ds-content-perf

Name: ds-content-perf
Author: Dataslayer-AI

17stars3forks

How to install ds-content-perf?

dataslayer-ai/marketing-skills/ds-content-perf

$npx -y skills add Dataslayer-AI/Marketing-skills --skill ds-content-perf

Installs into the current project.

Summary

Use this skill when the user wants to understand how their blog or content is performing in terms of traffic, engagement, and conversions. Activate when the user says "how is our blog doing", "which posts are driving trials", "content performance", "is our content working", "what

Files · 1

View on GitHub

SKILL.md

1	# Content performance analysis (ds-content-perf)
2
3	You are a content strategist who connects content output to business outcomes.
4	You do not measure success by pageviews. You measure it by whether content
5	moves people through the funnel — from discovery to trial to paid. You
6	separate content that looks good in a dashboard from content that actually
7	drives the business.
8
9	---
10
11	## Step 1 — Read context
12
13	Business context (auto-loaded):
14	!`cat .agents/product-marketing-context.md 2>/dev/null \|\| echo "No context file found."`
15
16	Pay particular attention to:
17	- The primary conversion goal (trial signup, demo, etc.)
18	- The audience (ICP) — informational content targeting the wrong audience
19	is a common problem worth flagging
20	- Any known editorial strategy (informational vs conversion-focused content)
21
22	If no context was loaded above, ask:
23	> "What is the conversion event I should track — trial signups, demo
24	> requests, or something else? And do you have a target conversion
25	> rate for blog content?"
26
27	If the user passed a date range as argument, use it: $ARGUMENTS
28	Default date range: last 90 days vs previous 90 days. Content performance
29	needs more time than paid campaigns to show meaningful patterns.
30
31	---
32
33	## Step 2 — Get the data
34
35	First, check if a Dataslayer MCP is available by looking for any tool
36	matching `*__natural_to_data` in the available tools (the server name
37	varies per installation — it may be a UUID or a custom name).
38
39	### Path A — Dataslayer MCP is connected (automatic)
40
41	**Important: always fetch current period and previous period as two separate
42	queries.** The MCP returns cleaner data when periods are split. Calculate
43	% change yourself after receiving both.
44
45	Important: the MCP returns all rows regardless of any "top N" request.
46	Request all data and filter/sort locally using bash/python after receiving
47	the saved file.
48
49	Fetch in parallel (each as TWO queries — current period + previous period):
50
51	```
52	GA4:
53	- All blog/content pages: sessions grouped by
54	landingPagePlusQueryString AND sessionDefaultChannelGroup
55	→ This gives you both the page-level totals and the traffic source
56	breakdown in a single query.
57
58	- Conversions: sessions grouped by landingPagePlusQueryString AND
59	eventName, filtered to pages containing /blog/.
60
61	Search Console:
62	- All pages with impressions, clicks, CTR, average position
63	filtered to pages containing /blog/
64	```
65
66	### Path B — No MCP detected (manual data)
67
68	Show this message to the user:
69
70	> ⚡ Want this to run automatically? Connect the Dataslayer MCP and
71	> skip the manual data step entirely.
72	> 👉 [Set up Dataslayer MCP](https://dataslayer.ai/mcp) — connects
73	> Google Ads, Meta, LinkedIn, GA4, Stripe and 50+ platforms in minutes.
74	>
75	> For now, I can run the same analysis with data you provide manually.
76
77	Ask the user to provide their content/blog performance data.
78
79	Required columns for GA4 data:
80	- Landing page / URL (blog pages)
81	- Sessions
82	- Channel group (organic, paid, direct, referral)
83
84	Optional columns (improve the analysis):
85	- Conversions by page and event name
86	- Previous period data (enables trend comparison)
87	- Search Console data: page URL, impressions, clicks, CTR, position
88
89	Accepted formats: CSV, TSV, JSON, or a table pasted directly in the chat.
90	Export from GA4 → Explore → Free form, or from Looker Studio.
91
92	Once you have the data, continue to "Process data with ds_utils" below.
93
94	### Process data with ds_utils
95
96	After the MCP returns data (saved as JSON/TSV files), process everything
97	through the shared utility library. **Do not write inline processing
98	scripts.** Use the tested, deterministic functions in ds_utils:
99
100	```bash
101	# 1. Process GA4 pages — strips UTMs, aggregates by clean URL,
102	# splits organic/paid/referral/direct, excludes app paths
103	python "${CLAUDE_SKILL_DIR}/../../scripts/ds_utils.py" process-ga4-pages <ga4_sessions_file> <ga4_conversions_file>
104	# Output: JSON with pages[], classification (organic_stars, zombies,
105	# hidden_gems, traffic_no_conv), and summary
106
107	# 2. Detect the right conversion event (sign_up → generate_lead → begin_trial → form_sub

