@awesomate/hosting-mcp 0.54.0 → 0.55.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/index.js +2 -2
- package/package.json +1 -1
- package/skill/CHANGELOG.json +8 -0
- package/skill/awesomate-email/SKILL.md +291 -0
- package/skill/awesomate-email/evals/ask-never-emailed/graders/grader.md +22 -0
- package/skill/awesomate-email/evals/ask-never-emailed/prompt.md +1 -0
- package/skill/awesomate-email/evals/health-segment/graders/grader.md +20 -0
- package/skill/awesomate-email/evals/health-segment/prompt.md +1 -0
- package/skill/awesomate-email/evals/results-honest/graders/grader.md +19 -0
- package/skill/awesomate-email/evals/results-honest/prompt.md +1 -0
- package/skill/awesomate-email/evals/spam-folder/graders/grader.md +18 -0
- package/skill/awesomate-email/evals/spam-folder/prompt.md +1 -0
- package/skill/awesomate-email/evals/starter-lists-studio/graders/grader.md +21 -0
- package/skill/awesomate-email/evals/starter-lists-studio/prompt.md +1 -0
- package/skill/awesomate-email/evals/write-newsletter/graders/grader.md +24 -0
- package/skill/awesomate-email/evals/write-newsletter/prompt.md +1 -0
- package/skill/awesomate-email/references/asking-permission.md +116 -0
- package/skill/awesomate-email/references/consent-law.md +111 -0
- package/skill/awesomate-email/references/copywriting.md +167 -0
- package/skill/awesomate-email/references/deliverability.md +81 -0
- package/skill/awesomate-email/references/list-planning.md +127 -0
- package/skill/awesomate-email/references/migration.md +101 -0
- package/skill/awesomate-email/references/reporting.md +53 -0
- package/skill/awesomate-email/references/segmentation.md +107 -0
|
@@ -0,0 +1,107 @@
|
|
|
1
|
+
# Groups (segments) that a small business can actually use
|
|
2
|
+
|
|
3
|
+
Read this when choosing who gets a particular email, or when the owner asks
|
|
4
|
+
for "a segment", "a group", "just the people who...".
|
|
5
|
+
|
|
6
|
+
In Awesomate an email goes to everyone on one list who may be emailed, and
|
|
7
|
+
can't be narrowed to a group. There, groups decide what to write, which list
|
|
8
|
+
fits, and when a handful of personal notes would do better than a broadcast.
|
|
9
|
+
Count them with `awesomate_crm_query` and check examples with
|
|
10
|
+
`awesomate_crm_rows`. On a platform that sends to groups, they also decide
|
|
11
|
+
who gets it.
|
|
12
|
+
|
|
13
|
+
## Start from what the business recorded
|
|
14
|
+
|
|
15
|
+
In order of usefulness for a small business:
|
|
16
|
+
|
|
17
|
+
1. **What they bought, booked or had done**, and when. The strongest signal
|
|
18
|
+
there is.
|
|
19
|
+
2. **What is due.** Last service date plus the interval: gas appliance
|
|
20
|
+
service, hot water check, dental recall, car service, term enrolment, tax
|
|
21
|
+
lodgement, lease renewal.
|
|
22
|
+
3. **What they clicked or replied to.** Interest shown in a past email.
|
|
23
|
+
4. **What they told you.** Answers on a sign-up or preferences page.
|
|
24
|
+
5. **Where they are.** Suburb or postcode, for anything local.
|
|
25
|
+
6. **Their role.** Owner vs tenant vs landlord; who pays vs who is on site.
|
|
26
|
+
|
|
27
|
+
Opens are not on this list. Apple Mail and many inbox scanners open emails
|
|
28
|
+
automatically, so "opened" does not mean "read". Never build an "engaged"
|
|
29
|
+
group from opens alone.
|
|
30
|
+
|
|
31
|
+
## Tags: how what the business knows gets in
|
|
32
|
+
|
|
33
|
+
When the email system holds contacts and email activity but not jobs or
|
|
34
|
+
orders, everything else arrives as **tags**. On most platforms an n8n workflow
|
|
35
|
+
can tag people when a job finishes in ServiceM8, an import brings the old
|
|
36
|
+
platform's tags, and the owner can tag people by hand. In Awesomate's Contacts
|
|
37
|
+
& email, tags and fields come in with an import. Tags are what most groups are
|
|
38
|
+
built from, so keep them tidy:
|
|
39
|
+
|
|
40
|
+
- **One idea per tag, in the owner's words, with a consistent prefix** when
|
|
41
|
+
there are many: `service: hot water`, `suburb: Carindale`, `customer:
|
|
42
|
+
regular`, `installed: 2016`. Prefixes make groups easy to read and stop
|
|
43
|
+
near-duplicates ("hotwater", "hot water", "HWS").
