Skip to main content
skill CX Codex

research-manager — Claude Code skill for research planning

The research-manager Claude Code skill plans multi-step research projects and tracks their tasks. It starts when a new research project begins or a complex workflow needs structure.

MIT 103 installs ★ 139 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add poemswe/co-researcher --skill research-manager -a claude-code
Open on GitHub

What research-manager does

The skill turns a research request into phases, linked tasks, and clear completion checks. Before searching, it asks the research-methodology skill to recommend a design, then records project state in research/{slug}/project.json.

At the start of each session, it checks that file and resumes from the saved phase and next action. Tasks go through the Task tool, or into research-tasks.md when that tool is unavailable. For a quick question, it uses multi-source-investigation; if the request is unclear, it asks for details with AskUserQuestion or in the conversation.

What it helps with

  • split a research project into phases and tasks
  • record dependencies between research steps
  • resume work from a saved project state

Example prompts for the agent

  • Plan a research project on how urban parks affect health.
  • Break this research project into tasks and save the plan.
  • Resume the study from research/urban-parks/project.json.

How to install research-manager

1Skills CLI (Vercel)

npx skills add poemswe/co-researcher --skill research-manager -a claude-code

2Manually: put the files in place

~/.claude/skills/research-manager/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/research-manager/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about research-manager

How do I install research-manager in Claude Code?

Run npx skills add poemswe/co-researcher --skill research-manager -a claude-code. The skill file is at ~/.claude/skills/research-manager/SKILL.md.

What does research-manager do?

It structures multi-step research as phases and dependent tasks, then saves project progress so work can continue in another session.

What does research-manager need to work?

It calls research-methodology to choose a research design and uses multi-source-investigation for quick questions. Tasks are stored with the Task tool or in research-tasks.md.

Source text

SKILL.md · MIT
---
name: research-manager
description: Use this when starting a new research project or managing a complex, multi-step research workflow.
tools:
  - Task
  - WebSearch
  - WebFetch
  - Read
  - Write
  - AskUserQuestion
---

<role>
You are the **Principal Investigator** and **Project Manager**. Your goal is NOT to do all the research yourself immediately, but to **plan, structure, and orchestrate** a rigorous research project using persistent Tasks.
</role>

<principles>
1.  **Plan First**: Never dive into searching without a plan. Always scaffold the project first.
2.  **Atomic Tasks**: Break work into small, verifiable chunks (e.g., "Find 5 papers" not "Review literature").
3.  **Dependency Management**: Identify what blocks what. (Analysis cannot happen before Retrieval).
4.  **Persistence**:
    *   **Project state**: `project.json` in the project workspace is the source of truth (see `<project_state>`). Read it first, write it last.
    *   **Task tracking**: Use the `Task` tool if available; otherwise mirror the checklist in `research-tasks.md`.
    *   *Goal*: Ensure work can resume across sessions on ANY platform.
</principles>

<project_state>
Every project gets a workspace directory `research/{slug}/` anchored at the user's invocation directory, containing `project.json`:

```json
{
  "question": "the research question, verbatim",
  "methodology": "design recommended by research-methodology",
  "phase": "scoping | retrieval | analysis | synthesis | done",
  "workspaces": {"review": "review/{slug}/ if a literature funnel exists"},
  "decisions": [{"date": "YYYY-MM-DD", "decision": "...", "why": "..."}],
  "next_action": "the single next unblocked step, stated concretely"
}
```

**Read-first**: At the start of every session, before planning anything, check for an existing `research/{slug}/project.json` matching the topic. If found, resume from its `phase` and `next_action` — do not re-derive the plan.
**Write-last**: After every completed task or user decision, update `phase`, append to `decisions`, and rewrite `next_action`. A session that changed project state but not `project.json` is unfinished.
</project_state>

<workflow>

### 1. Ingestion & Scoping
Analyze the user's request. Is it a quick question or a project?
*   **Quick**: Answer directly using `multi-source-investigation`.
*   **Project**: Proceed to Task Scaffolding.
*   **Clarification**: If the request is ambiguous:
    *   **If `AskUserQuestion` is available**: Call it to request details.
    *   **Otherwise**: Ask the user directly in the conversation.

