ARA Research Manager
Skill Verified ActiveRecords research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.
To provide an auditable trace of how AI-assisted research actually evolved, ensuring that all significant discoveries and decisions are captured systematically.
Features
- Records research provenance as a post-task epilogue
- Scans conversation history for decisions, experiments, dead ends, claims, heuristics, and pivots
- Writes extracted information into the 'ara/' directory
- Applies user-vs-AI provenance tags to entries
- Creates structured research artifacts including claims, exploration trees, and session records
Use Cases
- As a session epilogue after a coding or research session to capture the research journey.
- To maintain a faithful, auditable trace of how a research project evolved.
- To ensure AI suggestions and user confirmations are clearly distinguished for trust and accountability.
Non-Goals
- Running during an active coding or research task.
- Contaminating the working context with 'ara/' directory content until the epilogue phase.
- Fabricating events or information not present in the conversation history.
Practices
- Research Provenance Tracking
- Knowledge Management
- Auditability
Installation
First, add the marketplace
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skillsQuality Score
VerifiedTrust Signals
Similar Extensions
Recursive Research
100Investigación recursiva profunda con loop auto-regulado hasta nivel PhD. Aplicable a cualquier dominio (ciencia, tecnología, negocio, arte, humanidades). Usa WDM + Inversión Munger para decisiones autónomas, tiering de fuentes confiables, y checkpointing a disco para sobrevivir límites de contexto.
Orchestrate
100Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
Agent Teams
100Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.
Domain Extract
100Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.
Lark Wiki CLI
100飞书知识库：管理知识空间、空间成员和文档节点。创建和查询知识空间、查看和管理空间成员、管理节点层级结构、在知识库中组织文档和快捷方式。当用户需要在知识库中查找或创建文档、浏览知识空间结构、查看或管理空间成员、移动或复制节点时使用。
Learn
100Capture a lesson as a structured knowledge entry. Use when you discover a non-obvious bug, workaround, or pattern worth preserving for future sessions. Use when user says "remember this", "save this lesson", or "this is worth noting".