skills.rest
zhixuan312
zhixuan312COMMUNITY
Explore all skills by this author →
GitHub

mma-explore

Orchestrate parallel codebase investigation, external research, and journal recall into cited directions.

5|4|Updated Apr 9, 2026
Search Tags:#planning#research#codebase#orchestration#parallel#synthesis#journal
One-click install
npx skills add https://github.com/zhixuan312/multi-model-agent --skill mma-explore
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mma-explore
Source: https://github.com/zhixuan312/multi-model-agent/tree/main/packages/server/src/skills/mma-explore
Command: npx skills add https://github.com/zhixuan312/multi-model-agent --skill mma-explore

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrating divergent landscape exploration for planning, this skill orchestrates parallel internal-codebase investigation, external multi-source research, and prior-learnings recall to surface 3–5 distinct directions for decision-making.

Core Features & Use Cases

  • Parallel orchestration of internal investigation, external research, and journal recall to produce a set of viable directions.
  • Synthesis of results into 3–5 distinct directions with citations to sources and prior learnings.
  • Designed for exploratory planning; avoids convergent single-answer prompts and supports cross-domain evaluation.

Quick Start

Dispatch the three delegated skills in parallel and synthesize 3–5 distinct directions from internal, external, and journal sources.

Frequently Asked Questions about mma-explore

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

FAQPage Schema
How do I explore a codebase and external sources in parallel for planning?▼

Parallel codebase exploration orchestrates internal investigation, external multi-source research, and prior learnings recall simultaneously to synthesize 3–5 distinct, citable directions for cross-domain evaluation.

What is divergent landscape exploration in software engineering?▼

Divergent landscape exploration is a planning mechanism that runs parallel investigations across code, external sources, and project history to surface multiple viable directions, avoiding premature convergent single-answer prompts.

How do I synthesize distinct research directions with citations from multiple sources?▼

Synthesize distinct research directions by coordinating parallel investigation, external research, and journal recall calls, then ranking the aggregated results into 3–5 directions with citations to sources and prior learnings.

Does parallel orchestration work for exploratory planning without converging on a single answer?▼

Yes, parallel orchestration is explicitly designed for exploratory planning, supporting cross-domain evaluation by synthesizing multiple distinct directions rather than forcing a convergent single answer.

Can I recall prior project learnings while investigating a codebase simultaneously?▼

Yes, you can recall prior learnings while investigating a codebase by dispatching journal recall and internal investigation as parallel delegated calls, ensuring project history informs current code analysis.

Related Skills

Explore More Software Engineering Skills→
balic-AI-ML-R-D-Resourcesbalic-AI-ML-R-D-Resources

security-audit-context-building

Map architecture, trust boundaries, and data flows for security audit scoping.

Official
Advanced
CygnusfearCygnusfear
5

the-archivist

Document engineering decisions as ADRs with rationale and decision logs.

Community
Advanced
Jamie-CuiJamie-Cui
28

research-explore

Decompose research questions, delegate sub-tasks to an explore agent, and synthesize findings into a structured report.

Community
Advanced
ai-ecoverseai-ecoverse
28

workflows

Orchestrate parallel sub-agent runs with automatic result aggregation.

Official
Intermediate