27.4K skills · sorted by relevance
Improve mobile app listings on Apple App Store and Google Play Store through keyword research, competitor and review analysis, and listing revisions. Produce metadata suggestions, visual asset guidance, A/B test plans, and launch checklists.
Inspect browser storage and caches in a CTF sandbox to explain changes in authentication, page rendering, or requests. Compare clean and modified states, then document the smallest sequence that reproduces the relevant behavior.
Set up and manage DeepTutor from the command line, a text interface for running commands. Run learning tasks, build searchable document collections, manage sessions and notebooks, diagnose installation issues, and launch the server or Web app.
Prepare Windows desktop apps for Microsoft Store publication, from building and inspecting MSIX application packages to checking certification reports, completing store listings, submitting through Partner Center, and verifying publication status.
Analyze Zeek and NetFlow records for ransomware-related activity, including regular callbacks to attacker infrastructure, TOR connections, and possible data exfiltration. Combine indicators into risk scores and structured reports with timelines to support threat hunting and incident investigation.
Map attacker behaviors and indicators of compromise, or traces of an intrusion, to MITRE ATT&CK techniques. Build coverage heatmaps, compare threat groups, and identify monitoring gaps to guide detection improvements and threat intelligence reporting.
Find the replacement for a research command removed in OMX 0.21. This migration notice directs existing autoresearch-goal usage to $autoresearch, the canonical research loop that requires validation before proceeding.
Improve mobile app listings on Apple App Store and Google Play Store through keyword research, clearer descriptions, visual asset guidance, and review analysis. Create competitor reports, A/B test plans, and launch checklists to guide store page improvements.
Configure large language model pretraining with torchtitan across multiple GPUs. Covers ways to split training work, launch jobs on computing clusters, enable Float8 numerical processing, and save or resume training through distributed checkpoints.
Analyze competitors using deal outcomes, customer quotes, and public developments. Prepare tactics for a specific deal, battlecards—sales reference sheets for each competitor—and weekly updates that distinguish evidence from interpretation.
Find relevant Google Cloud monitoring metrics for a service or resource. Retrieves current metric definitions through the API, filters them by the requested concepts, and presents selected metrics with their names, data types, units, and monitored resources.
Develop fiction from existing ideas, notes, or partial drafts. Organize themes, character changes, plot, setting, relationships, reader knowledge, and prose, then use writer-approved plans to guide drafting and revision from short stories to book series.
Configure large language model pretraining with torchtitan across multiple GPUs. Covers ways to split training work, launch jobs on computing clusters, enable Float8 numerical processing, and save or resume training through distributed checkpoints.
Find GitHub projects using keywords, minimum stars, and update dates, then collect repository details and contributor profiles through BrowserAct. Results include project descriptions, contributor biographies, personal websites, and Twitter handles for research, recruiting, or collaboration scouting.
Convert existing PyTorch training code into an NVFLARE federated learning job, where sites train with their own data. Adapt training and evaluation, exchange model updates through the Client API, validate locally, and export the job.
Use Nexscope data to find and analyze competitors on Amazon, covering 12 marketplaces, with product metrics including sales, BSR, pricing, ratings, and growth trends. Trigger when the user mentions competitor lookup, competitor analysis, ASIN reverse lookup, competitive product research, finding similar products, market competitor discovery, product benchmarking, competitor sales estimation, analyzing competitor listings, competitor analysis, ASIN reverse lookup, competitor sales, competitor research, Nexscope, market competitor discovery, competitor trends. Even if the user does not explicitly mention "Nexscope" or "competitor lookup", if their need involves discovering and analyzing Amazon competitors by ASIN, keyword, seller name, brand, or category, this skill should also be triggered.
The English summary is being prepared. Showing the original description.
Locate CCSPlayerInventory::SendInventoryUpdateEvent in CS2 server.dll / libserver.so via IDA Pro MCP and emit a fresh, minimal-unique signature or offset for the WeaponPaints gamedata entry "CCSPlayerInventory::SendInventoryUpdateEvent" (symbol CCSPlayerInventory_SendInventoryUpdateEvent). Shortlist via functions constructing the inventory-full-update usermessage/event around m_pSOCache contents for the owning controller. The body packs the SO cache snapshot and sends it via the GC/usermessage path. Cross-check with callers in inventory-dirty flows (weapon paint mutations). Trigger: CCSPlayerInventory_SendInventoryUpdateEvent, CCSPlayerInventory::SendInventoryUpdateEvent
The English summary is being prepared. Showing the original description.
Helps organize PyTorch model training with LightningModule and Trainer, including validation, logging, model saving, and early stopping. It also guides distributed training across multiple GPUs and settings for reduced-precision computation.
Audit App Store or Google Play listings across six areas, including text, visuals, and reviews. Get a weighted score, specific copy and image recommendations, optional competitor comparisons, and prioritized changes tailored to the store and brand maturity.
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular property prediction, molecule generation, protein modeling, and knowledge graph reasoning. Connect datasets, models, training tasks, and evaluation while checking version compatibility and common implementation errors.
Refactor TypeScript code that handles several variants in multiple places using frozen classes and a Visitor interface, which defines a handler for each variant. This helps type checking expose missing handlers when new variants are added.
Check industrial process data servers for unauthorized clients and suspicious data patterns using a Python detector. Provides alerts for missing or constant values and investigation checks for attackers moving between IT and operational technology networks.
Map threat groups’ documented attack techniques in MITRE ATT&CK Navigator. Creates visual layers and heatmaps, compares groups, and highlights techniques missing from existing detection coverage to support security reporting and decisions about detection priorities.
Organize PyTorch training code with LightningModule and Trainer. Follow examples for validation, logging, model saving, and distributed training across multiple GPUs, with callbacks that add monitoring or stop training when progress stalls.