weekly-performance-advisor

Name: weekly-performance-advisor
Author: LaGrowthMachine

12installs4forks

How to install weekly-performance-advisor?

lagrowthmachine/gtm-system/weekly-performance-advisor

$npx -y skills add LaGrowthMachine/gtm-system --skill weekly-performance-advisor

Installs into the current project.

Summary

Generate your Weekly Performance Advisor dashboard from your La Growth Machine data: a two-tab cockpit (To do + Weekly performance) that flags campaigns to fix, sorts replies by urgency, and tracks reply volume week over week. It pulls only YOUR live LGM data, scores each running

Files · 1

View on GitHub

SKILL.md

1	# Weekly Performance Advisor
2
3	Generate the user's own Weekly Performance Advisor: a two-tab live artifact built from their
4	La Growth Machine (LGM) data. This skill is fully self-contained — every rule needed to detect
5	the environment, score campaigns, classify replies, and fill the dashboard is written below. It
6	references no other document.
7
8	Two hard rules, always:
9
10	1. Only ever show the downloading user's data. Pull exclusively from their connected MCPs.
11	Never inject numbers, campaign names, replies, or examples from anyone else. The template ships
12	empty; it is filled at runtime with their live values. If you cannot pull a value, render the
13	documented empty state — never a placeholder number and never a value borrowed from somewhere else.
14	2. The output is a LIVE ARTIFACT, not a saved HTML file. In Generate mode you fill the template
15	in memory and render it as a live artifact using the available artifact tool (whatever the
16	current Cowork build exposes for creating/updating an artifact — do not hard-code a tool name).
17	On a refresh, update the existing artifact rather than creating a new one. The
18	`assets/dashboard-template.html` file is the build source only.
19
20	---
21
22	## Two modes
23
24	- Setup mode (first run, or when LGM isn't connected / no identity chosen yet): interactive.
25	Detect the environment, guide install if needed, ask the scoping questions. Conversational.
26	- Generate mode (every run once setup is done): run the engine, fill the template, emit the
27	artifact + a short handoff. Apply output discipline here — return the artifact and a few lines of
28	handoff, no step-by-step narration.
29
30	If setup was already done in this project (a `./.lgm-wpa/` snapshot exists and LGM is connected),
31	skip straight to Generate mode; only re-ask a question if something is missing.
32
33	---
34
35	## Phase 0 — Detect (silent, no questions)
36
37	Check your own tool list — do not ask the user what they have installed.
38
39	- LGM MCP present? True if tools named `mcp__*` for La Growth Machine are available, i.e. any of
40	`list_identities`, `list_campaigns`, `get_campaign_stats`, `get_conversations_to_reply`,
41	`get_conversation_messages`, `search_conversations`. (In a terminal you could also confirm with
42	`claude mcp list` showing an LGM server, but tool presence is enough — never ask the user.)
43	- CRM / deal MCP present? Is a HubSpot MCP available (deal/company/contact tools)?
44	- `campaign-impact-analyzer` skill available? (used to build the optional deal/€ layer.)
45
46	Record these three booleans and move on. Do not announce the detection.
47
48	---
49
50	## Phase 1 — LGM MCP gate
51
52	If the LGM MCP is present: say "LGM connected ✓" in one line and go to Phase 2.
53
54	If the LGM MCP is absent: the dashboard is built entirely from LGM data, so it can't run yet.
55	Explain that in one sentence, then guide the install (do not ask "is it installed?" — you already
56	know it isn't):
57
58	1. From the `gtm-system` repo, run the installer and complete browser sign-in:
59	```bash
60	sh install.sh
61	```
62	(or the curl one-liner the repo's README provides). Auth is browser OAuth — there is **no API
63	key to paste**.
64	2. No LGM account yet → point them to register at https://app.lagrowthmachine.com and then re-run
65	the installer.
66	3. After they've run it, re-detect (Phase 0). Loop until the LGM tools appear, then continue.
67
68	Keep this friendly and short; it's a gate, not a lecture.
69
70	---
71
72	## Phase 2 — Identity scope (a real question)
73
74	Call `list_identities`. Then, to pick a sensible default, get each identity's campaign load: call
75	`list_campaigns {status:"RUNNING"}` (paginate) and count RUNNING campaigns per `identity.id`.
76
77	Ask which identity to track, defaulting to the identity running the most RUNNING campaigns
78	(name it, and ask them to confirm or switch). Mention they c

