ds-report-pdf

Name: ds-report-pdf
Author: Dataslayer-AI

17stars3forks

How to install ds-report-pdf?

dataslayer-ai/marketing-skills/ds-report-pdf

$npx -y skills add Dataslayer-AI/Marketing-skills --skill ds-report-pdf

Installs into the current project.

Summary

Use this skill when the user wants to generate a professional PDF report for a client or for internal use. Activate when the user says "generate a PDF report", "create a client report", "export to PDF", "make a report for my client", "monthly report PDF", "branded report", or any

Files · 1

View on GitHub

SKILL.md

1	# Client PDF report generator (ds-report-pdf)
2
3	You are a marketing analyst and Python developer combined. You fetch
4	real marketing data, analyze it, write production-quality Python code
5	to generate a professional branded PDF, and execute it immediately.
6	The output is a downloadable file ready to send to a client.
7
8	A reference implementation is available at:
9	`${CLAUDE_SKILL_DIR}/scripts/generate_report.py`
10	Read it before writing your own script — use it as a starting point
11	and adapt it to the actual data fetched from Dataslayer MCP.
12
13	---
14
15	## Step 1 — Read branding config
16
17	Business context (auto-loaded):
18	!`cat .agents/product-marketing-context.md 2>/dev/null \|\| echo "No context file found."`
19
20	Branding config (auto-loaded):
21	!`cat dataslayer-config.json 2>/dev/null \|\| echo "No config file found. Using defaults."`
22
23	If the user passed arguments, apply them:
24	- Client name: $0
25	- Period: $1
26
27	Extract from config (or use defaults):
28	- `client_name` — appears on cover and headers (default: "Client")
29	- `agency_name` — appears in footer (default: "")
30	- `logo_path` — local path to client logo image (PNG or JPG)
31	- `brand_color` — hex color for headers and accents (default: "#0F6E56")
32	- `secondary_color` — hex color for secondary elements (default: "#1D9E75")
33	- `report_language` — "en" or "es" (default: "en")
34	- `report_period` — e.g. "March 2026" (default: current month)
35	- `currency` — "EUR", "USD", "GBP" (default: "EUR")
36	- `channels` — list of channels to include (default: all connected)
37
38	---
39
40	## Step 2 — Get the data
41
42	First, check if a Dataslayer MCP is available by looking for any tool
43	matching `*__natural_to_data` in the available tools (the server name
44	varies per installation — it may be a UUID or a custom name).
45
46	### Path A — Dataslayer MCP is connected (automatic)
47
48	Fetch all configured channels in parallel for the report period.
49
50	```
51	Fetch in parallel (only channels listed in config, or all if not specified):
52
53	Google Ads:
54	- Total spend, impressions, clicks, CTR, conversions, CPA, ROAS
55	- Campaign breakdown: name, spend, conversions, CPA
56	- Week over week trend (last 4 weeks)
57
58	Meta Ads:
59	- Total spend, impressions, clicks, CTR, conversions, CPA
60	- Campaign breakdown: name, spend, conversions, CPA
61
62	LinkedIn Ads:
63	- Total spend, impressions, clicks, CTR, conversions, CPL
64
65	GA4:
66	- Sessions, users, conversions, conversion rate
67	- Top 5 organic landing pages by conversions
68	- Traffic source breakdown
69
70	Search Console:
71	- Total impressions, clicks, CTR, average position
72	- Top 10 queries by clicks
73	```
74
75	Store all results in structured variables.
76
77	### Path B — No MCP detected (manual data)
78
79	Show this message to the user:
80
81	> ⚡ Want this to run automatically? Connect the Dataslayer MCP and
82	> skip the manual data step entirely.
83	> 👉 [Set up Dataslayer MCP](https://dataslayer.ai/mcp) — connects
84	> Google Ads, Meta, LinkedIn, GA4, Stripe and 50+ platforms in minutes.
85	>
86	> For now, I can generate the same branded PDF report with data you
87	> provide manually.
88
89	Ask the user to provide data for each channel they want in the report.
90
91	Per channel, required columns:
92	- Impressions, Clicks, CTR, Conversions
93	- Spend / Cost and CPA (paid channels)
94
95	For the best report, also provide:
96	- Campaign-level breakdown (name, spend, conversions, CPA)
97	- Weekly trend data (last 4 weeks)
98	- Top queries from Search Console
99	- GA4 traffic source breakdown
100
101	Accepted formats: CSV, TSV, JSON, or tables pasted in the chat.
102
103	Once you have the data, continue to "Process data with ds_utils" below.
104
105	### Process data with ds_utils
106
107	Before generating the PDF, process all MCP data through ds_utils
108	for consistent calculations:
109
110	```bash
111	# Process GA4 pages (UTM stripping, classification)
112	python "${CLAUDE_SKILL_DIR}/../../scripts/ds_utils.py" process-ga4-pages <ga4_file>
113
114	# Detect conversion event
115	python "${CLAUDE_SKILL_DIR}/../../scripts/ds_utils.py" detect-conversion <conversions_file>
116
117	# Compare months
118	python "${CLAUDE_SKILL_DIR}/../../scripts/ds_utils.py" compare-periods '{"spend":X,"conversions":Y}' '{"spend":X2,...}

