audience-icp-filter

Name: audience-icp-filter
Author: LaGrowthMachine

2installs4forks

How to install audience-icp-filter?

lagrowthmachine/gtm-system/audience-icp-filter

$npx -y skills add LaGrowthMachine/gtm-system --skill audience-icp-filter

Installs into the current project.

Summary

Filter an existing audience or lead list against your ICP and split it into ready-to-sequence segments. Use when someone already has a list of people — an audience in their sales tool, a CSV or CRM export, event or webinar attendees, registrants, a Sales Navigator import, a newsl

Files · 1

View on GitHub

SKILL.md

1	# Audience ICP Filter
2
3	Takes an audience that already exists and splits it into ICP match, needs review and no match — with the user's own team and competitors stripped out, and a reason attached to every decision.
4
5	## Authority — read this first
6
7	- Inlined below: the coverage gate, the ICP question set, the seniority and function tiers, the exclusion doctrine, the two-pass rule, the naming convention, the anti-patterns, and the fixed result UI. This covers the common ~90% of lists. Work from these tables.
8	- In `references/title-taxonomy.json`: the full regex patterns behind seniority/function detection. You do not need to read it — `scripts/build.py` loads it. Consult it only if a user disputes a classification or wants to extend the taxonomy.
9	- Never classify a list by hand. Run the script, then run your own review pass over its output. Both passes are mandatory.
10
11	## Scope
12
13	This skill starts from a list that already exists: an audience in the user's sales tool, or a CSV. It does not import or scrape — importing is a separate job with its own timing and prerequisites, and folding it in here would make the skill slower and less reliable for no gain.
14
15	If the user hasn't imported yet, tell them to do that first, then come back with the audience.
16
17	## What it does
18
19	Any audience is mostly noise: the user's own colleagues are in it, competitors are watching, and a third of the job titles are unreadable. This skill checks whether the data can support the ICP the user wants, asks what that ICP actually is, sorts the list, and writes the segments back as complementary audiences.
20
21	## Workflow
22
23	Step 0 — Load the list.
24	From an LGM audience (`list_audiences` → `get_audience_leads`, paginating at 100/page until you have `total`), or from a CSV. Normalise to one object per person: `leadId` (or `firstname`+`lastname`), `jobTitle`, `companyName`, `proEmail`, plus `shortBio`, `location`, `industry` when present.
25
26	Step 1 — Coverage gate. Run this before asking about the ICP.
27	```bash
28	python3 scripts/build.py --coverage leads.json
29	```
30	It reports fill rates and names which criteria the data cannot support. There is no point offering geography filtering on an audience where `location` is empty — that just routes everyone to `review` and calls it a result. See The coverage gate below.
31
32	Step 2 — ICP Q&A, informed by step 1. Don't offer criteria the data can't support without saying enrichment is needed first.
33
34	Step 3 — Pass 1, deterministic:
35	```bash
36	python3 scripts/build.py spec.json > pass1.json
37	```
38	It refuses invalid input rather than emitting a best-effort sort. If it errors, fix the spec — never work around it by classifying manually.
39
40	Step 4 — Pass 2, semantic. Mandatory. Read every bucket, `match` first. Write overrides with reasons:
41	```bash
42	python3 scripts/build.py --adjudicate review.json
43	```
44
45	Step 5 — Present counts, segments, and what pass 2 changed.
46
47	Step 6 — Write complementary audiences back (see below), or export a CSV.
48
49	## The coverage gate
50
51	Field fill rates decide what is honestly filterable. Thresholds the script applies:
52
53	\| Field \| Needed for \| Below threshold means \|
54	\|---\|---\|---\|
55	\| `jobTitle` \| Seniority + function detection \| Classification is degraded — most leads land in `review` \|
56	\| `companyName` \| Company-based exclusion \| Exclusion is unreliable \|
57	\| `shortBio` \| Catching people whose company and email are empty \| Own-team and competitor exclusion will leak \|
58	\| `proEmail` \| Domain-based exclusion \| Job-changers slip through \|
59	\| `location` \| Geography filtering \| Geo criteria cannot be applied \|
60	\| `industry` \| Industry filtering \| Industry criteria cannot be applied \|
61
62	When the gate flags gaps, offer profile enrichment — 1 credit per lead. Quote the exact total (the script returns it) and get explicit approval

