Win Loss Analysis

Win/loss analysis

Analyze sales call transcripts to extract actionable insights on why deals are won, lost, retained, or churned. Cross-reference findings with ICP, firmographics, and competitive context to produce strategic recommendations.

Knowledge type: win-loss-analysis Maturity on first run: emergent → validated after team review

Claude Code triggers

Invoke when user says:

• "Win/loss analysis"
• "Analyze sales calls"
• "Why did we win/lose"
• "Churn analysis"
• "Retention analysis"
• "Sales call insights"
• "Deal outcome patterns"
• "Customer feedback synthesis"
• "Analyze these transcripts"
• "What patterns in our sales calls"

Do NOT invoke when:

• User wants general transcript analysis → use a generic transcript skill
• User wants competitor research → use competitor-research
• User wants a single customer interview write-up → use a transcript skill
• User wants sales enablement assets → use a sales-enablement skill

Input requirements

Required

Optional (improve quality)

Validation

Before proceeding: at least one transcript provided; outcome known or inferable from transcript; customer name identifiable.

If inputs are missing: ask the user for transcripts. Clarify if outcome should be inferred from transcript signals.

Transcript intake — normalize, redact, bind to evidence

Transcripts arrive in many shapes (Gong, Fireflies, Otter, Grain, Zoom/Avoma VTT, SRT, recorder JSON, or plain pasted text). Before Phase 1, normalize whatever you're handed into one shape — speaker-attributed turns with timestamps where present. Two rules apply to every transcript before analysis:

• Redact PII first. Mask end-client names, emails, and account numbers before processing; keep roles, company, and deal context. (Load-bearing for regulated industries.)
• Bind every claim to evidence. Every extracted pattern cites a verbatim quote plus the speaker; normalized, speaker-attributed turns make that attribution reliable.

Process

The analysis runs in 3 phases. Read references/process.md for the full step-by-step (4 transcript-processing steps, 4 aggregation steps, 4 synthesis steps, plus per-phase checkpoints and the process flowchart).

Phase summary:

1. Transcript processing — classify outcome, identify speakers, extract customer context, pull verbatim quotes for the 6 dimensions
2. Pattern aggregation — group by outcome, count frequency, rank patterns (3+ mentions), cross-reference by ICP/competitor/persona
3. Insight synthesis — state pattern, provide evidence with frequency + confidence, identify opportunity, generate executive summary

Core frameworks

Analysis modes

Default to batch analysis mode when multiple transcripts are provided.

6 analysis dimensions

Confidence scoring

Outcome classification

Output

Produce a single win/loss report markdown file. Template + iteration prompts library: references/output-format.md.

Pre-delivery quality checklist + worked example + anti-examples: references/quality.md.

Auto-update protocol (feedback signals, pattern detection, skill-update template): references/auto-update.md.

Anti-hallucination guardrails

1. Quote verbatim. All insights must trace to specific transcript quotes.
2. Never invent patterns. If a pattern appears in only one call, label it "Single mention — pattern unconfirmed."
3. State frequency. Always note how many calls support each finding (e.g., "4 of 7 calls").
4. Acknowledge gaps. If a dimension has no data, mark "Not discussed in transcripts."
5. Distinguish roles. Tag who said what — prospect vs. sales rep vs. champion.

Gotchas

• Correlation as causation. Reports "deals with longer sales cycles were lost" as if cycle length caused the loss → always distinguish patterns from causes. Use "associated with" not "caused by".
• Small sample bias. Draws conclusions from 2-3 deals instead of waiting for sufficient data → flag sample size prominently. Minimum 5 wins and 5 losses for reliable patterns.
• Missing verbatim quotes. Summarizes what buyers said instead of extracting exact quotes → verbatim quotes are the primary deliverable. Summaries are secondary.
• Single-dimension analysis. Only looks at win/loss by competitor, missing dimensions like deal size, ICP segment, or sales cycle stage → cross-tabulate across at least 3 dimensions.
• Conflates product feedback with sales insights. Mixes "they wanted feature X" with "they didn't trust our team" → separate product gaps from sales execution issues. They feed into different downstream work.

Integration with other skills

Reference files

Data integration

Level: 0 — Context (heavy pulls)

If you run win/loss inside a connected environment, pull transcripts and deal context fresh:

Fallback (no integrations): user-provided call transcripts or recordings; manual deal review notes.

Changelog