1.4K skills · sorted by relevance
Coordinates specialist agents in Claude Code to work from product requirements through design, implementation, testing, deployment, and operations. Includes task queues, saved progress, parallel reviews, and recovery workflows for managing extended development work.
Deploy language models with vLLM through an OpenAI-compatible API or offline batch processing. Tune response speed, throughput, and GPU memory use with quantization, which reduces numerical precision, and execution across multiple GPUs.
Helps speed up LLM text generation by comparing methods that predict and verify multiple tokens at once. Covers draft model selection, Medusa prediction heads, Lookahead Decoding settings, and deployment examples for inference services.
Get guidance on distributed training with PyTorch FSDP, which splits model parameters across devices. The skill covers implementation, mixed precision, moving data to CPU memory, communication setup, and debugging distributed training code.
Split independent debugging or repair tasks among multiple AI agents. Define a focused scope, constraints, and expected report for each agent, then review their changes, check for conflicts, and test the combined result.
Build and train Mixture of Experts models, which activate selected specialist networks for each input. Use DeepSpeed or HuggingFace workflows to configure routing, balance workloads, distribute experts across GPUs, and optimize inference.
Create a detailed chapter-by-chapter reading companion from an EPUB or PDF, connecting the book’s ideas to experiences and words saved in your personal knowledge store. The result highlights parallels without prescribing actions.
Prepare finalized contracts for electronic signature by checking attachments, legal entity names, and authorized signers. Configure signing order and copy recipients, then send through a connected signature service or prepare instructions for manual signing.
Design workflows in which AI agents handle multiple steps or specialist tasks. Choose a suitable structure, generate starter configurations, and define information handoffs, retries, validation checks, and limits on cost and context size.
Manage parallel feature development with Git worktrees, separate working folders for different branches. Assign distinct ports, copy environment files, optionally install dependencies, and check for uncommitted changes and merged branches before removing outdated worktrees.
Evaluate a Claude Managed Agent against a written rubric, a set of checkable criteria, and guide improvements within a fixed attempt limit. After a version passes, prepare separate evaluation cases to check performance beyond the examples used for revision.
Deploy n8n on a Linux server using Docker Compose and Caddy for automatic HTTPS. Covers single-instance setups, workers for parallel execution, secret management, deployment checks, updates, backups, and restoration.
Coordinate four AI researchers to examine a company's business, finances, competition, and management risks in parallel. Combine sourced findings into an investment report with valuation checks, arguments for and against investing, and suggested price ranges.
Run TVM's TIRx compiler tests alongside tirx-kernels import and correctness checks. It verifies the local build, selects GPUs, runs parallel tests, saves full logs, and guides failure investigation and result reporting.
Train Mixture of Experts models, which activate selected specialist networks for each input. The skill guides architecture, input routing, workload balancing, and GPU distribution using DeepSpeed or HuggingFace, with examples for training configuration and inference optimization.
Reduce LLM generation delays with speculative decoding, which proposes tokens ahead of verification. This skill compares small draft models, Medusa, and Lookahead Decoding, with implementation examples, tuning guidance, and deployment using vLLM.
Deploy language model APIs and run batch generation with vLLM. Configure GPU memory use, quantization—lower precision model storage—and distribution across GPUs, then test response times and monitor how many requests the server handles.
Manage parallel tracks of milestone work with commands to create, list, switch, inspect, archive, and resume them. View each track’s phase status or a combined progress summary in a readable format.
Analyze an existing codebase with parallel agents and produce seven structured documents covering technology, integrations, architecture, conventions, testing, and concerns. Use the results to understand an unfamiliar project or prepare for major changes.
Routes GSD project management requests to the appropriate skill for configuration, workspace management, parallel work, pausing and resuming tasks, shipping completed work, and maintenance. It also covers inbox processing, project statistics, and command guidance.
Run a quick first review of code changes with six specialist agents working in parallel. They check logic, input and output, shared state, resources, missing behavior, and API completeness, then combine duplicate findings into a report ranked by confidence.
Investigate independent bugs or test failures concurrently by assigning each problem area to a separate agent. Define clear boundaries and expected reports, then review the fixes, check for conflicts, and run the full test suite before integration.
Design workflows where specialized AI agents share recurring product management tasks. Define each agent’s role, required information, handoffs, and human review points, then create monitoring and evaluation plans for the overall workflow.
Improve CircleCI build and test pipelines by identifying slow or unreliable jobs, then adjusting caching, data sharing between jobs, triggers, and parallel execution. Receive incremental configuration changes with expected effects, validation criteria, and rollback guidance.