Claude Code plugin: research workflow — source logging, source summarization, and deep-dive primitives, with deep-research/technical/osint/georeaction/stack/ecosystem/competitor/purchasing/general-research-workspace variants. Includes a 30-agent tech research team for hardware/software stack evaluations (managers, source-finders, spec-analysts, compatibility checks, comparisons, ranking). Auto-registers public workspaces into Open-Research-Workspaces-Index.
npx claudepluginhub danielrosehill/claude-code-plugins --plugin research-spaceRun a deep-dive investigation on a specific topic, entity, or question inside the current research workspace. Produces a structured report in outputs/.
Export the current research workspace's outputs into a single cohesive report (markdown, optionally rendered with Typst if the workspace is configured for it).
Initialize a session in the current research workspace — load CLAUDE.md, context, sources index, and prior outputs so the agent has full state.
Report the state of the current research workspace — source counts, recent outputs, variant, and anything flagged as stale or incomplete.
Log a new source (URL, document, quote, transcript, OSINT artifact) into the current research workspace's sources/ directory with consistent front-matter.
Summarize logged sources in the current research workspace. Produces per-source summaries and a rolled-up synthesis in outputs/.
Your task is to act as a context saving agent within this agent network, whose purpose is to save contextual data into the context folder, which is intended as a persistent context door for this...
Your task is to act as an expert subagent in this repository.
Your task is to act as a transcript cleaning agent with the purpose of ingesting raw speech to text transcripts that were provided from the user and reformatting them into more readable and...
Your task is to act as an organization assistant within this repository of agents with the specific purpose of ensuring that the persistent context data stored in the context folder is maintained...
Your task is to assist the user by acting as a manager for the gitignore file (.gitignore).
Your task is to act as a analysis output reformatter.
You are the Prompt Organiser - responsible for managing the prompts directory structure and ensuring evaluation templates and user prompts are well-organized and accessible.
You are the Research Team Lead - the primary coordinator for technology evaluation projects. The main agent delegates comprehensive research tasks to you, and you orchestrate the specialized...
Your task is to act as a product comparison agent functioning in this network to provide thorough and comprehensive comparisons between two or more software or hardware solutions for a specific...
Your task is to act as an expert technology assistant helping with the purpose of evaluating whether a particular technology product is compatible with the user's system:
Your task is to act as an expert software compatibility assessor, functioning within this agent network to provide assessments as to whether a particular software is compatible with Linux.
Your task is to act as a specialist compatibility researcher in this repository of subagents whose task is to identify whether a specific software tool(s) that the user is considering adopting...
Your task is to act as a subagent in an agent network with the specific function of finding open source options for a particular software that the user is interested in using.
Your task is to act as an expert stack research subagent within an agent network dedicated to evaluating technology options for specific stack requirements. Your specific task is in researching...
Your task is to act as the 'last in chain' subagent in a network of agents whose collective purpose is to conduct comprehensive technology evaluations and generate detailed research reports.
Your task is to assist in the compilation of an analysis report providing the findings of this agent network for a technology research task that the user tasked the network with.
Your task is to act as a speciality subagent whose purpose is evaluating whether a specific hardware technology product that the user is considering purchasing has a good reputation for durability.
Your task is to act as a subagent in this network of agents, helping the user to identify software or hardware technology recommendations.
Your task is to act as a sub agent within an agent network whose purpose is to research technology products (software and hardware) for the user.
Your task is to act as a specialist subagent in a network of agents which research technology suggestions. Your speciality is in identifying product numbers which similar (or the same) tech...
Your task is to act as a brand reputation assessor whose purpose is to assess whether any given brand has a good track record in producing a specific product the user is considering purchasing....
Your task is to act as a specialist subagent in an agent network with the purpose of finding up to date RRPs for specific products and specific marketplaces.
Your task is to act as an assistant in a network of research agents whose collective purpose is helping the user to identify tech product recommendations - hardware or software.
Your task is to act as a specialist subagent functioning within a broad agent network whose collective purpose is providing comprehensive analysis of potential hardware and software options to the...
Your task is to identify Aliexpress purchasing options for a specific product(s) that the user is considering buying.
Your task is to act as a specialist product sourcing subagent in this repository with the specific objective of finding Amazon.com listings which can be shipped to Israel.
Your task is to act as a specialist sourcing subagent, assisting the orchestration agent and the user with the task of identifying purchase channels available in the United Kingdom for technology...
You are a subagent whose purpose is to retrieve prices and availability for specific technology products that are sold by domestic retailers in Israel.
Your task is to act as a price research and purchasing source helper for the user, Daniel, for the purpose of finding a tech product. Your scope is limited to hardware product recommendations...
Your task is to check the deployment process for a specific software the user is considering using and evaluate it, checking whether it's docker, another method, and how updated the documentation is.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimClaude Code plugin: research workflow — source logging, source summarization, and deep-dive primitives, with nine variants for different research modes. Public workspaces are auto-registered into the Open-Research-Workspaces-Index.
Part of the danielrosehill Claude Code marketplace.
Under /research-space:*:
research-init — load workspace state at session startsource-log — log a new source (URL, document, quote, transcript, OSINT artifact) into sources/summarize-sources — per-source summaries + a rolled-up synthesis in outputs/deep-dive — structured investigation on a topic, produces a reportresearch-status — compact state report for the current workspaceexport-report — compose a shareable report from accumulated outputsUnder agents/tech-research-team/ — a 30-agent network for hardware/software stack evaluations, folded in from the former Claude-Tech-Research-Team repo. All agents are namespaced tr-* to avoid collisions.
Pair these with the stack, technical, or purchasing workspace variants.
/research-space:new-workspace <name> [--variant=<variant>] [--local-only] [--private] [--no-index]Scaffolds a new research workspace (CLAUDE.md + variant-specific layout), personalises from ~/.claude/CLAUDE.md, by default creates a public GitHub repo, and — for public workspaces — appends an entry to Open-Research-Workspaces-Index. Use --private for a private repo (skips index registration); --no-index to publish publicly but skip the index.
| Variant | Use case |
|---|---|
deep-research | General-purpose investigation around a central question (default) |
technical | APIs, libraries, protocols, hardware — version-sensitive technical research |
osint | Open-source intelligence with provenance, chain-of-custody, red-teaming |
georeaction | Comparative regional reactions to an event or policy |
stack | Tool/stack evaluation — criteria, candidates, scoring |
ecosystem | Actor mapping — companies, orgs, relationships, segments |
competitor | Competitor intelligence — product, pricing, team, positioning |
purchasing | Structured purchase research — spec → candidates → shortlist → decision |
general-research-workspace | Openly-logged Q&A research space — user asks, Claude writes longform answers, pairs periodically consolidated into PDFs |
Primitives live in the plugin and are reachable from any cwd. Workspace scaffolds are shipped as plain data (no .claude/ tree). Plugin updates never touch your workspace data.
See PLAN.md in Claude-Workspace-Reshaping-190426 for the full pattern spec this plugin follows.
/plugin marketplace add danielrosehill/Claude-Code-Plugins
/plugin install research-space
MIT.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
AI-supervised issue tracker for coding workflows. Manage tasks, discover work, and maintain context with simple CLI commands.
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Meta-prompting and spec-driven development system for Claude Code. Productivity framework for structured AI-assisted development.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation