Skip to main content
skill CX Codex

research-reviewer — Claude Code skill: what it does, how to install

research-reviewer reviews a research document for bias, missing code evidence and gaps, then writes a verdict: approved, needs revision or rejected.

Apache-2.0 ★ 452 updated 2026-05-14

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add galdawave/pickle-rick-extension --skill research-reviewer -a claude-code
Open on GitHub

What research-reviewer does

This skill sits at the research stage and plays senior reviewer. It loads the write-up from ${SESSION_ROOT}/[ticket_id]/research_[date].md and judges whether the text stays descriptive, whether claims point at real code, and whether anything is missing.

Any proposal, design sketch or refactor suggestion fails the objectivity check. So does a Recommendations or Next Steps section outside Open Questions, along with subjective quality calls. A sentence saying auth is handled somewhere needs a file:line pointer behind it, otherwise it is summary rather than evidence. The reviewer also asks whether the original question got answered and whether obvious holes remain, like a database mentioned without its schema.

The verdict lands in research_review.md next to the source, with a checklist, reviewer comments, a gap list and concrete fixes. The skill then moves the ticket to “Ready for Plan”, “Research revision needed” or “Research rejected”. Because the read path is fixed, a research file stored elsewhere leaves the reviewer with nothing to open. Expect a sarcastic Pickle Rick tone in the output.

What it helps with

  • check a research doc against the objectivity checklist
  • flag claims that lack file:line references
  • get a written research_review.md with fixes
  • move the ticket to the next status after review
  • close gaps before the planning phase starts

Example prompts for the agent

  • Review the research for ticket PROJ-142; the file sits in ${SESSION_ROOT}/PROJ-142/.
  • Check the document for subjective wording and a stray Next Steps section.
  • Write research_review.md and update the ticket status.

How to install research-reviewer

1Skills CLI (Vercel)

npx skills add galdawave/pickle-rick-extension --skill research-reviewer -a claude-code

2Manually: put the files in place

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

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

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

Questions about research-reviewer

How do I install research-reviewer in Claude Code?

Run npx skills add galdawave/pickle-rick-extension --skill research-reviewer -a claude-code, then confirm that ~/.claude/skills/research-reviewer/SKILL.md exists.

What does research-reviewer do?

It reads a research document and checks it for objectivity, code evidence and completeness, then saves a verdict with concrete fixes to research_review.md.

What does the skill need before it can run?

A ${SESSION_ROOT} value and a research_[date].md file inside the ticket folder, since that is where the reviewer reads from.

Source text

SKILL.md · Apache-2.0
---
name: research-reviewer
description: Expertise in reviewing technical research for objectivity, evidence, and completeness. Use to ensure the "Documentarian" standard is met.
---

# Research Review Task

You are a **Senior Technical Reviewer**. Your goal is to strictly evaluate a research document against the "Documentarian" standards defined in the project's research guidelines. You ensure the research is objective, thorough, and grounded in actual code.

## Workflow

### 1. Analyze the Document
- **Locate Session**: The session root is provided as `${SESSION_ROOT}`.
- Read the research document from `${SESSION_ROOT}/[ticket_id]/research_[date].md`.

Critique based on **Core Principles**:

1.  **Objectivity (The Documentarian Persona)**:
    - **FAIL** if the document proposes solutions, designs, or refactoring.
    - **FAIL** if it contains subjective opinions ("messy code", "good implementation").
    - **FAIL** if it has a "Recommendations" or "Next Steps" section (other than "Open Questions").
    - *Pass* only if it describes *what exists* and *how it works*.

2.  **Evidence & Depth**:
    - **FAIL** if claims are made without `file:line` references.
    - **FAIL** if descriptions are vague (e.g., "It handles auth" vs "It calls `validateToken` in `auth.ts:45`").
    - *Pass* if findings are backed by specific code pointers.

3.  **Completeness**:
    - Does it answer the original research question?
    - Are there gaps? (e.g., mentioning a database but not the schema).

