skills.rest
doubleuuser
doubleuuserCOMMUNITY
Explore all skills by this author →
GitHub

rlm-subagent

Orchestrate parallel subagent execution for implementation, review, and testing tasks.

67|2|Updated Feb 7, 2026
Search Tags:#workflow#testing#tdd#subagent#code-review#task-orchestration#parallel-execution
One-click install
npx skills add https://github.com/doubleuuser/rlm-workflow --skill rlm-subagent
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rlm-subagent
Source: https://github.com/doubleuuser/rlm-workflow/tree/main/skills/rlm-subagent
Command: npx skills add https://github.com/doubleuuser/rlm-workflow --skill rlm-subagent

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables safe, efficient parallelization of implementation, code review, and testing across independent sub-phases while providing an automatic sequential fallback when subagents or task primitives are unavailable.

Core Features & Use Cases

  • Parallel Mode Dispatch: Detects platform capabilities and dispatches implementer, reviewer, and test subagents for independent sub-phases.
  • Sequential Fallback: Executes sub-phases sequentially in the main agent when subagents are not available, preserving TDD discipline and extended self-review.
  • Two-stage Review and Aggregation: Enforces spec and code-quality reviews, aggregates test results, summarizes pass/fail counts, and documents artifacts for traceability and approval gates.
  • Use Case: Break a multi-domain feature into API, UI, and database migration sub-phases, dispatch implementers in parallel, run code-review subagents, then aggregate integration and E2E test results.

Quick Start

Dispatch parallel implementer subagents for independent sub-phases and fall back to sequential execution if subagents are unavailable.

Frequently Asked Questions about rlm-subagent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run parallel code review and testing across independent feature phases?▼

Parallel code review and testing across independent feature phases is orchestrated by dispatching implementer, reviewer, and test subagents concurrently, then aggregating pass/fail results and documenting artifacts for approval gates.

What happens if subagent task primitives are unavailable during workflow orchestration?▼

When subagent task primitives are unavailable, the workflow automatically falls back to enforced sequential execution within the main agent, preserving TDD discipline, two-stage reviews, and artifact documentation.

How do I break a multi-domain feature into concurrent sub-phases for implementation?▼

Multi-domain features are broken down by detecting independent sub-phases like API, UI, and database migrations, dispatching implementer subagents in parallel for each, followed by parallel code-review and aggregated E2E testing.

Can I maintain TDD discipline while dispatching parallel implementation tasks?▼

TDD discipline is maintained during parallel implementation by enforcing two-stage spec and code-quality reviews through reviewer subagents, aggregating integration test results, and documenting all artifacts for traceability.

Does parallel task dispatch work without explicit subagent dependencies?▼

Parallel task dispatch works without explicit dependencies by applying platform capability detection at runtime, routing to parallel subagents if supported, or executing sub-phases sequentially in the main agent as a safe fallback.

Related Skills

Explore More Software Engineering Skills→
timzaaktimzaak
64

t-run

Coordinate multi-phase software development by dispatching tasks to specialized sub-agents.

Community
Advanced
proffesor-for-testingproffesor-for-testing
436

shift-left-testing

Generate and execute unit, integration, and end-to-end tests within CI/CD workflows.

Community
Advanced
jacexhjacexh

subagent-driven-development

Dispatch fresh subagents per task with two-stage spec and code quality reviews.

Community
Advanced
try-workstry-works
4

rlm-subagent

Coordinate parallel RLM sub-phase execution with sequential fallback and two-stage reviews.

Community
Advanced