Turn a LinkedIn Analytics export

Analytics dashboard

by charlie947 · MIT license · ★ 3,652 on GitHub · updated Sep 15

Turn a LinkedIn Analytics export into an interactive dark-themed React dashboard plus a written strategic analysis with 5 data-backed content recommendations. Reads every sheet in the export, builds charts for engagement trend, follower…

---
name: analytics-dashboard
description: >
Turn a LinkedIn Analytics export into an interactive dark-themed React dashboard plus a written strategic analysis with 5 data-backed content recommendations. Reads every sheet in the export, builds charts for engagement trend, follower growth, post performance scatter, day-of-week heatmap, and audience breakdown. Use this skill whenever the user says "analyse my linkedin", "linkedin analytics", "build my dashboard", "review my performance", or uploads a LinkedIn Analytics export file. Requires the user's LinkedIn Analytics export (xlsx) as input.
---

# Analytics Dashboard

## Codex and Claude runtime

- Use this skill in Codex or Claude with the tools actually available in the current task. `AskUserQuestion` examples describe the questions, not a required API: use an available question tool within its limits, or ask in chat. Reuse answers and source material already supplied.
- Work in the user-selected project. Read its `about-me.md`, `voice.md` and relevant brand files before personalised work. Confirm the intended author if files conflict or contain starter defaults. Ask for missing facts or run `voice-builder`; never inherit the maintainer's identity, accounts or private files.
- Resolve bundled `references/` relative to this skill folder. For an explicitly requested profile refresh, read and update the canonical `about-me.md`, `voice.md` or `newsletter-voice.md` in place, preserving unrelated user facts and rules. Consumers must reread those canonical files. Use a new filename only for new deliverables that would collide with unrelated existing files. Installation alone never starts an interview or writes files. Do not write persistent learnings unless requested.
- Use supplied evidence first. Verify external claims through available search/source tools when needed. If a source or integration is unavailable, name the missing capability and offer supplied text/export input. Never invent facts, first-person experience, metrics or a successful tool run.
- Connect only services needed for the chosen route through the user's existing account. Never print credentials or overwrite connections. Drafting, saving and reviewing do not authorise publishing, sending messages or changing accounts.

## CRITICAL: Auto-start on load

Overview

Read every sheet in the file. Confirm author, reporting window, units and actual column names before calculating. The following sheets are examples, not a guaranteed export schema:

Manual install (npx, ZIP)

Claude Codenpx skills add charlie947/social-media-skills --skill analytics-dashboard -g -a claude-code

Claude Code (manual)

mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/charlie947/social-media-skills/tar.gz/8cefb5b6d037 \
  | tar -xz -C ~/.claude/skills --strip-components=2 social-media-skills-8cefb5b6d037/skills/analytics-dashboard

Windows (PowerShell)

New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/19addea003c321dc7ceb/analytics-dashboard.zip" -OutFile "$env:TEMP\analytics-dashboard.zip"; Expand-Archive "$env:TEMP\analytics-dashboard.zip" -DestinationPath "$HOME\.claude\skills" -Force

Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md7.2 KB

Read the files here

charlie947/8cefb5b1 file

SKILL.md7.2 KB

SKILL.md

Show the full text144 lines

Analytics Dashboard

Codex and Claude runtime

Use this skill in Codex or Claude with the tools actually available in the current task. AskUserQuestion examples describe the questions, not a required API: use an available question tool within its limits, or ask in chat. Reuse answers and source material already supplied.
Work in the user-selected project. Read its about-me.md, voice.md and relevant brand files before personalised work. Confirm the intended author if files conflict or contain starter defaults. Ask for missing facts or run voice-builder; never inherit the maintainer's identity, accounts or private files.
Resolve bundled references/ relative to this skill folder. For an explicitly requested profile refresh, read and update the canonical about-me.md, voice.md or newsletter-voice.md in place, preserving unrelated user facts and rules. Consumers must reread those canonical files. Use a new filename only for new deliverables that would collide with unrelated existing files. Installation alone never starts an interview or writes files. Do not write persistent learnings unless requested.
Use supplied evidence first. Verify external claims through available search/source tools when needed. If a source or integration is unavailable, name the missing capability and offer supplied text/export input. Never invent facts, first-person experience, metrics or a successful tool run.
Connect only services needed for the chosen route through the user's existing account. Never print credentials or overwrite connections. Drafting, saving and reviewing do not authorise publishing, sending messages or changing accounts.

