trace-claude-code
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.
QLTY During Development
$ npx -y skills add parcadei/Continuous-Claude-v3 --skill qlty-during-development --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/qlty-during-developmentContext preview
The summary Claude sees to decide when to auto-load this skill.
QLTY During Development
name: qlty-during-development description: QLTY During Development user-invocable: false
Run QLTY checks during code writing to catch issues early.
Run QLTY after significant code changes:
# Quick lint check qlty check # Format code qlty fmt # Check specific files qlty check src/sdk/providers.ts # Auto-fix issues qlty check --fix
After writing code: 1. Run `qlty check` on changed files 2. If errors, fix them before proceeding 3. Run `qlty fmt` to ensure formatting
A persistent, learning, multi-agent development environment built on Claude Code Continuous Claude transforms Claude Code into a continuously learning system that maintains context across sessions, orchestrates specialized agents, and eliminates wasting
Repo: parcadei/Continuous-Claude-v3
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.
Guide for integrating Agentica SDK with Claude Code CLI proxy
Reference guide for Agentica multi-agent infrastructure APIs