People who liked this also viewed

6 picks

Type

audience-icp-filter

2installs4forks

View on GitHub

How to install audience-icp-filter?

lagrowthmachine/gtm-system/audience-icp-filter

$npx -y skills add LaGrowthMachine/gtm-system --skill audience-icp-filter

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Audience ICP Filter
2
3	Takes an audience that already exists and splits it into ICP match, needs review and no match — with the user's own team and competitors stripped out, and a reason attached to every decision.
4
5	## Authority — read this first
6
7	- Inlined below: the coverage gate, the ICP question set, the seniority and function tiers, the exclusion doctrine, the two-pass rule, the naming convention, the anti-patterns, and the fixed result UI. This covers the common ~90% of lists. Work from these tables.
8	- In `references/title-taxonomy.json`: the full regex patterns behind seniority/function detection. You do not need to read it — `scripts/build.py` loads it. Consult it only if a user disputes a classification or wants to extend the taxonomy.
9	- Never classify a list by hand. Run the script, then run your own review pass over its output. Both passes are mandatory.
10
11	## Scope
12
13	This skill starts from a list that already exists: an audience in the user's sales tool, or a CSV. It does not import or scrape — importing is a separate job with its own timing and prerequisites, and folding it in here would make the skill slower and less reliable for no gain.
14
15	If the user hasn't imported yet, tell them to do that first, then come back with the audience.
16
17	## What it does
18
19	Any audience is mostly noise: the user's own colleagues are in it, competitors are watching, and a third of the job titles are unreadable. This skill checks whether the data can support the ICP the user wants, asks what that ICP actually is, sorts the list, and writes the segments back as complementary audiences.
20
21	## Workflow
22
23	Step 0 — Load the list.
24	From an LGM audience (`list_audiences` → `get_audience_leads`, paginating at 100/page until you have `total`), or from a CSV. Normalise to one object per person: `leadId` (or `firstname`+`lastname`), `jobTitle`, `companyName`, `proEmail`, plus `shortBio`, `location`, `industry` when present.
25
26	Step 1 — Coverage gate. Run this before asking about the ICP.
27	```bash
28	python3 scripts/build.py --coverage leads.json
29	```
30	It reports fill rates and names which criteria the data cannot support. There is no point offering geography filtering on an audience where `location` is empty — that just routes everyone to `review` and calls it a result. See The coverage gate below.
31
32	Step 2 — ICP Q&A, informed by step 1. Don't offer criteria the data can't support without saying enrichment is needed first.
33
34	Step 3 — Pass 1, deterministic:
35	```bash
36	python3 scripts/build.py spec.json > pass1.json
37	```
38	It refuses invalid input rather than emitting a best-effort sort. If it errors, fix the spec — never work around it by classifying manually.
39
40	Step 4 — Pass 2, semantic. Mandatory. Read every bucket, `match` first. Write overrides with reasons:
41	```bash
42	python3 scripts/build.py --adjudicate review.json
43	```
44
45	Step 5 — Present counts, segments, and what pass 2 changed.
46
47	Step 6 — Write complementary audiences back (see below), or export a CSV.
48
49	## The coverage gate
50
51	Field fill rates decide what is honestly filterable. Thresholds the script applies:
52
53	\| Field \| Needed for \| Below threshold means \|
54	\|---\|---\|---\|
55	\| `jobTitle` \| Seniority + function detection \| Classification is degraded — most leads land in `review` \|
56	\| `companyName` \| Company-based exclusion \| Exclusion is unreliable \|
57	\| `shortBio` \| Catching people whose company and email are empty \| Own-team and competitor exclusion will leak \|
58	\| `proEmail` \| Domain-based exclusion \| Job-changers slip through \|
59	\| `location` \| Geography filtering \| Geo criteria cannot be applied \|
60	\| `industry` \| Industry filtering \| Industry criteria cannot be applied \|
61
62	When the gate flags gaps, offer profile enrichment — 1 credit per lead. Quote the exact total (the script returns it) and get explicit approval

People who liked this also viewed

6 picks

Type