tov-guidelines

Name: tov-guidelines
Author: matteotitta

36stars14forks

How to install tov-guidelines?

matteotitta/claude-code-marketing-quickstart/tov-guidelines

$npx -y skills add matteotitta/claude-code-marketing-quickstart --skill tov-guidelines

Installs into the current project.

Summary

Extract voice patterns from existing content (website, blog, social, sales-call transcripts) and codify into voice rules. Produces voice analysis + voice guidelines (rules per pattern + violation pattern + fix template). Writes to marketing/brand/brand-voice.md as the canonical v

Files · 1

View on GitHub

SKILL.md

1	# tov-guidelines — Stage 1 + 2 research skill (PMM spine)
2
3	Analyzes existing content (your website, blog, recent LinkedIn posts, sales-call transcripts) and produces voice rules that downstream content skills apply.
4
5	---
6
7	## When to use
8
9	- When onboarding a new content writer / contractor — they need codified voice rules to write in your voice
10	- When LinkedIn or blog output stops sounding like the founder / brand
11	- Quarterly refresh
12
13	## When NOT to use
14
15	- For visual brand identity (use `/brand-kit` — voice + visual are separate but both live in `marketing/brand/`)
16	- For one-off content checks against existing rules (write a custom gate skill that reads `brand-voice.md`)
17	- For positioning or messaging (use `/positioning` or `/product-messaging`)
18
19	## How it works
20
21	1. Inputs: source content (one or more of: website URL, blog URL, LinkedIn handle, sales-call transcripts, founder writing samples).
22	2. Reads (Exa MCP for fresh data): the source content. Patterns extracted include: vocabulary preferences, sentence-length defaults, headline conventions, em-dash usage, list-vs-prose preference, contraction frequency, persona pronouns, signature opening / closing patterns.
23	3. Produces a two-phase output:
24	- Phase 1 — Voice analysis (extracted patterns from source material with frequency scores): "uses em-dash with spaces 87% of the time across 30 LinkedIn posts; sentence case headings 100% of the time; banned-word violations 0 in last 10 posts"
25	- Phase 2 — Voice guidelines (codified rules every content skill applies):
26	- Rule N — {rule name}
27	- The rule: 1-sentence statement
28	- Why: 1-sentence justification
29	- Violation pattern: what breaking this looks like
30	- Fix template: how to fix
31	- Exception: when the rule doesn't apply
32	4. Writes to `marketing/brand/brand-voice.md` (overwrites prior canonical; git history preserves prior versions). Marks `status: locked` once approved.
33
34	## Invoke
35
36	```
37	/tov-guidelines https://yourdomain.com + analyze my last 10 LinkedIn posts
38	```
39
40	Or open-ended:
41	```
42	/tov-guidelines extract voice from these sales-call transcripts: [paths]
43	```
44
45	## Example output
46
47	See [`marketing/brand/brand-voice.md`](../../../marketing/brand/brand-voice.md) for the PulseAnalytics seed. Notice the 5 rules each have rule statement + why + violation pattern + fix template + exception. The 5 rules cluster into two themes (prose hygiene + claim integrity).
48
49	## Dependencies
50
51	- Reads from: source content (URL or files — provided as input); optionally `marketing/icp/ICP.md` (voice should match the ICP's vocabulary register)
52	- Reads via Exa MCP (optional): the source content if it lives on the web
53	- Writes to: `marketing/brand/brand-voice.md` (canonical)
54	- Downstream readers: any content skill (LinkedIn, blog, newsletter, email), `/landing-page-copy`, future gate skills
55
56	## Customization
57
58	The 5-rule default in the PulseAnalytics example is operator-flavored. Yours may need more rules (large enterprise teams sometimes track 8-12) or fewer (founder voice often clusters into 3-4 rules). Use whatever rule count matches the patterns you can actually enforce.
59
60	Don't add a rule you can't enforce — every rule should map to a check a gate skill could run automatically. Vague rules ("be human") get ignored; specific rules ("no em-dashes without spaces") get enforced.
61
62	## Where this fits in the Example 1 chain
63
64	```
65	Week 1: /tov-guidelines (parallel with competitor + ICP research) → voice rules locked
66	Week 2: /positioning + /product-messaging apply voice rules to output
67	Week 3+: every content / paid / outbound execution skill reads voice rules
68	```
69
70	## Refresh cadence
71
72	Quarterly. Trigger sooner when the team finds a new buzzword pattern, customer flags off-brand phrasing, or a new persona is added (vocabulary may shift).

