weekly-team-performance

Name: weekly-team-performance
Author: LaGrowthMachine

29stars4forks

How to install weekly-team-performance?

lagrowthmachine/gtm-system/weekly-team-performance

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

Installs into the current project.

Summary

Generate your Weekly Team Performance dashboard from your La Growth Machine data: a head-of-sales cockpit that ranks each sender (rep) on reply rate, your success event (signups/meetings/deals) and conversion, surfaces hot leads going cold, and turns your best reps' campaigns int

Files · 1

View on GitHub

SKILL.md

1	# Weekly Team Performance
2
3	Generate the user's own Weekly Team Performance dashboard: a four-tab live artifact built from
4	their La Growth Machine (LGM) data, ranked by sender identity (rep). This skill is **fully
5	self-contained** — every rule needed to detect the environment, pull data, score, classify, mine
6	patterns, and fill the dashboard is written below. It references no other document except the
7	generic skill-download links table inlined in the handoff section.
8
9	## Job to be done
10
11	Every week, show a head of sales *who's generating the most replies and* the most actual
12	conversions and why**, which hot leads are going cold, and how to spread what the best campaigns do
13	across the reps who are behind — as coaching, not a scoreboard.
14
15	## Three hard rules, always
16
17	1. Only ever show the downloading user's data. Pull exclusively from their connected MCPs.
18	Never inject numbers, rep names, leads, campaign names, replies or examples from anyone else or
19	from this skill's author. The template ships empty; it is filled at runtime with their live
20	values. If a value can't be pulled, render the documented empty state — never a placeholder
21	number and never a value borrowed from somewhere else.
22	2. Rank for visibility, coach without punishing. Reps are sorted by performance and a
23	recommendation may name the rep a winning pattern came from ("apply what {rep}'s campaign does").
24	This is a manager-facing internal tool, so that transparency is intended. The line not to cross:
25	never frame a low performer as failing — a rep below the account average gets "here's the proven
26	fix", never "you're behind". No rep is hidden to spare feelings.
27	3. **The output is a LIVE, INTERACTIVE ARTIFACT — never a saved .html file and never a raw code
28	block.** This is the single most common failure: do NOT write the filled HTML to a file on disk
29	and stop, and do NOT paste it as a fenced code block. You MUST publish it through whatever
30	artifact / canvas / live-preview mechanism your current environment exposes so the user gets
31	a rendered, clickable dashboard they can open and interact with (sort the table, switch tabs,
32	click Fix). On claude.ai and Claude Code this is the Artifacts/canvas surface; in a plain
33	terminal with no artifact surface, say so and offer to open the rendered HTML in a browser
34	instead — but the default and correct output is a live artifact, not a file. Do not hard-code a
35	specific tool name; use the artifact capability that exists. On a refresh, **update the existing
36	artifact rather than creating a new one. `assets/dashboard-template.html` is the build source
37	only** — you fill its single `{{DASHBOARD_DATA}}` token in memory and render the result live.
38
39	---
40
41	## Two modes
42
43	- Setup mode (first run, or LGM isn't connected / no config yet): interactive, conversational,
44	~10-15 minutes. Detect, guide connections, ask the setup questions, persist the config.
45	- Generate mode (every run once `./.wtp/config.json` exists and LGM is connected): run the
46	engine, fill the template, emit the artifact + a short handoff. No step-by-step narration.
47
48	---
49
50	## Phase 0 — Detect (silent, no questions)
51
52	Check your own tool list — never ask what's installed.
53	- LGM MCP present? True if tools like `list_identities`, `list_campaigns`, `get_campaign_stats`,
54	`get_conversations_to_reply`, `search_conversations`, `get_conversation_messages` are available.
55	- CRM / deal MCP present? (HubSpot/Salesforce/Pipedrive) · Airtable MCP? · Stripe?
56	- Companion skills available? `campaign-challenger`, `campaign-impact-analyzer`.
57	Record these booleans and move on. Do not announce the detection.
58
59	## Phase 1 — LGM MCP gate
60
61	If present: say "LGM connected" in one line, continue.
62	If absent: the dashboard is built entir

