REQUIRED Phase 4 of /ds workflow. Reviews methodology, data quality, and statistical validity.
Reviews data science analysis for methodology correctness, data quality handling, and reproducibility. Used in Phase 4 of /ds workflow to validate analysis meets quality standards before approval.
/plugin marketplace add edwinhu/workflows/plugin install workflows@edwinhu-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Announce: "I'm using ds-review (Phase 4) to check methodology and quality."
Single-pass review combining methodology correctness, data quality handling, and reproducibility checks. Uses confidence-based filtering.
<EXTREMELY-IMPORTANT> ## The Iron Law of DS ReviewOnly report issues with >= 80% confidence. This is not negotiable.
Before reporting ANY issue, you MUST:
This applies even when:
If you catch yourself about to report a low-confidence issue, DISCARD IT. </EXTREMELY-IMPORTANT>
| Thought | Why It's Wrong | Do Instead |
|---|---|---|
| "This looks wrong" | Vague suspicion isn't evidence | Find concrete proof or discard |
| "I would do it differently" | Style preference isn't methodology error | Check if approach is valid |
| "This might cause problems" | "Might" means < 80% confidence | Find proof or discard |
| "Unusual approach" | Unusual isn't wrong | Verify if methodology is sound |
Rate each potential issue from 0-100:
| Score | Meaning |
|---|---|
| 0 | False positive or style preference |
| 25 | Might be real, methodology is unusual but valid |
| 50 | Real issue but minor impact on conclusions |
| 75 | Verified issue, impacts result interpretation |
| 100 | Certain error that invalidates conclusions |
CRITICAL: Only report issues with confidence >= 80.
## Analysis Review: [Analysis Name]
Reviewing: [files/notebooks being reviewed]
### Critical Issues (Confidence >= 90)
#### [Issue Title] (Confidence: XX)
**Location:** `file/path.py:line` or `notebook.ipynb cell N`
**Problem:** Clear description of the issue
**Impact:** How this affects results/conclusions
**Fix:**
```python
# Specific fix
[Same format as Critical Issues]
| Check | Status | Notes |
|---|---|---|
| Missing values | PASS/FAIL | [details] |
| Duplicates | PASS/FAIL | [details] |
| Outliers | PASS/FAIL | [details] |
| Type correctness | PASS/FAIL | [details] |
| Check | Status | Notes |
|---|---|---|
| Appropriate for data | PASS/FAIL | [details] |
| Assumptions checked | PASS/FAIL | [details] |
| Sample size adequate | PASS/FAIL | [details] |
| Check | Status | Notes |
|---|---|---|
| Seeds set | PASS/FAIL | [details] |
| Versions documented | PASS/FAIL | [details] |
| Data versioned | PASS/FAIL | [details] |
Verdict: APPROVED | CHANGES REQUIRED
[If APPROVED] The analysis meets quality standards. No methodology issues with confidence >= 80 detected.
[If CHANGES REQUIRED] X critical issues and Y important issues must be addressed before proceeding.
## Agent Invocation
Main chat spawns Task agent:
Task(subagent_type="general-purpose"): "Review analysis against .claude/SPEC.md.
Single-pass review covering:
Confidence score each issue (0-100). Only report issues >= 80 confidence. Return structured output per /ds-review format."
## Quality Standards
- Never report methodology preferences not backed by statistical principles
- Alternative valid approaches are NOT issues (confidence = 0)
- Each reported issue must be immediately actionable
- If unsure whether approach is valid, the issue is below 80 confidence
- Focus on what affects conclusions, not style
## Phase Complete
**REQUIRED SUB-SKILL:** After review is APPROVED, IMMEDIATELY invoke:
Skill(skill="workflows:ds-verify")
If CHANGES REQUIRED, return to `/ds-implement` to fix issues first.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.