Collecting Evidence

Evidence Collection

This skill guides the creation of structured Evidence Objects for a single research pillar.

Prerequisites

• Ledger workspace initialized (/ledger-init completed)
• Pillar assignment (which pillar to research)
• Research scope from 01-pillars/PILLARS.md

Workflow

Use TodoWrite to track these mandatory steps:

Step 1: Load Pillar Scope

Read 01-pillars/PILLARS.md to understand:

• Pillar priority level
• Specific research questions for this pillar
• Any scope restrictions

See references/research-protocols.md for pillar-specific protocols.

Step 2: Identify Evidence Sources

For each research question, identify potential sources:

Step 3: Collect Raw Evidence

For each source:

1. Extract the key claim(s)
2. Note supporting quotes/data
3. Assess confidence level
4. List assumptions

Web research protocol:

• Use WebSearch for discovery
• Use WebFetch to retrieve and analyze content
• Track source URLs and retrieval dates
• Note if sources agree or contradict

Step 4: Create Evidence Objects

Write YAML files to 02-evidence/<pillar>/.

Naming: Use semantic IDs per references/id-generation-rules.md.

Schema: See references/evidence-object-schema.md.

Step 5: Validate Evidence Quality

Each Evidence Object must pass:

Quality warnings:

• Confidence > 0.9 without peer-reviewed source
• Multiple evidence objects with identical claims
• Assumptions that can't be tested

Step 6: Check Evidence Gate

Before synthesis, verify minimum 5 Evidence Objects per pillar.

Evidence Gate Check: market
├── EV-market-tam-b2b-saas ✓
├── EV-market-pricing-smb-wtp ✓
├── EV-market-growth-remote-tools ✓
├── EV-market-segment-priorities ✓
└── EV-market-competitive-density ✓
Total: 5/5 minimum ✓ GATE PASSED

If gate fails, continue research until threshold met.

User Interaction

Use the AskUserQuestion tool when:

Source prioritization needed

Question: "Multiple sources available for [topic]. Which to prioritize?"
Options:
- "Academic/peer-reviewed sources (higher confidence)"
- "Recent industry reports (more current)"
- "Direct user research (more specific)"
- "Research all and compare"

Confidence assessment uncertain

Question: "How confident should I rate this claim: '[claim]'?"
Options:
- "High (0.8-0.9) - Strong source, well-supported"
- "Medium (0.5-0.7) - Reasonable source, some uncertainty"
- "Low (0.3-0.5) - Weak source or significant assumptions"
- "Help me assess the source quality"

Contradictory evidence found

Question: "Sources disagree on [topic]. Source A says X, Source B says Y."
Options:
- "Create evidence for both, note contradiction"
- "Prioritize more recent source"
- "Prioritize more authoritative source"
- "Research further for resolution"

Evidence gate failing

Question: "Only [N] evidence objects for [pillar]. Need [5-N] more to pass gate."
Options:
- "Continue researching this pillar"
- "Accept partial evidence (will affect synthesis quality)"
- "Deprioritize this pillar for MVP"
- "Help me identify additional research areas"

Output

After evidence collection:

## Evidence Collection Complete: [pillar]

**Evidence Objects Created:** [N]
**Gate Status:** [PASSED/FAILED]

### Evidence Summary
| ID | Claim Summary | Confidence |
|----|---------------|------------|
| EV-market-tam-b2b-saas | TAM is $X billion | 0.80 |
| EV-market-pricing-smb-wtp | SMB WTP peaks at $29/mo | 0.75 |
| ... | ... | ... |

### Key Findings
- [Top 3 findings from this pillar]

### Contradictions Noted
- [Any conflicting evidence]

### Gaps Remaining
- [Research questions not fully answered]

References

• references/evidence-object-schema.md - YAML schema
• references/research-protocols.md - Pillar-specific research guidance
• references/id-generation-rules.md - Semantic ID creation