Loading...
Loading...
Found 103 Skills
Project management expertise - agile methodology, estimation, risk management, stakeholder management
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.
Estimate software development tasks accurately using various techniques. Use when planning sprints, roadmaps, or project timelines. Handles story points, t-shirt sizing, planning poker, and estimation best practices.
This skill should be used when the user asks to 'broadcast transaction', 'send tx', 'estimate gas', 'simulate transaction', 'check tx status', 'track my transaction', 'get gas price', 'gas limit', 'broadcast signed tx', or mentions broadcasting transactions, sending transactions on-chain, gas estimation, transaction simulation, tracking broadcast orders, or checking transaction status. Covers gas price, gas limit estimation, transaction simulation, transaction broadcasting, and order tracking across Solana, Ethereum, Base, BSC, Polygon, Arbitrum, and 20+ other chains. Do NOT use for swap quote or execution — use okx-dex-swap instead. Do NOT use for general programming questions about transaction handling.
This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.
Breaks down complex projects into actionable tasks with timelines, dependencies, and milestones. Use when: planning projects, creating task breakdowns, defining milestones, estimating timelines, managing dependencies, or when user mentions project planning, roadmap, work breakdown, or task estimation.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Estimate project scope, timeline, and resource requirements using multiple estimation techniques including bottom-up, top-down, and analogous estimation methods for accurate project planning.
Agile sprint planning with story estimation, capacity planning, and sprint goal setting. Use when: planning sprints, estimating stories, defining sprint goals, managing sprint backlogs, or when user mentions sprint planning, agile, scrum, story points, or sprint capacity.
Causal inference specialist for causal discovery, counterfactual reasoning, and effect estimationUse when "causal inference, causal discovery, counterfactual, intervention effect, confounder, structural causal model, SCM, dowhy, causal graph, causal, dowhy, scm, dag, counterfactual, intervention, causalnex, confounding, ml-memory" mentioned.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Douyin Viral Copy Intelligent Generator. It is automatically triggered when the user says "generate new copy", "create Douyin content", or "write short video copy". It automatically executes: (1) Read and analyze historical data (2) Optimize with 9 viral factors (3) Multi-dimensional scoring evaluation (4) Automatic iterative optimization until it meets the 5-star standard (5) Intelligent play volume estimation (6) Output the fully optimized copy. Fully automated, no need to manually specify any analysis or optimization tasks.