CRITICAL: Auto-start on load

When this skill triggers, go straight to Step 1.

Step 1. Get the export file

Ask:

Upload your LinkedIn Analytics export file (xlsx).

Not sure how to get it? Go to LinkedIn Analytics, set your date range (30, 60, or 90 days works well), and click Export in the top right.

Wait for the file upload.

Step 2. Parse the data

Read every sheet in the file. Confirm author, reporting window, units and actual column names before calculating. The following sheets are examples, not a guaranteed export schema:

DISCOVERY: overall impressions and reach
ENGAGEMENT: daily impressions and engagements over time
TOP POSTS: top 50 posts, ranked by engagements and by impressions (two tables to merge)
FOLLOWERS: daily new followers plus total count
DEMOGRAPHICS: job titles, locations, industries, seniority, company size, top companies

Top-post tables are selected samples, not the account’s entire posting history. Keep their denominators separate from account-wide metrics; do not infer best posting times from daily aggregates. Clean any messy headers. Merge the two TOP POSTS tables (by engagements and by impressions) into one unified dataset per post. De-duplicate.

Step 3. Build the interactive dashboard

Use a supported React artifact surface or the selected project’s existing React and Recharts setup. If neither is available, provide the computed analysis and React source with preview pending; do not silently install dependencies or claim an interactive dashboard is running. Preview and exercise chart tooltips/resizing before calling it verified. Dark theme (background #0f1117), accent colours for charts. Use Recharts for all visualisations.

Include these panels in this order:

Headline metrics (top row cards)

Total impressions
Total reach
Total new followers
Average daily impressions
Average daily engagements
Overall engagement rate (sum of engagements / sum of impressions, for the same reporting window). Zero or missing denominators are unavailable, not zero.
Total posts tracked

Engagement trend (line chart)

Daily impressions (left y-axis) and engagements (right y-axis) over the full date range
Highlight the top 3 spike days with markers

Follower growth (area chart)

Daily new followers
7-day moving average trendline overlaid
Cumulative follower gain

Post performance scatter

X axis: impressions. Y axis: engagements
Colour-code posts into four quadrants:
- Stars: high reach + high engagement
- Viral but shallow: high reach + low engagement
- Niche gold: low reach + high engagement
- Underperformers: low reach + low engagement
Hoverable dots showing post URL and date

Day-of-week heatmap

Average impressions and engagements by day of week
Highlight the strongest days

Audience breakdown (bar charts)

Job titles
Industries
Seniority
Company size
Top locations

Formatting rules

Format numbers: 67K not 67000, 1.2M not 1200000
Total follower count prominent at the top
Responsive layout (works on laptop and large display)
Dark background, high contrast chart colours

Step 4. Written strategic analysis

Below the dashboard, write a concise analysis with these sections:

Performance Summary

Trajectory: growing, plateauing, or declining (use trendlines)
Current engagement rate; compare external benchmarks only with a verified dated source and matching metric definition

Audience-Content Fit

Who the core audience is, based on demographics
Which content topics and formats would resonate
Segments to lean into or away from

Growth Velocity

Average daily follower growth
30, 60, 90 day scenarios at current pace, labelled as extrapolations rather than forecasts
Acceleration or deceleration trends

Day and Timing Strategy

Best days for impressions
Best days for engagement
Optimal posting schedule based on the data

5 Specific Content Recommendations

Each one includes:

Content angle or topic
Why the data supports it
Which audience segment it targets
Evidence and a testable hypothesis, without guaranteed impact

Step 5. Offer the next move

After the analysis:

Want me to draft one of these 5 recommendations as a full post? Call the post-writer or post-formatter skill with the recommendation number.