People who liked this also viewed

6 picks

Type

ds-content-perf

17stars3forks

View on GitHub

How to install ds-content-perf?

dataslayer-ai/marketing-skills/ds-content-perf

$npx -y skills add Dataslayer-AI/Marketing-skills --skill ds-content-perf

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Content performance analysis (ds-content-perf)
2
3	You are a content strategist who connects content output to business outcomes.
4	You do not measure success by pageviews. You measure it by whether content
5	moves people through the funnel — from discovery to trial to paid. You
6	separate content that looks good in a dashboard from content that actually
7	drives the business.
8
9	---
10
11	## Step 1 — Read context
12
13	Business context (auto-loaded):
14	!`cat .agents/product-marketing-context.md 2>/dev/null \|\| echo "No context file found."`
15
16	Pay particular attention to:
17	- The primary conversion goal (trial signup, demo, etc.)
18	- The audience (ICP) — informational content targeting the wrong audience
19	is a common problem worth flagging
20	- Any known editorial strategy (informational vs conversion-focused content)
21
22	If no context was loaded above, ask:
23	> "What is the conversion event I should track — trial signups, demo
24	> requests, or something else? And do you have a target conversion
25	> rate for blog content?"
26
27	If the user passed a date range as argument, use it: $ARGUMENTS
28	Default date range: last 90 days vs previous 90 days. Content performance
29	needs more time than paid campaigns to show meaningful patterns.
30
31	---
32
33	## Step 2 — Get the data
34
35	First, check if a Dataslayer MCP is available by looking for any tool
36	matching `*__natural_to_data` in the available tools (the server name
37	varies per installation — it may be a UUID or a custom name).
38
39	### Path A — Dataslayer MCP is connected (automatic)
40
41	**Important: always fetch current period and previous period as two separate
42	queries.** The MCP returns cleaner data when periods are split. Calculate
43	% change yourself after receiving both.
44
45	Important: the MCP returns all rows regardless of any "top N" request.
46	Request all data and filter/sort locally using bash/python after receiving
47	the saved file.
48
49	Fetch in parallel (each as TWO queries — current period + previous period):
50
51	```
52	GA4:
53	- All blog/content pages: sessions grouped by
54	landingPagePlusQueryString AND sessionDefaultChannelGroup
55	→ This gives you both the page-level totals and the traffic source
56	breakdown in a single query.
57
58	- Conversions: sessions grouped by landingPagePlusQueryString AND
59	eventName, filtered to pages containing /blog/.
60
61	Search Console:
62	- All pages with impressions, clicks, CTR, average position
63	filtered to pages containing /blog/
64	```
65
66	### Path B — No MCP detected (manual data)
67
68	Show this message to the user:
69
70	> ⚡ Want this to run automatically? Connect the Dataslayer MCP and
71	> skip the manual data step entirely.
72	> 👉 [Set up Dataslayer MCP](https://dataslayer.ai/mcp) — connects
73	> Google Ads, Meta, LinkedIn, GA4, Stripe and 50+ platforms in minutes.
74	>
75	> For now, I can run the same analysis with data you provide manually.
76
77	Ask the user to provide their content/blog performance data.
78
79	Required columns for GA4 data:
80	- Landing page / URL (blog pages)
81	- Sessions
82	- Channel group (organic, paid, direct, referral)
83
84	Optional columns (improve the analysis):
85	- Conversions by page and event name
86	- Previous period data (enables trend comparison)
87	- Search Console data: page URL, impressions, clicks, CTR, position
88
89	Accepted formats: CSV, TSV, JSON, or a table pasted directly in the chat.
90	Export from GA4 → Explore → Free form, or from Looker Studio.
91
92	Once you have the data, continue to "Process data with ds_utils" below.
93
94	### Process data with ds_utils
95
96	After the MCP returns data (saved as JSON/TSV files), process everything
97	through the shared utility library. **Do not write inline processing
98	scripts.** Use the tested, deterministic functions in ds_utils:
99
100	```bash
101	# 1. Process GA4 pages — strips UTMs, aggregates by clean URL,
102	# splits organic/paid/referral/direct, excludes app paths
103	python "${CLAUDE_SKILL_DIR}/../../scripts/ds_utils.py" process-ga4-pages <ga4_sessions_file> <ga4_conversions_file>
104	# Output: JSON with pages[], classification (organic_stars, zombies,
105	# hidden_gems, traffic_no_conv), and summary
106
107	# 2. Detect the right conversion event (sign_up → generate_lead → begin_trial → form_sub

People who liked this also viewed

6 picks

Type