fix(linkedin-studio): downgrade A/B significance claim to directional

Wave 2 / Step 6 of the remediation plan.

Organic personal-post A/B tests gather a handful of posts per variant — far below
the volume a significance test needs — so the tool must not imply statistical
significance:
- Rename the results-table "Significant?" column to "Directional?" and define it
  as "clears the ~20% minimum-meaningful-difference AND points the same way across
  most posts" — a direction to test further, not a significant result.
- Reword the "20% significance rule" to a minimum-meaningful-difference effect-size
  heuristic (explicitly NOT statistical significance).
- Replace the "3 = Medium, 5+ = High" confidence ladder with a directional-only
  confidence section: treat every result as directional (not significant) given
  realistic volume is well under ~50 conversions/variant; name a direction, not a
  winner.

The 20% minimum-meaningful-difference threshold itself stays — it is a legitimate
effect-size heuristic; only the significance framing was the false claim.

Verify: no "Significant?"/"20% significance" remain; "directional" present;
structural lint 0 failed.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

plugins/linkedin-studio/commands/ab-test.md

@@ -274,7 +274,7 @@ Read each file and check if both variants have 3+ posts logged. Present only tes
 Read the test file. For each variant:
 - Calculate average for each metric (impressions, engagement rate, comments, reposts)
 - Calculate percentage difference: ((B_avg - A_avg) / A_avg) * 100
-- Apply the 20% significance rule from the framework
+- Apply the framework's minimum-meaningful-difference threshold (default 20%). This is an effect-size heuristic for "is the gap worth acting on" — NOT a test of statistical significance (organic personal-post volume rarely reaches it)
 
 ### 2c.3: Cross-Reference Analytics Data
 
@@ -298,13 +298,15 @@ Output the analysis in this format:
 **Posts per variant:** A: [X], B: [Y]
 
 ### Results Comparison
-| Metric | Variant A (Avg) | Variant B (Avg) | Difference | Significant? |
+| Metric | Variant A (Avg) | Variant B (Avg) | Difference | Directional? |
 |--------|----------------|----------------|------------|--------------|
 | Impressions | X | X | +X% | Yes/No |
 | Engagement Rate | X% | X% | +X% | Yes/No |
 | Comments | X | X | +X% | Yes/No |
 | Reposts | X | X | +X% | Yes/No |
 
+_"Directional?" = the gap clears the ~20% minimum-meaningful-difference AND points the same way across most posts. It is a direction to test further, not a statistically significant result._
+
 ### Verdict
 [Clear recommendation based on the data:]
 - **Adopt B:** If B wins with >20% difference on primary metric
@@ -312,11 +314,17 @@ Output the analysis in this format:
 - **Inconclusive:** If results are mixed or inconsistent across posts
 - **Extend test:** If sample size is borderline or results are close to 20% threshold
 
-### Confidence Level
-**[High/Medium/Low]**
-- Based on sample size (3 = Medium, 5+ = High)
-- Based on consistency across individual posts
-- Based on alignment with secondary metrics
+### Confidence Level (directional only)
+**[Directional signal: weak / moderate / strong]**
+
+Organic personal-post volume rarely reaches statistical significance: with the
+handful of posts per variant a creator realistically gathers (well under the
+~50 conversions/variant a significance test would need), treat every result as
+**directional, not significant**. Do not declare a statistically confident
+"winner" — name a direction to test further. Judge the strength of that signal on:
+- Consistency across individual posts (did B beat A on most posts, or one outlier?)
+- Size of the gap relative to the ~20% minimum-meaningful-difference threshold
+- Alignment with secondary metrics
 
 ### Key Insight
 [One sentence capturing the most important learning for their content strategy]