|
|
44
|
+
- **Say where each tag comes from**: "added by the ServiceM8 workflow when a
|
|
45
|
+
job is invoiced". A tag nobody can explain is a tag nobody should send on.
|
|
46
|
+
- **A tag is a fact, never permission.** Tagging someone "customer" does not
|
|
47
|
+
put them on a list or make them emailable. Only their consent does.
|
|
48
|
+
- **Retire tags that stop being true** ("quote pending") or the groups built
|
|
49
|
+
on them quietly go wrong.
|
|
50
|
+
- Before creating a tag, look for an existing one that means the same thing.
|
|
51
|
+
|
|
52
|
+
## Recipes
|
|
53
|
+
|
|
54
|
+
| Group | Rule, in a sentence |
|
|
55
|
+
|---|---|
|
|
56
|
+
| New in the last 30 days | Joined any list in the last 30 days. Gets the welcome, not the backlog. |
|
|
57
|
+
| Active customers | Job, booking or purchase in the last 12 months. |
|
|
58
|
+
| Lapsed customers | Last job or purchase more than one buying cycle ago (12 to 18 months for most services; a term for classes). |
|
|
59
|
+
| Subscribers who never bought | On a list, no job or purchase ever. |
|
|
60
|
+
| Due for service | Last service of type X more than its interval ago, no open booking. |
|
|
61
|
+
| Clicked, didn't act | Clicked the booking or buy link in the last send, no booking or order since. |
|
|
62
|
+
| Quiet for six months | No click, reply, booking or purchase in six months. Candidates for one "still want these?" email, then stop. |
|
|
63
|
+
| Local | Postcode in a list, or within N km of the business. |
|
|
64
|
+
| High value | Top 20% by spend in 24 months (retail), or repeat customers (services). |
|
|
65
|
+
| Interested in X | Ticked X on the preferences page, or clicked an X link twice. |
|
|
66
|
+
|
|
67
|
+
For retail, recency, frequency and spend (RFM) groups work well: recent and
|
|
68
|
+
frequent buyers get new arrivals first; high spend but lapsed get a personal
|
|
69
|
+
win-back.
|
|
70
|
+
|
|
71
|
+
## Always leave out
|
|
72
|
+
|
|
73
|
+
- Unsubscribed, hard-bounced and complained. Not a choice.
|
|
74
|
+
- Anyone emailed in the last few days, unless the list promised more.
|
|
75
|
+
- Anyone with an open complaint or a job in dispute. An offer to an unhappy
|
|
76
|
+
customer is how a complaint becomes a review.
|
|
77
|
+
- Staff, family and test addresses (put them in a test group instead).
|
|
78
|
+
- People whose only consent is for another list.
|
|
79
|
+
|
|
80
|
+
## Never build a group from
|
|
81
|
+
|
|
82
|
+
Health conditions or diagnoses, disability, financial hardship, criminal
|
|
83
|
+
record, religion, ethnicity, sexuality, union or political membership, unless
|
|
84
|
+
the person explicitly consented to that information being used for that
|
|
85
|
+
purpose. In Australia most of these are "sensitive information" under the
|
|
86
|
+
Privacy Act and need consent to collect at all. In practice: use an opt-in
|
|
87
|
+
interest ("interested in our Pilates classes") instead of a condition ("has
|
|
88
|
+
back pain").
|
|
89
|
+
|
|
90
|
+
Also avoid groups that feel creepy even when legal: "looked at this page
|
|
91
|
+
three times", "lives on your street". Use what the person would expect the
|
|
92
|
+
business to know.
|
|
93
|
+
|
|
94
|
+
## Size sense
|
|
95
|
+
|
|
96
|
+
- Under about 20 people: consider personal emails from the owner instead of
|
|
97
|
+
a broadcast. They will out-perform any template.
|
|
98
|
+
- A group that is most of the list is not a group. Ask what makes this email
|
|
99
|
+
relevant to only some people.
|
|
100
|
+
- Show the count and two or three example names before using a group, so
|
|
101
|
+
the owner can spot a wrong rule ("why is my accountant in here?").
|
|
102
|
+
|
|
103
|
+
## How to write a group down
|
|
104
|
+
|
|
105
|
+
Name, rule as one sentence, count, and when it was counted. Groups update
|
|
106
|
+
themselves: the count at send time can differ from the count at drafting,
|
|
107
|
+
and each batch re-checks who may be emailed at that moment.
|