@elitedcs/ghl-mcp 3.72.2 → 3.73.0
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/CHANGELOG.md +63 -0
- package/dist/assessment.html +789 -0
- package/dist/index.js +1587 -485
- package/guide/guide.html +1 -1
- package/package.json +6 -4
- package/templates/action-schemas.json +2 -2
- package/templates/clinic-medspa.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,68 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 3.73.0 — the assessment, for Command OS licensees
|
|
4
|
+
|
|
5
|
+
An agency's first paid conversation with a prospect, and the document that comes out of
|
|
6
|
+
it. This is Command OS only: on the $97 licence these five tools answer with upgrade
|
|
7
|
+
information, and nothing about the GoHighLevel product changes.
|
|
8
|
+
|
|
9
|
+
You sit down with a business owner and go through forty-six questions across eleven
|
|
10
|
+
areas — what a job is worth, what happens to the phone, what happens after a quote goes
|
|
11
|
+
out, who is sitting in their database doing nothing. Each question has the words to say
|
|
12
|
+
out loud and a follow-up for when the answer is vague. At the end you have their numbers,
|
|
13
|
+
what those numbers are costing them each month, how many hours a week are going into work
|
|
14
|
+
a system should do, and a report you hand over with your name on it and nothing of ours.
|
|
15
|
+
|
|
16
|
+
Three rules are enforced in the code rather than left to good intentions, because all
|
|
17
|
+
three are the kind that quietly stop being true when a report needs to look impressive:
|
|
18
|
+
|
|
19
|
+
- **An answer nobody knows omits its finding.** It is never defaulted, estimated, or
|
|
20
|
+
filled in from an industry average. The report says which numbers were missing and what
|
|
21
|
+
to measure first.
|
|
22
|
+
- **Assumptions are yours and they print beside the figure they moved**, not in a footnote.
|
|
23
|
+
Set one to zero and its finding disappears rather than falling back to a default.
|
|
24
|
+
- **There is no minimum number of findings**, and "there is not much here" is a verdict the
|
|
25
|
+
tool will actually reach and say plainly. A report that always finds something will
|
|
26
|
+
invent something.
|
|
27
|
+
|
|
28
|
+
`save_assessment` puts the whole thing in **your own** GoHighLevel — the prospect as a
|
|
29
|
+
contact, the answers as a note you can read in plain English, the deal on an Assessments
|
|
30
|
+
pipeline. We store none of it. That is also what lets someone else on your team pick it
|
|
31
|
+
up: they open the GoHighLevel they already log into.
|
|
32
|
+
|
|
33
|
+
`read_assessment_transcript` turns a recording into answers, and refuses anything the
|
|
34
|
+
owner did not say: every answer must carry their verbatim words, and those words are
|
|
35
|
+
checked against the transcript. Anything worked out rather than heard — "two or three a
|
|
36
|
+
week" becoming eleven a month — is held for you to confirm.
|
|
37
|
+
|
|
38
|
+
`write_assessment_report` writes the finished document to your machine, self-contained so
|
|
39
|
+
it opens anywhere, with a random filename and no-index because it holds another business's
|
|
40
|
+
revenue and customer numbers. We publish it nowhere; the host is yours.
|
|
41
|
+
|
|
42
|
+
## 3.72.3 — the waits in a built account can actually go live
|
|
43
|
+
|
|
44
|
+
Blueprint builds a client's account and then asks whether to publish the workflows or
|
|
45
|
+
leave them as drafts for review. Say publish, and the ones with a wait of a day or more
|
|
46
|
+
were refused by GoHighLevel and stayed as drafts. The build still reported them as
|
|
47
|
+
created, so the account looked finished when the follow-up sequences were not running.
|
|
48
|
+
|
|
49
|
+
The cause was one word. GoHighLevel takes `minutes` and `hour`, but for days it wants
|
|
50
|
+
`days`, and we were sending `day`. It is not a rule you can guess: a workflow that is
|
|
51
|
+
nothing but a wait accepts the singular quite happily, which is why this went unnoticed.
|
|
52
|
+
It only fails on the shape a real nurture has, a message followed by a wait, which is
|
|
53
|
+
every follow-up sequence the presets build. **123 of the waits in the shipped presets
|
|
54
|
+
were affected.**
|
|
55
|
+
|
|
56
|
+
Workflows already in an account are untouched and keep working; this was only ever about
|
|
57
|
+
newly built ones.
|
|
58
|
+
|
|
59
|
+
**The second half is the reporting.** A workflow that could not be published was still
|
|
60
|
+
counted as built, and the summary read the same as a run where nobody asked to publish at
|
|
61
|
+
all: it suggested turning on publishing, to someone who had just turned it on. The real
|
|
62
|
+
reason sat further down the report where nobody looks first. A build now says plainly
|
|
63
|
+
which workflows could not be published, what GoHighLevel said about each, that they are
|
|
64
|
+
sitting as drafts and not running, and that repeating the build will not help.
|
|
65
|
+
|
|
3
66
|
## 3.72.2 — a form you read back can be saved again
|
|
4
67
|
|
|
5
68
|
A subscriber tried to edit one of her forms the documented way: read it with
|