People who liked this also viewed

6 picks

Type

tov-guidelines

36stars14forks

View on GitHub

How to install tov-guidelines?

matteotitta/claude-code-marketing-quickstart/tov-guidelines

$npx -y skills add matteotitta/claude-code-marketing-quickstart --skill tov-guidelines

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# tov-guidelines — Stage 1 + 2 research skill (PMM spine)
2
3	Analyzes existing content (your website, blog, recent LinkedIn posts, sales-call transcripts) and produces voice rules that downstream content skills apply.
4
5	---
6
7	## When to use
8
9	- When onboarding a new content writer / contractor — they need codified voice rules to write in your voice
10	- When LinkedIn or blog output stops sounding like the founder / brand
11	- Quarterly refresh
12
13	## When NOT to use
14
15	- For visual brand identity (use `/brand-kit` — voice + visual are separate but both live in `marketing/brand/`)
16	- For one-off content checks against existing rules (write a custom gate skill that reads `brand-voice.md`)
17	- For positioning or messaging (use `/positioning` or `/product-messaging`)
18
19	## How it works
20
21	1. Inputs: source content (one or more of: website URL, blog URL, LinkedIn handle, sales-call transcripts, founder writing samples).
22	2. Reads (Exa MCP for fresh data): the source content. Patterns extracted include: vocabulary preferences, sentence-length defaults, headline conventions, em-dash usage, list-vs-prose preference, contraction frequency, persona pronouns, signature opening / closing patterns.
23	3. Produces a two-phase output:
24	- Phase 1 — Voice analysis (extracted patterns from source material with frequency scores): "uses em-dash with spaces 87% of the time across 30 LinkedIn posts; sentence case headings 100% of the time; banned-word violations 0 in last 10 posts"
25	- Phase 2 — Voice guidelines (codified rules every content skill applies):
26	- Rule N — {rule name}
27	- The rule: 1-sentence statement
28	- Why: 1-sentence justification
29	- Violation pattern: what breaking this looks like
30	- Fix template: how to fix
31	- Exception: when the rule doesn't apply
32	4. Writes to `marketing/brand/brand-voice.md` (overwrites prior canonical; git history preserves prior versions). Marks `status: locked` once approved.
33
34	## Invoke
35
36	```
37	/tov-guidelines https://yourdomain.com + analyze my last 10 LinkedIn posts
38	```
39
40	Or open-ended:
41	```
42	/tov-guidelines extract voice from these sales-call transcripts: [paths]
43	```
44
45	## Example output
46
47	See [`marketing/brand/brand-voice.md`](../../../marketing/brand/brand-voice.md) for the PulseAnalytics seed. Notice the 5 rules each have rule statement + why + violation pattern + fix template + exception. The 5 rules cluster into two themes (prose hygiene + claim integrity).
48
49	## Dependencies
50
51	- Reads from: source content (URL or files — provided as input); optionally `marketing/icp/ICP.md` (voice should match the ICP's vocabulary register)
52	- Reads via Exa MCP (optional): the source content if it lives on the web
53	- Writes to: `marketing/brand/brand-voice.md` (canonical)
54	- Downstream readers: any content skill (LinkedIn, blog, newsletter, email), `/landing-page-copy`, future gate skills
55
56	## Customization
57
58	The 5-rule default in the PulseAnalytics example is operator-flavored. Yours may need more rules (large enterprise teams sometimes track 8-12) or fewer (founder voice often clusters into 3-4 rules). Use whatever rule count matches the patterns you can actually enforce.
59
60	Don't add a rule you can't enforce — every rule should map to a check a gate skill could run automatically. Vague rules ("be human") get ignored; specific rules ("no em-dashes without spaces") get enforced.
61
62	## Where this fits in the Example 1 chain
63
64	```
65	Week 1: /tov-guidelines (parallel with competitor + ICP research) → voice rules locked
66	Week 2: /positioning + /product-messaging apply voice rules to output
67	Week 3+: every content / paid / outbound execution skill reads voice rules
68	```
69
70	## Refresh cadence
71
72	Quarterly. Trigger sooner when the team finds a new buzzword pattern, customer flags off-brand phrasing, or a new persona is added (vocabulary may shift).

People who liked this also viewed

6 picks

Type