People who liked this also viewed

6 picks

Type

weekly-team-performance

29stars4forks

View on GitHub

How to install weekly-team-performance?

lagrowthmachine/gtm-system/weekly-team-performance

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Weekly Team Performance
2
3	Generate the user's own Weekly Team Performance dashboard: a four-tab live artifact built from
4	their La Growth Machine (LGM) data, ranked by sender identity (rep). This skill is **fully
5	self-contained** — every rule needed to detect the environment, pull data, score, classify, mine
6	patterns, and fill the dashboard is written below. It references no other document except the
7	generic skill-download links table inlined in the handoff section.
8
9	## Job to be done
10
11	Every week, show a head of sales *who's generating the most replies and* the most actual
12	conversions and why**, which hot leads are going cold, and how to spread what the best campaigns do
13	across the reps who are behind — as coaching, not a scoreboard.
14
15	## Three hard rules, always
16
17	1. Only ever show the downloading user's data. Pull exclusively from their connected MCPs.
18	Never inject numbers, rep names, leads, campaign names, replies or examples from anyone else or
19	from this skill's author. The template ships empty; it is filled at runtime with their live
20	values. If a value can't be pulled, render the documented empty state — never a placeholder
21	number and never a value borrowed from somewhere else.
22	2. Rank for visibility, coach without punishing. Reps are sorted by performance and a
23	recommendation may name the rep a winning pattern came from ("apply what {rep}'s campaign does").
24	This is a manager-facing internal tool, so that transparency is intended. The line not to cross:
25	never frame a low performer as failing — a rep below the account average gets "here's the proven
26	fix", never "you're behind". No rep is hidden to spare feelings.
27	3. **The output is a LIVE, INTERACTIVE ARTIFACT — never a saved .html file and never a raw code
28	block.** This is the single most common failure: do NOT write the filled HTML to a file on disk
29	and stop, and do NOT paste it as a fenced code block. You MUST publish it through whatever
30	artifact / canvas / live-preview mechanism your current environment exposes so the user gets
31	a rendered, clickable dashboard they can open and interact with (sort the table, switch tabs,
32	click Fix). On claude.ai and Claude Code this is the Artifacts/canvas surface; in a plain
33	terminal with no artifact surface, say so and offer to open the rendered HTML in a browser
34	instead — but the default and correct output is a live artifact, not a file. Do not hard-code a
35	specific tool name; use the artifact capability that exists. On a refresh, **update the existing
36	artifact rather than creating a new one. `assets/dashboard-template.html` is the build source
37	only** — you fill its single `{{DASHBOARD_DATA}}` token in memory and render the result live.
38
39	---
40
41	## Two modes
42
43	- Setup mode (first run, or LGM isn't connected / no config yet): interactive, conversational,
44	~10-15 minutes. Detect, guide connections, ask the setup questions, persist the config.
45	- Generate mode (every run once `./.wtp/config.json` exists and LGM is connected): run the
46	engine, fill the template, emit the artifact + a short handoff. No step-by-step narration.
47
48	---
49
50	## Phase 0 — Detect (silent, no questions)
51
52	Check your own tool list — never ask what's installed.
53	- LGM MCP present? True if tools like `list_identities`, `list_campaigns`, `get_campaign_stats`,
54	`get_conversations_to_reply`, `search_conversations`, `get_conversation_messages` are available.
55	- CRM / deal MCP present? (HubSpot/Salesforce/Pipedrive) · Airtable MCP? · Stripe?
56	- Companion skills available? `campaign-challenger`, `campaign-impact-analyzer`.
57	Record these booleans and move on. Do not announce the detection.
58
59	## Phase 1 — LGM MCP gate
60
61	If present: say "LGM connected" in one line, continue.
62	If absent: the dashboard is built entir

People who liked this also viewed

6 picks

Type