People who liked this also viewed

6 picks

Type

weekly-performance-advisor

12installs4forks

View on GitHub

How to install weekly-performance-advisor?

lagrowthmachine/gtm-system/weekly-performance-advisor

$npx -y skills add LaGrowthMachine/gtm-system --skill weekly-performance-advisor

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Weekly Performance Advisor
2
3	Generate the user's own Weekly Performance Advisor: a two-tab live artifact built from their
4	La Growth Machine (LGM) data. This skill is fully self-contained — every rule needed to detect
5	the environment, score campaigns, classify replies, and fill the dashboard is written below. It
6	references no other document.
7
8	Two hard rules, always:
9
10	1. Only ever show the downloading user's data. Pull exclusively from their connected MCPs.
11	Never inject numbers, campaign names, replies, or examples from anyone else. The template ships
12	empty; it is filled at runtime with their live values. If you cannot pull a value, render the
13	documented empty state — never a placeholder number and never a value borrowed from somewhere else.
14	2. The output is a LIVE ARTIFACT, not a saved HTML file. In Generate mode you fill the template
15	in memory and render it as a live artifact using the available artifact tool (whatever the
16	current Cowork build exposes for creating/updating an artifact — do not hard-code a tool name).
17	On a refresh, update the existing artifact rather than creating a new one. The
18	`assets/dashboard-template.html` file is the build source only.
19
20	---
21
22	## Two modes
23
24	- Setup mode (first run, or when LGM isn't connected / no identity chosen yet): interactive.
25	Detect the environment, guide install if needed, ask the scoping questions. Conversational.
26	- Generate mode (every run once setup is done): run the engine, fill the template, emit the
27	artifact + a short handoff. Apply output discipline here — return the artifact and a few lines of
28	handoff, no step-by-step narration.
29
30	If setup was already done in this project (a `./.lgm-wpa/` snapshot exists and LGM is connected),
31	skip straight to Generate mode; only re-ask a question if something is missing.
32
33	---
34
35	## Phase 0 — Detect (silent, no questions)
36
37	Check your own tool list — do not ask the user what they have installed.
38
39	- LGM MCP present? True if tools named `mcp__*` for La Growth Machine are available, i.e. any of
40	`list_identities`, `list_campaigns`, `get_campaign_stats`, `get_conversations_to_reply`,
41	`get_conversation_messages`, `search_conversations`. (In a terminal you could also confirm with
42	`claude mcp list` showing an LGM server, but tool presence is enough — never ask the user.)
43	- CRM / deal MCP present? Is a HubSpot MCP available (deal/company/contact tools)?
44	- `campaign-impact-analyzer` skill available? (used to build the optional deal/€ layer.)
45
46	Record these three booleans and move on. Do not announce the detection.
47
48	---
49
50	## Phase 1 — LGM MCP gate
51
52	If the LGM MCP is present: say "LGM connected ✓" in one line and go to Phase 2.
53
54	If the LGM MCP is absent: the dashboard is built entirely from LGM data, so it can't run yet.
55	Explain that in one sentence, then guide the install (do not ask "is it installed?" — you already
56	know it isn't):
57
58	1. From the `gtm-system` repo, run the installer and complete browser sign-in:
59	```bash
60	sh install.sh
61	```
62	(or the curl one-liner the repo's README provides). Auth is browser OAuth — there is **no API
63	key to paste**.
64	2. No LGM account yet → point them to register at https://app.lagrowthmachine.com and then re-run
65	the installer.
66	3. After they've run it, re-detect (Phase 0). Loop until the LGM tools appear, then continue.
67
68	Keep this friendly and short; it's a gate, not a lecture.
69
70	---
71
72	## Phase 2 — Identity scope (a real question)
73
74	Call `list_identities`. Then, to pick a sensible default, get each identity's campaign load: call
75	`list_campaigns {status:"RUNNING"}` (paginate) and count RUNNING campaigns per `identity.id`.
76
77	Ask which identity to track, defaulting to the identity running the most RUNNING campaigns
78	(name it, and ask them to confirm or switch). Mention they c

People who liked this also viewed

6 picks

Type