Compute AND return in ONE block. Multiple blocks means only first executes.
# GOOD: Single block
content = await view_file(path)
return any(c.isdigit() for c in content)
# BAD: Split blocks (second block never runs)
content = await view_file(path)
---
**Source:** [`parcadei/Continuous-Claude-v3`](https://github.com/parcadei/Continuous-Claude-v3) → `.claude/skills/async-repl-protocol/SKILL.md`
**Also appears in:** `parcadei/Continuous-Claude-v3/.claude/skills/archive/async-repl-protocol/SKILL.md`
1---2name: async-repl-protocol3description: "Async REPL Protocol"4category: general-purpose5source_repo: parcadei/Continuous-Claude-v36source_path: ".claude/skills/async-repl-protocol/SKILL.md"7source_url: https://github.com/parcadei/Continuous-Claude-v3/blob/HEAD/.claude/skills/async-repl-protocol/SKILL.md8metadata:9 source: https://skillmd.com/skills/parcadei/async-repl-protocol10---111213# Async REPL Protocol1415When working with Agentica's async REPL harness for testing.1617## Rules1819### 1. Use `await` for Future-returning tools2021```python22content = await view_file(path) # NOT view_file(path)23answer = await ask_memory("...")24```2526### 2. Single code block per response2728Compute AND return in ONE block. Multiple blocks means only first executes.2930```python31# GOOD: Single block32content = await view_file(path)33return any(c.isdigit() for c in content)3435# BAD: Split blocks (second block never runs)36content = await view_file(path)3738---3940**Source:** [`parcadei/Continuous-Claude-v3`](https://github.com/parcadei/Continuous-Claude-v3) → `.claude/skills/async-repl-protocol/SKILL.md`4142**Also appears in:** `parcadei/Continuous-Claude-v3/.claude/skills/archive/async-repl-protocol/SKILL.md`
Run npx get-skill add parcadei/async-repl-protocol in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Async REPL Protocol It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
parcadei (@parcadei) published this skill. Their other Agent Skills are listed on their SkillMD profile.