Rules

Use numbers, not adjectives. "Engagement rate is 2.3%" beats "engagement is healthy".
Keep the analysis direct. No fluff, no filler.
Never invent metrics not present in the export.
Flag data quality issues (missing columns, odd date ranges) instead of silently working around them.
Never use em dashes.
British English unless voice.md specifies otherwise.
Recommend running this monthly. Patterns only surface over time.

1	---
2	name: analytics-dashboard
3	description: >
4	Turn a LinkedIn Analytics export into an interactive dark-themed React dashboard plus a written strategic analysis with 5 data-backed content recommendations. Reads every sheet in the export, builds charts for engagement trend, follower growth, post performance scatter, day-of-week heatmap, and audience breakdown. Use this skill whenever the user says "analyse my linkedin", "linkedin analytics", "build my dashboard", "review my performance", or uploads a LinkedIn Analytics export file. Requires the user's LinkedIn Analytics export (xlsx) as input.
5	---
6
7	# Analytics Dashboard
8
9	## Codex and Claude runtime
10
11	- Use this skill in Codex or Claude with the tools actually available in the current task. `AskUserQuestion` examples describe the questions, not a required API: use an available question tool within its limits, or ask in chat. Reuse answers and source material already supplied.
12	- Work in the user-selected project. Read its `about-me.md`, `voice.md` and relevant brand files before personalised work. Confirm the intended author if files conflict or contain starter defaults. Ask for missing facts or run `voice-builder`; never inherit the maintainer's identity, accounts or private files.
13	- Resolve bundled `references/` relative to this skill folder. For an explicitly requested profile refresh, read and update the canonical `about-me.md`, `voice.md` or `newsletter-voice.md` in place, preserving unrelated user facts and rules. Consumers must reread those canonical files. Use a new filename only for new deliverables that would collide with unrelated existing files. Installation alone never starts an interview or writes files. Do not write persistent learnings unless requested.
14	- Use supplied evidence first. Verify external claims through available search/source tools when needed. If a source or integration is unavailable, name the missing capability and offer supplied text/export input. Never invent facts, first-person experience, metrics or a successful tool run.
15	- Connect only services needed for the chosen route through the user's existing account. Never print credentials or overwrite connections. Drafting, saving and reviewing do not authorise publishing, sending messages or changing accounts.
16
17	## CRITICAL: Auto-start on load
18
19	When this skill triggers, go straight to Step 1.
20
21	## Step 1. Get the export file
22
23	Ask:
24
25	> Upload your LinkedIn Analytics export file (xlsx).
26	>
27	> Not sure how to get it? Go to LinkedIn Analytics, set your date range (30, 60, or 90 days works well), and click Export in the top right.
28
29	Wait for the file upload.
30
31	## Step 2. Parse the data
32
33	Read every sheet in the file. Confirm author, reporting window, units and actual column names before calculating. The following sheets are examples, not a guaranteed export schema:
34
35	- DISCOVERY: overall impressions and reach
36	- ENGAGEMENT: daily impressions and engagements over time
37	- TOP POSTS: top 50 posts, ranked by engagements and by impressions (two tables to merge)
38	- FOLLOWERS: daily new followers plus total count
39	- DEMOGRAPHICS: job titles, locations, industries, seniority, company size, top companies
40
41	Top-post tables are selected samples, not the account’s entire posting history. Keep their denominators separate from account-wide metrics; do not infer best posting times from daily aggregates. Clean any messy headers. Merge the two TOP POSTS tables (by engagements and by impressions) into one unified dataset per post. De-duplicate.
42
43	## Step 3. Build the interactive dashboard
44