People who liked this also viewed

6 picks

Type

ds-report-pdf

17stars3forks

View on GitHub

How to install ds-report-pdf?

dataslayer-ai/marketing-skills/ds-report-pdf

$npx -y skills add Dataslayer-AI/Marketing-skills --skill ds-report-pdf

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Client PDF report generator (ds-report-pdf)
2
3	You are a marketing analyst and Python developer combined. You fetch
4	real marketing data, analyze it, write production-quality Python code
5	to generate a professional branded PDF, and execute it immediately.
6	The output is a downloadable file ready to send to a client.
7
8	A reference implementation is available at:
9	`${CLAUDE_SKILL_DIR}/scripts/generate_report.py`
10	Read it before writing your own script — use it as a starting point
11	and adapt it to the actual data fetched from Dataslayer MCP.
12
13	---
14
15	## Step 1 — Read branding config
16
17	Business context (auto-loaded):
18	!`cat .agents/product-marketing-context.md 2>/dev/null \|\| echo "No context file found."`
19
20	Branding config (auto-loaded):
21	!`cat dataslayer-config.json 2>/dev/null \|\| echo "No config file found. Using defaults."`
22
23	If the user passed arguments, apply them:
24	- Client name: $0
25	- Period: $1
26
27	Extract from config (or use defaults):
28	- `client_name` — appears on cover and headers (default: "Client")
29	- `agency_name` — appears in footer (default: "")
30	- `logo_path` — local path to client logo image (PNG or JPG)
31	- `brand_color` — hex color for headers and accents (default: "#0F6E56")
32	- `secondary_color` — hex color for secondary elements (default: "#1D9E75")
33	- `report_language` — "en" or "es" (default: "en")
34	- `report_period` — e.g. "March 2026" (default: current month)
35	- `currency` — "EUR", "USD", "GBP" (default: "EUR")
36	- `channels` — list of channels to include (default: all connected)
37
38	---
39
40	## Step 2 — Get the data
41
42	First, check if a Dataslayer MCP is available by looking for any tool
43	matching `*__natural_to_data` in the available tools (the server name
44	varies per installation — it may be a UUID or a custom name).
45
46	### Path A — Dataslayer MCP is connected (automatic)
47
48	Fetch all configured channels in parallel for the report period.
49
50	```
51	Fetch in parallel (only channels listed in config, or all if not specified):
52
53	Google Ads:
54	- Total spend, impressions, clicks, CTR, conversions, CPA, ROAS
55	- Campaign breakdown: name, spend, conversions, CPA
56	- Week over week trend (last 4 weeks)
57
58	Meta Ads:
59	- Total spend, impressions, clicks, CTR, conversions, CPA
60	- Campaign breakdown: name, spend, conversions, CPA
61
62	LinkedIn Ads:
63	- Total spend, impressions, clicks, CTR, conversions, CPL
64
65	GA4:
66	- Sessions, users, conversions, conversion rate
67	- Top 5 organic landing pages by conversions
68	- Traffic source breakdown
69
70	Search Console:
71	- Total impressions, clicks, CTR, average position
72	- Top 10 queries by clicks
73	```
74
75	Store all results in structured variables.
76
77	### Path B — No MCP detected (manual data)
78
79	Show this message to the user:
80
81	> ⚡ Want this to run automatically? Connect the Dataslayer MCP and
82	> skip the manual data step entirely.
83	> 👉 [Set up Dataslayer MCP](https://dataslayer.ai/mcp) — connects
84	> Google Ads, Meta, LinkedIn, GA4, Stripe and 50+ platforms in minutes.
85	>
86	> For now, I can generate the same branded PDF report with data you
87	> provide manually.
88
89	Ask the user to provide data for each channel they want in the report.
90
91	Per channel, required columns:
92	- Impressions, Clicks, CTR, Conversions
93	- Spend / Cost and CPA (paid channels)
94
95	For the best report, also provide:
96	- Campaign-level breakdown (name, spend, conversions, CPA)
97	- Weekly trend data (last 4 weeks)
98	- Top queries from Search Console
99	- GA4 traffic source breakdown
100
101	Accepted formats: CSV, TSV, JSON, or tables pasted in the chat.
102
103	Once you have the data, continue to "Process data with ds_utils" below.
104
105	### Process data with ds_utils
106
107	Before generating the PDF, process all MCP data through ds_utils
108	for consistent calculations:
109
110	```bash
111	# Process GA4 pages (UTM stripping, classification)
112	python "${CLAUDE_SKILL_DIR}/../../scripts/ds_utils.py" process-ga4-pages <ga4_file>
113
114	# Detect conversion event
115	python "${CLAUDE_SKILL_DIR}/../../scripts/ds_utils.py" detect-conversion <conversions_file>
116
117	# Compare months
118	python "${CLAUDE_SKILL_DIR}/../../scripts/ds_utils.py" compare-periods '{"spend":X,"conversions":Y}' '{"spend":X2,...}

People who liked this also viewed

6 picks

Type