research-kit

Plugin research-kit from marketplace research-kit in shine102/research-kit. Commands read from the repo's manifest — 1 month ago.

Skills (11)

• assess-knowledge

  Use when needing to check user's familiarity with a topic before diving in, or after teaching to verify understanding -- reads and updates the knowledge state in .research-kit/profile/knowledge.md

• create-exercise

  Use when the user needs hands-on practice after learning a concept -- generates exercises appropriate to the topic type (critical thinking, threat modeling, links to online labs)

• curate-resources

  Use when needing to find and organize learning resources for a topic -- curates docs, labs, blogs, tools, and forum discussions matched to user's knowledge level

• deep-research

  Use when the user wants dedicated deep research on a security topic -- dispatches the Researcher agent for multi-source investigation with structured output

• draft-deliverable

  Use when needing to produce a work output document -- threat models, playbooks, checklists, architecture docs, reports, and other security deliverables

• learn

  Use when the user wants to directly learn a specific security concept without starting a full topic -- dispatches the Mentor agent for interactive teaching

• manage-workspace

  Use when initializing a new research topic workspace, listing existing topics, reading progress, or performing any CRUD operation on .research-kit workspace files

• start

  Use when starting a new security research topic or continuing existing work -- main entry point that dispatches to Collaborator, Mentor, or Researcher agents based on context

• summarize

  Use when needing to distill web content, search results, or raw text into a structured summary with key takeaways -- produces concise, actionable summaries for security topics

• teach

  Use when needing to explain a security concept to the user -- adapts explanation depth to user's current knowledge level, uses interactive Q&A to verify understanding

• web-search

  Use when needing to search the internet for security-related information with trusted source weighting -- prioritizes authoritative and community sources from the curated registry

Subagents (3)

• collaborator

  Use this agent as the default co-worker when the user starts a new security topic or continues existing work. Examples: <example>Context: User starts a new research topic. user: "/research-kit:start evaluate security for enterprise AI chatbot" assistant: "Let me dispatch the Collaborator to help bre

• mentor

  Use this agent when the user needs to understand a security concept -- either detected as a knowledge gap by Collaborator or explicitly requested by the user. Examples: <example>Context: Collaborator detects user doesn't understand prompt injection at scale. user: "I'm not sure how prompt injection

• researcher

  Use this agent for deep research that requires searching multiple sources, synthesizing findings, and producing structured research notes. Examples: <example>Context: Collaborator needs comprehensive research on a new topic. user: "I need to understand the current state of enterprise AI security fra

Similar plugins