Plan, measure, and iterate LinkedIn content experiments using post hypotheses, format tests, analytics, comments, and learning loops.
SkillScore95Maintained
Automatic
◆Marketing & Content pack
Last verified 8/16/2026
What it changes
Passed 21 of 22 test cases with the skill, and 8 of 22 without it.
Without skill36%
With skill95%
Checks it passed that the model alone missed
The plan includes a section header titled `## Test Design`.
The document includes a dedicated `## Learning Log` section.
The document contains a dedicated section titled `## Decision Rules`.
and 13 more in the full report
14 fixed7 passed either way0 still failing1 broke
Pass-rate lift
+59 pp
Tokens
-21%
Agent turns
0%
Response time
-36%
Model gemini-3.6-flashMeasured 8/16/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 14
Prompt
Draft the hypothesis section for a LinkedIn experiment comparing infographics vs text lists. I usually just write 'infographics are better'. What key components must a properly structured hypothesis contain?
What was checked, without and with the skill
Checked
Without skill
With skill
The hypothesis combines the target audience, content variable, and expected behavioral signal into a unified statement.
Passed
Passed
The response formats the hypothesis under a `## Hypothesis` section header.
Missed
Passed
case-13 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md64 linessingle file
LinkedIn Post Experimentation
Source Traceability
Primary source: Growth Hacking LinkedIn by Bjorn Radde, especially sections 2.1
"Phases of growth hacking", 2.2 "Growth Hacking LinkedIn", 3.4.1 "Posts",
3.7 "Social Selling Index", and 4.1 "LinkedIn analysis tools". Guidance is
transformed and paraphrased.
Reference Routing
Need
Read
Experiment model and source notes
references/core/knowledge.md
Experiment design rules
references/core/rules.md
Test templates and analysis examples
references/core/examples.md
Run a content experiment
workflows/run-post-experiment.md
Workflow
Turn a content idea into a hypothesis about audience, topic, format, or
response.
Choose one variable to test.
Define metrics before publishing: impressions, engagements, comments, saves,
sends, profile visits, followers, newsletter subscriptions, or qualified
conversations.
Publish, respond to comments, and collect results after a sensible window.
Decide whether to repeat, revise, or stop the content angle.
Output Format
# LinkedIn Content Experiment
## Hypothesis
[Audience + content variable + expected signal.]
## Test Design
- Variable:
- Control or comparison: