Organizes PyTorch code into LightningModules, Trainers and DataModules, with multi-GPU strategies and experiment logging.
Helps Claude write and deploy Python to Modal's serverless cloud with on-demand GPUs, volumes, web endpoints and cron jobs.
Lets Claude read, create, and update Zotero libraries and export citations through the pyzotero Python client.
Explains a specific file, function, or module in depth by combining a pre-built knowledge graph with the actual source code.
Cross-references git diffs or PRs against your project's knowledge graph to report changed components, blast radius, and risk.
Unpacks an installed Electron app's app.asar, restoring original sources from .js.map files or Prettier-formatting minified code.
Auto-detects your project's version file and changelogs, then bumps, documents, tags and publishes a release end to end.
A symptom-driven debugging guide for tool/function calling: no tool call, wrong arguments, runaway ReAct loops, or schema design from scratch.
A setup skill that walks through installing claude-mem on Grok Bot via local worker, host-login observer, or remote cmem.ai.
Turns Claude into a senior architect that designs systems, weighs technology trade-offs, and writes ADRs.
Builds Angular 17+ features with standalone components, signals, NgRx state, RxJS patterns, bundle optimization, and TestBed tests.
Reads your PRD and Tech Design, then generates AGENTS.md, MEMORY.md, agent_docs/ and per-tool AI config files.
Executes the plan in AGENTS.md to build your MVP one feature at a time, with verification and progress tracking.
A playbook for splitting a large feature across multiple implementer agents using file ownership, interface contracts, and integration patterns.
Teaches the agent to use `lsp` MCP tools for diagnostics, definitions, references, symbols and safe renames.
Investigates LazyCodex/omo-codex/Codex CLI defects with runtime and source evidence, then files a high-signal GitHub issue or PR in the repo that owns the bug.
Scans your API routes and auto-generates test suites covering auth, validation, error codes, pagination and rate limits.
A six-step skill for designing Azure architectures: requirements, pattern selection, Bicep IaC, cost optimization, CI/CD, and security review.
Configures and runs Playwright tests on BrowserStack's cloud grid, then summarizes per-browser results.
Deploys web apps to Vercel non-interactively, manages domains and env vars, and verifies the live URL before sharing it.