win-loss-analysis

Name: win-loss-analysis
Author: matteotitta

36stars14forks

How to install win-loss-analysis?

matteotitta/claude-code-marketing-quickstart/win-loss-analysis

$npx -y skills add matteotitta/claude-code-marketing-quickstart --skill win-loss-analysis

Installs into the current project.

Summary

Analyze sales-call transcripts to extract why deals are won and lost across six dimensions — product, messaging, GTM/sales, pricing, competition, and customer context. Produces aggregated patterns with verbatim buyer quotes, frequencies, and recommendations. Writes to marketing/w

Files · 1

View on GitHub

SKILL.md

1	# win-loss-analysis — Day 4 research skill
2
3	The Example 1 Day 4 skill. Reads your won + lost sales-call transcripts and writes a pattern-level analysis to `marketing/win-loss/win-loss.md`. This is the evidence base under positioning, messaging, and ICP — every claim in those docs should trace back to something a real buyer said here.
4
5	---
6
7	## When to use
8
9	- Day 4 of Example 1: before `/icp-research` + `/positioning`, so the strategy reads from real buyer language
10	- You have a fresh batch of 5+ won/lost call transcripts
11	- A quarter closes and you want to refresh why deals moved
12	- Churn spikes and you need the pattern, not the anecdote
13
14	## When NOT to use
15
16	- For a single account's interview prep (use `/customer-interviews` — not in V2 quickstart)
17	- For behavioural simulation of a buyer (use `/icp-behavioural` — not in V2 quickstart)
18	- When you have fewer than ~5 transcripts — patterns need volume; below that you get anecdotes, not signal
19
20	## Two rules apply before any analysis
21
22	- Redact PII first — [`.claude/rules/pii-redaction.md`](../../rules/pii-redaction.md). Mask end-customer names, emails, and account numbers before processing; keep roles, company, and deal context.
23	- Bind every claim to evidence — [`.claude/rules/evidence-bound-outputs.md`](../../rules/evidence-bound-outputs.md). Every pattern cites a verbatim quote + speaker, or it lowers its confidence. No invented quotes.
24
25	## How it works
26
27	1. Inputs: sales-call transcripts (Gong, Fireflies, Otter, Granola, Zoom/Avoma VTT, or pasted text), each tagged with the deal outcome (won / lost / churned). Optional: `marketing/icp/ICP.md` to frame patterns by segment.
28	2. Normalize each transcript to speaker-attributed turns with timestamps where present.
29	3. Pick a mode:
30	- Single — deep analysis of one transcript
31	- Batch (default) — aggregate 5–20 transcripts into patterns with frequency counts
32	- Comparison — won vs lost (or retained vs churned) side by side
33	4. Extract patterns across six dimensions: product, messaging, GTM / sales process, pricing, competition, customer context.
34	5. Score confidence by frequency: a pattern needs 2+ occurrences across different deals; High = 3+ deals, Medium = 2, Low = single mention. Aim for ≥5 wins and ≥5 losses before trusting a pattern.
35	6. Writes to `marketing/win-loss/win-loss.md` (overwrites prior canonical; git history preserves prior versions).
36
37	## Invoke
38
39	```
40	/win-loss-analysis
41	```
42
43	Then paste or point to the transcripts and tag each outcome. Or:
44
45	```
46	/win-loss-analysis — here are 8 won + 6 lost transcripts: [paste / paths]
47	```
48
49	## Example output
50
51	See [`marketing/win-loss/win-loss.md`](../../../pulse-analytics-example/win-loss/win-loss.md) for the PulseAnalytics example seed. Notice: patterns are grouped by dimension; each carries a frequency + a verbatim quote with speaker; the closing section routes findings to positioning / messaging / ICP.
52
53	## Dependencies
54
55	- Reads from: sales-call transcripts (required); `marketing/icp/ICP.md` (optional, for segment framing)
56	- Reads via Granola MCP (optional): meeting transcripts, if wired
57	- Writes to: `marketing/win-loss/win-loss.md` (canonical; positioning, messaging, and ICP read from here)
58
59	## Customization
60
61	Split the analysis by segment when your ICP has more than one (enterprise vs mid-market lose for different reasons). Add a competitor column to the competition dimension once you're losing to a named rival repeatedly — that feeds `/competitor-research`.
62
63	## Where this fits in the Example 1 chain
64
65	```
66	Day 1-3: /competitor-research × N → per-competitor files
67	Day 3: /competitor-aggregate → competitor canonical
68	Day 4: /win-loss-analysis (THIS SKILL) → win-loss canonical
69	Day 5: /icp-researc

