trace-claude-code
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.
Problem-solving strategies for connectedness in topology
$ npx -y skills add parcadei/Continuous-Claude-v3 --skill connectedness --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/connectednessContext preview
The summary Claude sees to decide when to auto-load this skill.
Problem-solving strategies for connectedness in topology
name: connectedness description: "Problem-solving strategies for connectedness in topology" allowed-tools: [Bash, Read]
Use this skill when working on connectedness problems in topology.
1. **Is X connected?**
2. **Connectedness Proofs**
3. **Path Connectedness**
4. **Components**
uv run python -m runtime.harness scripts/z3_solve.py prove "no_separation"
uv run python -m runtime.harness scripts/sympy_compute.py simplify "(1-t)*x + t*y"
uv run python -m runtime.harness scripts/z3_solve.py prove "intermediate_value"
*From indexed textbooks:*
See `.claude/skills/math-mode/SKILL.md` for full tool documentation.
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