Squad Assemble — Testing skill for Claude Code
Analyze a spec/requirement and produce a recommended team composition (review mode, models, specialists, limited external-executor roles) gated behind explicit approval.
How to install Squad Assemble
Installs to ~/.claude/skills/jakkajee11-happysquad-squad-assemble/SKILL.md
mkdir -p ~/.claude/skills/jakkajee11-happysquad-squad-assemble && curl -fsSL https://raw.githubusercontent.com/jakkajee11/happysquad/HEAD/commands/squad-assemble.md -o ~/.claude/skills/jakkajee11-happysquad-squad-assemble/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Squad Assemble does
description: Analyze a spec/requirement and produce a recommended team composition (review mode, models, specialists, limited external-executor roles) gated behind explicit approval. Run before /happysquad-loop on non-trivial work. argument-hint:
Load the `team-assembly` skill at `${CLAUDE_PLUGIN_ROOT}/skills/team-assembly/SKILL.md` and run the full procedure.
Steps:
- Resolve the spec: if
$ARGUMENTSis a file path, Read it; otherwise treat `$AR
Alternatives in Testing
- Inkline — by inkline - Structures development workflow using pnpm with emphasis on TypeScript and Vue 3 Composition API 1.4k ★
- Adversarial Spec — A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until a 514 ★
- Create E2e — Create a Playwright E2E test with explicit success criteria 335 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
AutoConst Spec Index Claude
Index a 500+ page construction specifications book into a queryable SQLite database. Extracts every division,
Public Browser
Token-efficient Chrome browser automation MCP server for AI agents. Direct CDP, a11y-tree refs, multi-tab, ser
Assemble
Assemble the film — narrate, ASR-verify pronunciation, build, test, check — looping until green or reporting i
Brand Auto
Brand-auto — bounded autonomous brand work. Brand-orchestrator routes to Durham specialists (Aaker/Kotler/Glas
Happysquad Loop
Run the full happysquad loop (architect → implement → test → conflict-gate → review) on a task, iterating unti
Squad Implement
Run only the implementer agent against the current run's design document. Does not auto-advance to testing.
Related Agents
Primer Squad
Coordinator for the Primer specialists (payments, workflows, 3DS, performance, tokenization, integrations). Us
Harness Eng Lead
Engineering lead — routes each task to one of five specialists by consult-when, owns architecture review for i
Pan Release
Release squad agent for the bot-army campaign. Ships approved, green work safely behind a human gate — squash-