People who liked this also viewed

6 picks

Type

win-loss-analysis

36stars14forks

View on GitHub

How to install win-loss-analysis?

matteotitta/claude-code-marketing-quickstart/win-loss-analysis

$npx -y skills add matteotitta/claude-code-marketing-quickstart --skill win-loss-analysis

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# win-loss-analysis — Day 4 research skill
2
3	The Example 1 Day 4 skill. Reads your won + lost sales-call transcripts and writes a pattern-level analysis to `marketing/win-loss/win-loss.md`. This is the evidence base under positioning, messaging, and ICP — every claim in those docs should trace back to something a real buyer said here.
4
5	---
6
7	## When to use
8
9	- Day 4 of Example 1: before `/icp-research` + `/positioning`, so the strategy reads from real buyer language
10	- You have a fresh batch of 5+ won/lost call transcripts
11	- A quarter closes and you want to refresh why deals moved
12	- Churn spikes and you need the pattern, not the anecdote
13
14	## When NOT to use
15
16	- For a single account's interview prep (use `/customer-interviews` — not in V2 quickstart)
17	- For behavioural simulation of a buyer (use `/icp-behavioural` — not in V2 quickstart)
18	- When you have fewer than ~5 transcripts — patterns need volume; below that you get anecdotes, not signal
19
20	## Two rules apply before any analysis
21
22	- Redact PII first — [`.claude/rules/pii-redaction.md`](../../rules/pii-redaction.md). Mask end-customer names, emails, and account numbers before processing; keep roles, company, and deal context.
23	- Bind every claim to evidence — [`.claude/rules/evidence-bound-outputs.md`](../../rules/evidence-bound-outputs.md). Every pattern cites a verbatim quote + speaker, or it lowers its confidence. No invented quotes.
24
25	## How it works
26
27	1. Inputs: sales-call transcripts (Gong, Fireflies, Otter, Granola, Zoom/Avoma VTT, or pasted text), each tagged with the deal outcome (won / lost / churned). Optional: `marketing/icp/ICP.md` to frame patterns by segment.
28	2. Normalize each transcript to speaker-attributed turns with timestamps where present.
29	3. Pick a mode:
30	- Single — deep analysis of one transcript
31	- Batch (default) — aggregate 5–20 transcripts into patterns with frequency counts
32	- Comparison — won vs lost (or retained vs churned) side by side
33	4. Extract patterns across six dimensions: product, messaging, GTM / sales process, pricing, competition, customer context.
34	5. Score confidence by frequency: a pattern needs 2+ occurrences across different deals; High = 3+ deals, Medium = 2, Low = single mention. Aim for ≥5 wins and ≥5 losses before trusting a pattern.
35	6. Writes to `marketing/win-loss/win-loss.md` (overwrites prior canonical; git history preserves prior versions).
36
37	## Invoke
38
39	```
40	/win-loss-analysis
41	```
42
43	Then paste or point to the transcripts and tag each outcome. Or:
44
45	```
46	/win-loss-analysis — here are 8 won + 6 lost transcripts: [paste / paths]
47	```
48
49	## Example output
50
51	See [`marketing/win-loss/win-loss.md`](../../../pulse-analytics-example/win-loss/win-loss.md) for the PulseAnalytics example seed. Notice: patterns are grouped by dimension; each carries a frequency + a verbatim quote with speaker; the closing section routes findings to positioning / messaging / ICP.
52
53	## Dependencies
54
55	- Reads from: sales-call transcripts (required); `marketing/icp/ICP.md` (optional, for segment framing)
56	- Reads via Granola MCP (optional): meeting transcripts, if wired
57	- Writes to: `marketing/win-loss/win-loss.md` (canonical; positioning, messaging, and ICP read from here)
58
59	## Customization
60
61	Split the analysis by segment when your ICP has more than one (enterprise vs mid-market lose for different reasons). Add a competitor column to the competition dimension once you're losing to a named rival repeatedly — that feeds `/competitor-research`.
62
63	## Where this fits in the Example 1 chain
64
65	```
66	Day 1-3: /competitor-research × N → per-competitor files
67	Day 3: /competitor-aggregate → competitor canonical
68	Day 4: /win-loss-analysis (THIS SKILL) → win-loss canonical
69	Day 5: /icp-researc

People who liked this also viewed

6 picks

Type