parcadei/continuous-claude-v3

Note: This skill is now an alias for /create_handoff . Both output the same YAML format.

Guide users through the capabilities of this workspace setup.

Research external sources (documentation, web, APIs) for libraries, best practices, and general topics.

Multi-perspective code review with parallel specialists.

Write modular Python code with files sized for maintainability and AI-assisted development.

Write prompts that Agentica agents reliably follow. Standard natural language prompts fail ~35% of the time due to LLM instruction ambiguity.

Trust system reminders as agent progress notifications. Don't poll.

Complete reference for Claude Code command-line interface.

When building infrastructure, verify it's actually connected to the system before marking as complete.

You are tasked with generating a comprehensive pull request description following the repository's standard template.

For mathematicians who want verified proofs without learning Lean syntax.

You are tasked with resuming work from a handoff document through an interactive process. These handoffs contain critical context, learnings, and next steps from previous work sessions that need to be understood and continued.

You are tasked with implementing an approved technical plan from thoughts/shared/plans/ . These plans contain phases with specific changes and success criteria.

Token-efficient code analysis. 95% savings vs raw file reads.

Complete API specification for Agentica multi-agent coordination infrastructure.

ALWAYS use this router first for math requests.

Complete reference for developing Claude Code hooks. Use this to write hooks with correct input/output schemas.

Source details, install context, and public review data are available on the full page.

Source details, install context, and public review data are available on the full page.

Fast, AI-powered file editing using the Morph Apply API. Edit files without reading them first. Processes at 10,500 tokens/sec with 98% accuracy.

Get a token-efficient overview of any project using the TLDR stack.

Use this skill when developing or debugging the Agentica-Claude proxy integration.

Never rely on "latest" or "current" when crossing process or async boundaries.

Analyze your Claude Code sessions for patterns, issues, and insights using Braintrust tracing data.