Happysquad Loop — Testing skill for Claude Code
Run the full happysquad loop (architect → implement → test → conflict-gate → review) on a task, iterating until pass or the round cap.
How to install Happysquad Loop
Installs to ~/.claude/skills/jakkajee11-happysquad-happysquad-loop/SKILL.md
mkdir -p ~/.claude/skills/jakkajee11-happysquad-happysquad-loop && curl -fsSL https://raw.githubusercontent.com/jakkajee11/happysquad/HEAD/commands/happysquad-loop.md -o ~/.claude/skills/jakkajee11-happysquad-happysquad-loop/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Happysquad Loop does
description: Run the full happysquad loop (architect → implement → test → conflict-gate → review) on a task, iterating until pass or the round cap. Auto-detects parallel workstreams from the architecter's design and dispatches implementer/tester in parallel waves when safe. argument-hint: [--no-parallel] [--worktree]
Load the `squad-loop` skill, then drive the full hand-off loop for the task described in `$ARGUMENTS`.
Concretely:
- Read `${CLAUDE_PLUGIN_ROOT}/skill
Alternatives in Testing
- Deslop Reborn — One iteration of the IronClaw Reborn de-slop loop — take ONE Reborn crate, fan out parallel review sub-agents 12.6k ★
- Add Plugin — Integrate a spec-driven/skill framework as a bundled agtx plugin 1.5k ★
- Adversarial Spec — A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until a 514 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
MultiAgentGameStudio
Claude Code plugin for spec-driven multi-agent builds. A Main Architect splits a spec into module folders with
Module Pipeline
Claude Code plugin for spec-driven multi-agent builds. A Main Architect splits a spec into module folders with
Implement Phase
Autonomously execute a whole roadmap phase - resolve features to specs, create missing ones, then loop impleme
Spec Impl Task
Implement one or more vertical-slice tasks from tasks.md. Accepts task IDs (1.2) or whole groups (1). Auto-tic
Piv
Self-recursive development loop with real auth testing, live DB research, 100% test pass requirements, and MAN
Feature Team
Run a multi-task plan with the implementer→spec-review→quality-review loop using the model ladder. For COMPLEX
Related Agents
ChatGPT PR Review
Coordinates ChatGPT PR review round-by-round in a dedicated session (manual / automated / parallel modes). Rea
Omd Final QA
Read-only final-gate critic. Enforces an 8-item rubric. Hard 2-round revision cap. Forbids 'looks good' rubber
Gan Generator
Implement the plan produced by gan-planner against the named files. Returns proposed changes as unified diffs