45	Use a supported React artifact surface or the selected project’s existing React and Recharts setup. If neither is available, provide the computed analysis and React source with preview pending; do not silently install dependencies or claim an interactive dashboard is running. Preview and exercise chart tooltips/resizing before calling it verified. Dark theme (background `#0f1117`), accent colours for charts. Use Recharts for all visualisations.
46
47	Include these panels in this order:
48
49	### Headline metrics (top row cards)
50	- Total impressions
51	- Total reach
52	- Total new followers
53	- Average daily impressions
54	- Average daily engagements
55	- Overall engagement rate (sum of engagements / sum of impressions, for the same reporting window). Zero or missing denominators are unavailable, not zero.
56	- Total posts tracked
57
58	### Engagement trend (line chart)
59	- Daily impressions (left y-axis) and engagements (right y-axis) over the full date range
60	- Highlight the top 3 spike days with markers
61
62	### Follower growth (area chart)
63	- Daily new followers
64	- 7-day moving average trendline overlaid
65	- Cumulative follower gain
66
67	### Post performance scatter
68	- X axis: impressions. Y axis: engagements
69	- Colour-code posts into four quadrants:
70	- Stars: high reach + high engagement
71	- Viral but shallow: high reach + low engagement
72	- Niche gold: low reach + high engagement
73	- Underperformers: low reach + low engagement
74	- Hoverable dots showing post URL and date
75
76	### Day-of-week heatmap
77	- Average impressions and engagements by day of week
78	- Highlight the strongest days
79
80	### Audience breakdown (bar charts)
81	- Job titles
82	- Industries
83	- Seniority
84	- Company size
85	- Top locations
86
87	### Formatting rules
88	- Format numbers: `67K` not `67000`, `1.2M` not `1200000`
89	- Total follower count prominent at the top
90	- Responsive layout (works on laptop and large display)
91	- Dark background, high contrast chart colours
92
93	## Step 4. Written strategic analysis
94
95	Below the dashboard, write a concise analysis with these sections:
96
97	### Performance Summary
98	- Trajectory: growing, plateauing, or declining (use trendlines)
99	- Current engagement rate; compare external benchmarks only with a verified dated source and matching metric definition
100
101	### Top Post Patterns
102	- Analyse top 10 by impressions and top 10 by engagements
103	- Patterns: posting day, time of month, content themes
104	- High impressions + low engagement: what does that signal?
105	- Low impressions + high engagement: what does that signal?
106
107	### Audience-Content Fit
108	- Who the core audience is, based on demographics
109	- Which content topics and formats would resonate
110	- Segments to lean into or away from
111
112	### Growth Velocity
113	- Average daily follower growth
114	- 30, 60, 90 day scenarios at current pace, labelled as extrapolations rather than forecasts
115	- Acceleration or deceleration trends
116
117	### Day and Timing Strategy
118	- Best days for impressions
119	- Best days for engagement
120	- Optimal posting schedule based on the data
121
122	### 5 Specific Content Recommendations
123	Each one includes:
124	- Content angle or topic
125	- Why the data supports it
126	- Which audience segment it targets
127	- Evidence and a testable hypothesis, without guaranteed impact
128
129	## Step 5. Offer the next move
130
131	After the analysis:
132
133	> Want me to draft one of these 5 recommendations as a full post? Call the post-writer or post-formatter skill with the recommendation number.
134
135	## Rules
136
137	- Use numbers, not adjectives. "Engagement rate is 2.3%" beats "engagement is healthy".
138	- Keep the analysis direct. No fluff, no filler.
139	- Never invent metrics not present in the export.
140	- Flag data quality issues (missing columns, odd date ranges) instead of silently working around them.
141	- Never use em dashes.
142	- British English unless voice.md specifies otherwise.
143	- Recommend running this monthly. Patterns only surface over time.
144