Agent skills for Claude Code

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).

Generates a current RFC 6238 TOTP two-factor code from a shared secret the user already holds, via a bundled zero-dependency script that…

Friendly onboarding tour of Claude Code capabilities for users asking what it can do.

Automatically trace Claude Code conversations to Braintrust for observability.

Parses local CLI transcripts and accurately attributes work packages and commits to specific AI sessions.

Track real-time cryptocurrency prices across exchanges with historical

This skill enables Claude to track and optimize resource usage across an application stack.

Define and track SLAs, SLIs, and SLOs for service reliability including availability, latency, and error rates.

Builds trade area and catchment analysis workflows in CARTO.

Query TradingView market data through the bundled tradingview MCP server without a desktop app or login.

Eliminates AI writing patterns, translationese, and Mainland Chinese terms to produce natural, authentic Traditional Chinese copy for…

Traefik changes since training cutoff (latest: 3.6.9) — multi-layer routing, Redis rate limiter, p2c/leasttime LB strategies, fast proxy…

Extract clean article text, metadata, and structured content from web pages using the Trafilatura command-line tool or Python API.

Searches and explores Burp Suite project files (.burp) from the command line.

Help address review/issue comments on the open GitHub PR for the current branch using gh

Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with…

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval…

Corrects speech-to-text transcription errors in meeting notes, lectures, and interviews using dictionary rules and AI.

Convert and browse session transcripts as HTML or Markdown.

After the learner demonstrates understanding of a concept, present near-transfer and far-transfer challenges.

This skill should be used when building payment systems, implementing token transfers, or adding ENS/social handle resolution.