EVERY CODE STEP YOU WRITE MUST PRODUCE VISIBLE OUTPUT. This is not negotiable.

Before moving to the next step, you MUST execute the following:

1. Run the code
2. See the output (print, display, plot)
3. Verify output is correct/reasonable
4. Document in LEARNINGS.md
5. Only THEN proceed to next step

This applies even when YOU think:

• "I know this works"
• "It's just a simple transformation"
• "I'll check results at the end"
• "The code is straightforward"

If you're about to write code without outputting results, STOP.

What Output-First Means

The Mantra: If not visible, it cannot be trusted.

Red Flags - STOP Immediately

Output-First Protocol

For Every Data Operation:

# BEFORE
print(f"Before: {df.shape}")

# OPERATION
df = df.merge(other, on='key')

# AFTER - MANDATORY
print(f"After: {df.shape}")
print(f"Nulls introduced: {df.isnull().sum().sum()}")
df.head()

Required Outputs by Operation Type

Implementation Process

Step 1: Read Plan

Read the plan to understand task order:

cat .claude/PLAN.md  # View analysis plan and task sequence

Follow the task order defined in the plan.

Step 2: Implement with Output

For each task:

# Task N: [Description]
print("=" * 50)
print("Task N: [Description]")
print("=" * 50)

# Before state
print(f"Input shape: {df.shape}")

# Operation
result = do_operation(df)

# After state - MANDATORY
print(f"Output shape: {result.shape}")
print(f"Sample output:")
display(result.head())

# Verification
assert result.shape[0] > 0, "No rows returned!"
print("Task N complete")

Step 3: Log to LEARNINGS.md

Document every significant step:

## Step N: [Task Description]

**Input:** DataFrame with shape (10000, 15)

**Operation:** Merged with reference table on 'id'

**Output:**
- Shape: (9500, 20)
- 500 rows dropped (no match)
- 5 new columns added
- No new nulls introduced

**Verification:**
- Row count reasonable (5% drop expected due to filtering)
- Sample output matches expected format
- Key columns preserved

**Notes:** [Any observations, issues, or decisions]

Task Agent Invocation

Main chat spawns Task agent:

Task(subagent_type="general-purpose", prompt="""
Implement [TASK] following output-first protocol.

Context:
- Read .claude/LEARNINGS.md for prior steps
- Read .claude/PLAN.md for task details
- Read .claude/SPEC.md for objectives

Output-First Protocol:
1. Print state BEFORE each operation
2. Execute the operation
3. Print state AFTER with verification
4. Display sample output
5. Document in LEARNINGS.md

Required outputs per operation:
- Shape before/after
- Null counts
- Sample rows (head)
- Sanity checks (row counts, value ranges)

DO NOT proceed to next task without:
- Visible output showing operation worked
- LEARNINGS.md entry documenting the step

Report back: what was done, output observed, any issues.
""")

Verification Patterns

See references/verification-patterns.md for detailed code patterns for:

• Data loading, filtering, merging
• Aggregation and model training
• Quick reference table by operation type

Common Failures to Avoid

Logging

Append each step to .claude/LEARNINGS.md:

## Step N: [Description] - [STATUS]

**Input:** [Describe input state]

**Operation:** [What was done]

**Output:** [Shape, stats, sample]

[Paste actual output here]

**Verification:** [How you confirmed it worked]

**Next:** [What comes next]

If Output Looks Wrong

1. STOP - do not proceed
2. Investigate - print more details
3. Document - log the issue in LEARNINGS.md
4. Ask - if unclear, ask user for guidance
5. Fix - only proceed after output verified

Never hide failures. Bad output documented is better than silent failure.

No Pause Between Tasks

Skill(skill="workflows:ds-review")