the requested file format, confirm every reference file was used, and compare the result with the original request to catch omissions and work that misses the goal.
Coordinate feature development from product direction through architecture, planning, validation, and implementation. Run the whole workflow or start at a selected stage, with saved decisions, review checkpoints, and a final pull request.
Create a reusable command with explicit preconditions, numbered actions, checks after each step, and error handling. This template provides a structure to customize so Claude verifies the required context before starting a defined workflow.
Supports development with code quality and security checks, change impact analysis, documentation templates, and coordination across multiple agents. It defines checkpoints for new modules and refactoring, plus roles and file ownership rules for parallel work.
Manage terminal work across panes: open jobs, run commands, read output, and wait for completion. Report agent status, exchange messages, and request human decisions through tuios, a terminal window manager with a background service.
Find interrupted Copilot CLI sessions in stored history, review conversations, checkpoints, files, and linked issues or pull requests, then resume unfinished work with the context needed to understand where it stopped.
Find your way around Diverga with a guide to its 24 research agents across nine categories. View commands, example requests, direct invocation syntax, and checkpoints where people review research decisions, with recommendations based on research context.
Prepare research papers for RAG, a method that supplies retrieved documents to AI. Download PDFs, extract and split text, and build a local searchable database, with parallel processing for document batches.
Coordinate a seven-stage literature review, from defining a research question to collecting and screening papers, building a searchable knowledge database, and producing PRISMA documentation. Specialized agents handle execution, with human approval at key decisions.
Coordinate research from question development through literature searches, analysis, and publication with specialized agents. Supports quantitative, qualitative, and mixed methods studies, plus systematic reviews, with human approval at key decisions about research direction and methods.
Keep research progress, decisions, and pending checkpoints across sessions. Store project context locally, recover essential details when returning, and track why decisions changed so research work can resume with a clear next step.
Revise formulaic academic prose through staged vocabulary and structure edits while checking that citations, statistics, and technical terms remain intact. Choose sections and editing intensity, compare changes, and review progress before accepting the revised manuscript.
Coordinate research, drafting, citation and data verification, AI review, revision, and final formatting through connected skills. Start from a research topic, an existing manuscript, or reviewer comments, with progress tracking and user checkpoints.
Estimate how an intervention affects outcomes using Bayesian causal analysis. The workflow confirms causal assumptions with the user, selects a suitable method, checks whether findings withstand challenges, and reports effects with uncertainty and limitations.
Plan philosophy and interdisciplinary papers by comparing preprint platforms, searching literature, identifying unanswered questions, and assessing originality. Receive a detailed outline with section word counts, key citations, and improvements based on a reviewer-style assessment.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
The English summary is being prepared. Showing the original description.
Validate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling.
The English summary is being prepared. Showing the original description.
Set up the public CodonFM v1 repository and download public Encodon checkpoints. Use for requests to build or launch the CodonFM development container, configure local data/checkpoint mounts, verify GPU access, or download public Encodon 80M, 600M, 1B, or Cdwt-1B weights. Do not use for Decodon, Encodon 5B/10B, missense-aggregation, or codon-optimization setup because those implementations are not in the public repository.
The English summary is being prepared. Showing the original description.
Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning. Use when a user explicitly asks to fine-tune CodonFM or Encodon for regression or classification. Support generic public-v1 Encodon workflows only; reject Decodon, MissenseDataset, missense_synom_agg, and generation workflows.
The English summary is being prepared. Showing the original description.
Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint, cosmos defect generation, cosmos-predict2 defect, cosmos-anomalygen, cosmos predict2 finetune.
The English summary is being prepared. Showing the original description.
Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.
The English summary is being prepared. Showing the original description.
Run the root-level workflow runtime policy or rule-based rollouts and verify simulator success. Use for evaluation, checkpoints, or local controllers; do not use for replay or dataset annotation.
The English summary is being prepared. Showing the original description.
Continue KERMT pretraining on a custom SMILES corpus with a grover_base, cmim, or hybrid checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized training and write model bundles, prepared data, logs, and checkpoints to user-selected host directories.
The English summary is being prepared. Showing the original description.