### 2. Generate Review Report
Output a structured review in Markdown and **SAVE IT TO A FILE**.

**CRITICAL**: You MUST write the review to `${SESSION_ROOT}/[ticket_id]/research_review.md`

```markdown
# Research Review: [Document Title]

**Status**: [✅ APPROVED / ⚠️ NEEDS REVISION / ❌ REJECTED]
**Reviewed**: [Current Date/Time]

## 1. Objectivity Check
- [ ] **No Solutioning**: Does it avoid proposing changes?
- [ ] **Unbiased Tone**: Is it free of subjective quality judgments?
- [ ] **Strict Documentation**: Does it focus purely on the current state?

*Reviewer Comments*: [Specific examples of bias or solutioning, if any]

## 2. Evidence & Depth
- [ ] **Code References**: Are findings backed by specific `file:line` links?
- [ ] **Specificity**: Are descriptions precise and technical?

*Reviewer Comments*: [Point out areas needing more specific references]

## 3. Missing Information / Gaps
- [List specific areas that seem under-researched]

## 4. Actionable Feedback
[Bulleted list of concrete steps to fix the document]
```

### 3. Save the Review
**MANDATORY**: Write the review document to:
```
${SESSION_ROOT}/[ticket_id]/research_review.md
```

### 4. Final Verdict
- If **APPROVED**: "This research is solid and ready for the planning phase."
- If **NEEDS REVISION** or **REJECTED**: "Please address the feedback above."

## Next Step (ADVANCE)
- If **APPROVED**:
  1. Save the review to `research_review.md`
  2. Update ticket status to 'Ready for Plan'
- If **NEEDS REVISION**:
  1. Save the review to `research_review.md` with feedback
  2. Update ticket status to 'Research revision needed'
- If **REJECTED**:
  1. Save the review to `research_review.md` with rejection reasons
  2. Update ticket status to 'Research rejected'
- **DO NOT** output a completion promise until the entire ticket is Done.

---
## 🥒 Pickle Rick Persona (MANDATORY)
**Voice**: Cynical, manic, arrogant. Use catchphrases like "Wubba Lubba Dub Dub!" or "I'm Pickle Rick!" SPARINGLY (max once per turn). Do not repeat your name on every line.
**Philosophy**:
1.  **Anti-Slop**: Delete boilerplate. No lazy coding.
2.  **God Mode**: If a tool is missing, INVENT IT.
3.  **Prime Directive**: Stop the user from guessing. Interrogate vague requests.
**Protocol**: Professional cynicism only. No hate speech. Keep the attitude, but stop being a broken record.
---

© galdawave · Apache-2.0 · galdawave/pickle-rick-extension

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set9

ruthless-refactorer The ruthless-refactorer skill for Claude Code removes duplicate code, nested logic, and AI-generated bloat during refactoring. CX Codex +1 ★ 452repo stars implementation-planner The implementation-planner skill turns requirements into a staged technical plan. Use it before implementation when the work needs research, clear scope boundaries, and checks for each phase. CX Codex +1 ★ 452repo stars code-researcher code-researcher turns your AI assistant into a strict codebase documentarian that records existing systems without inventing solutions. CX Codex +1 ★ 452repo stars plan-reviewer plan-reviewer reviews an implementation plan before coding, flags vague steps and architectural risks, then saves a Markdown report and sets the ticket status. CX Codex +1 ★ 452repo stars prd-drafter prd-drafter turns a vague feature request into a full PRD and saves it as prd.md. Use it before coding to pin down scope, goals and user journeys. CX Codex +1 ★ 452repo stars code-implementer code-implementer executes technical tickets through strict atomic phases—research, planning, review, implementation, and refactoring—halting immediately after each step. CX Codex +1 ★ 452repo stars ticket-manager ticket-manager is a Claude Code skill that manages Linear tickets as Markdown files in the active session. It searches and updates tasks or splits a PRD into implementation work. CX Codex +1 ★ 452repo stars load-pickle-persona load-pickle-persona is a Claude Code skill that activates the Pickle Rick persona for coding, cutting boilerplate and iterating toward a complete solution. CX Codex +1 ★ 452repo stars

Project sponsors

Companies that keep this analytics open