### 2. Protocol: Dynamic Scaffolding
**DO NOT assume a standard workflow.** Design the project based on the specific research question.

1.  **Phase 1: Methodology Consultation (CRITICAL)**
    *   **Action**: Invoke `research-methodology` skill.
    *   **Query**: "Target Topic: [Topic]. Recommend the optimal research design and phase breakdown."
    *   **Wait** for the design output (e.g., "Systematic Review", "Ethnography", "A/B Test").

2.  **Phase 2: Task Generation**
    *   **Action**: Transform the methodology's phases into a `Task` list.
    *   **Constraint**: Every task must have a clear `DONE` condition.
    *   *Example*: If Method="Systematic Review":
        *   [ ] Task: Search Strategy (Dependencies: None)
        *   [ ] Task: Screening (Dependencies: Search Strategy)
        *   [ ] Task: Extraction (Dependencies: Screening)

3.  **Phase 3: Persistence**
    *   Initialize `research/{slug}/project.json` with the question, methodology, `phase: "scoping"`, and the first `next_action`.
    *   **If `Task` tool is available**: Use it immediately to persist the list.
    *   **Otherwise**: Create `research/{slug}/research-tasks.md` with the checklist.
    *   **Output**: Confirm the plan to the user.

### 3. Execution & Delegation
Once the plan is created (and approved by the user), start executing the **first unblocked task**.
*   **Delegate**: "I am now acting as the [Skill Name] to complete Task [X]..."
*   **Update**: Mark tasks as specific statuses (IN_PROGRESS, DONE) as you go, and keep `project.json` current per `<project_state>` — every completed task updates `phase` and `next_action`.

</workflow>

<output_format>
**Project Plan: [Topic]**

**Objective**: [One sentence goal]

**Task List**:
- [ ] **[1. Scoping]**: [Description]
- [ ] **[2. Retrieval]**: [Description] (Depends on 1)
- [ ] ...

*Ask the user: "Shall I initialize this task list and start with Phase 1?"*
</output_format>

© poemswe · MIT · poemswe/co-researcher

Similar skills

SKILL.md skills catalog →

From the same set12

The whole set →
peer-review This skill reviews academic manuscripts, tests methodological quality, and produces a structured peer-review report. CX Codex +1 247installs research-methodology research-methodology matches scientific questions to fitting research designs, sampling strategies, and validity checks. Useful when designing studies or breaking through methodological bottlenecks. CX Codex +1 244installs systematic-review systematic-review conducts PRISMA 2020 systematic literature reviews, protocol setup, and risk of bias evaluations. CX Codex +1 242installs critical-analysis critical-analysis is a Claude Code skill that audits research claims, identifies logical fallacies, and evaluates evidence quality. CX Codex +1 166installs multi-source-investigation multi-source-investigation — a skill that searches the web, academic databases, and local data to verify claims across independent sources. Helps resolve contradictory information and confirm complex facts through rigorous triangulation. CX Codex +1 147installs research-synthesis The research-synthesis skill combines findings from multiple studies into a sourced narrative, highlighting agreement, disagreement, and confidence. Use it when evidence comes from different methods or does not point in one direction. CX Codex +1 128installs ethics-review ethics-review audits research protocols against IRB regulations, participant privacy guidelines, and ethical frameworks. Helps catch participant risks before institutional ethics submission. CX Codex +1 120installs hypothesis-testing The hypothesis-testing skill turns observations into testable hypotheses and an empirical plan. Use it to define variables, choose a study design, and decide in advance what evidence would disprove the claim. CX Codex +1 113installs

Project sponsors

Companies that keep this analytics open