Coordinate Parallel Development Agents
Large coding tasks become slow when independent work is handled sequentially. This skill groups dependencies, dispatches isolated agents, verifies results, and integrates completed branches.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "team-dev" from https://skillstore.io/skills/cubha-team-dev.md and its manifest at https://skillstore.io/api/skills/cubha-team-dev/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "team-dev". Plan authentication API, profile page, and shared user types.
Expected outcome:
The shared user types form the first group. The authentication API and profile page follow in a parallel second group.
Using "team-dev". Implement four independent validation functions with TDD.
Expected outcome:
Using "team-dev". Run a dry analysis for a dashboard migration.
Expected outcome:
The skill returns dependency groups, target files, and blocking relationships without modifying the repository.
Four command-execution findings are confirmed because the workflow runs repository-provided tests and verification scripts. Sixteen Markdown backtick findings and four entropy findings are false positives, but prompt propagation and automatic integration create additional security concerns.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/cubha-team-dev/audits/3?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/cubha-team-dev?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/cubha-team-dev?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/cubha-team-dev/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/cubha-team-dev.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>cubha. (2026). team-dev security audit report (audit version 3) [Author version unspecified]. Skillstore. https://skillstore.io/skills/cubha-team-dev/audits/3@techreport{cubha-cubha-team-dev-2026,
author = {cubha},
title = {team-dev security audit report (audit version 3)},
institution = {Skillstore},
year = {2026},
number = {3},
url = {https://skillstore.io/skills/cubha-team-dev/audits/3},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "team-dev security audit report (audit version 3)"
version: "unspecified"
type: report
authors:
- name: "cubha"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/cubha-team-dev/audits/3"
identifiers:
- type: other
value: "skillstore:cubha-team-dev:audit:3"
description: "Skillstore immutable audit report identifier"
Split a large feature into isolated modules and implement independent modules concurrently.
Group migration tasks by shared files and dependencies before assigning work to separate agents.
Identify deterministic logic tasks, create failing tests first, and verify integrated results.
Analyze these subtasks for dependencies and show parallel groups without implementing anything: {subtasks}. Use dry-run mode.Implement {feature} with team development. Separate the work into clear subtasks, show the dependency groups, and wait for approval.Implement these logic tasks in parallel with TDD enabled: {subtasks}. Confirm valid failing tests before writing implementation code.Coordinate {migration_goal} across {modules}. Preserve project conventions, map cross-module dependencies, limit agents to five, and stop automatic progress after any verification failure.Author
cubhaLicense
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Ref
c43861a65bb95efcae259cd161c9d6f4dc7eec6f
Maintenance freshness
7/24/2026
Usage
0 downloads Β· 1 views
File structure
Check designs with deterministic CSS rules
Design reviews can vary between reviewers and slow down delivery. This skill applies repeatable checks to HTML and CSS so teams can catch token, layout, and accessibility issues before release.
Research Projects with Parallel Specialist Agents
Early project decisions often rely on incomplete technical and market evidence. This skill coordinates specialist agents and combines sourced findings into a structured research report.
Stress-Test Decisions With a Review Panel
Important decisions can retain hidden assumptions when reviewed by one perspective. This skill assigns independent review lenses and combines concrete findings before you finalize a plan.
Analyze Existing Codebases in Depth
Existing codebases often lack a clear view of architecture, quality risks, and technical debt. This skill combines repository inspection with focused research and produces a prioritized Markdown report.
Document Your Existing Design System
Existing projects often lack a clear record of their interface decisions. This skill extracts design tokens and current UX structure into practical documentation for future UI work.
Run feature scenario tests
Feature changes need repeatable validation before release. This skill creates and runs Playwright scenarios, then separates functional results from visual observations.
Design Multi-Agent Architectures
by ChakshuGautam
Complex agent work can fail when one context window carries every task. This skill helps Claude, Codex, and Claude Code design agent systems with clear handoffs.
Build Streamed Multi-Agent Workflows
by DNYoussef
Sequential AI workflows often lose context between steps. This skill defines stream-chain patterns that pass each result into the next task.
Practice Test-Driven Development
by DMJGilbert
AI coding agents often write implementation code before proving expected behavior with tests. This skill enforces a red, green, refactor workflow for safer feature work, bug fixes, and refactoring.
Coordinate Parallel Subagent Workflows
by DieGopherLT
Multi-agent work can fail when tasks overlap or depend on hidden context. This skill helps Claude, Codex, and Claude Code plan bounded subagent assignments.
Apply Test-Driven Development to Every Change
by Benny9193
Software changes often grow before their expected behavior is verified. This skill guides Claude, Codex, and Claude Code through focused Red-Green-Refactor cycles.
Coordinate Advanced Hive Mind Workflows
by DNYoussef
Large AI projects need clear agent roles, durable memory, and reliable decisions. This skill guides Claude Flow hive minds with queen-led coordination and consensus workflows.