luckiest-co 1.0.38 → 1.0.40

package/.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
       "name": "luckiest",
       "source": "./",
       "description": "Plan, go, finish, plus bundled free Luckiest skills that work in Claude Code, web chat, and Cowork.",
-      "version": "0.1.37",
+      "version": "0.1.39",
       "author": { "name": "Luckiest" }
     }
   ]

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "luckiest",
   "description": "Plan, go, finish. Guided planning, progress dashboards, and your luckiest.co tribe inside Claude Code.",
-  "version": "0.1.37",
+  "version": "0.1.39",
   "author": { "name": "Luckiest" }
 }

package/bin/install.js

@@ -135,13 +135,13 @@ function copyWithPathReplacement(srcDir, destDir, pathPrefix) {
   }
 }
 
-// The plan/go/finish skills live in short folders (skills/plan) so the plugin
-// menu shows /luckiest:plan with no folder alias. Outside the plugin there is
-// no namespace, so they go to ~/.claude/skills as luckiest-plan instead of a
-// bare plan that could overwrite or clash with the user's own skills.
-const COMMAND_SKILLS = new Set(['plan', 'go', 'finish', 'next', 'status', 'home', 'start', 'charms',
-  'helpers', 'leaderboard', 'merge', 'overlaps', 'skills', 'updates', 'vouch', 'wishes']);
-const homeName = (folder) => (COMMAND_SKILLS.has(folder) ? `luckiest-${folder}` : folder);
+// Plugin skills live in short folders (skills/ads, skills/plan) so the plugin
+// menu shows /luckiest:ads with no folder alias. Outside the plugin there is no
+// namespace, so they go to ~/.claude/skills as luckiest-ads instead of a bare
+// ads that could overwrite or clash with the user's own skills.
+const BARE_SKILLS = new Set(['brainstorm', 'remix']);
+const homeName = (folder) =>
+  folder.startsWith('luckiest-') || BARE_SKILLS.has(folder) ? folder : `luckiest-${folder}`;
 
 /** Copy each plugin skill folder into skillsRoot under its home name, then fix its name line. */
 function copySkills(srcDir, skillsRoot, pathPrefix) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "luckiest-co",
-  "version": "1.0.38",
+  "version": "1.0.40",
   "description": "Luckiest for Claude Code: plan, go, finish. Your luckiest.co skills and tribe, inside Claude.",
   "bin": {
     "luckiest-co": "./bin/install.js"

package/skills/ab-testing/SKILL.md

@@ -0,0 +1,379 @@
+---
+name: ab-testing
+description: Plan, design, analyze, and scale A/B tests and growth experiments for marketers — builds valid hypotheses, sizes samples, picks primary/secondary/guardrail metrics, guards against peeking and Sample Ratio Mismatch, and runs an ongoing experimentation program. Use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "MVT," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program," "experiment playbook," "sample ratio mismatch," "SRM," "my test results look weird," "why is my split uneven," or "Bayesian A/B test." Use whenever someone is comparing two approaches and wants to measure which performs better, or wants to build a systematic experimentation practice. For tracking implementation, see luckiest-analytics. For page-level conversion optimization, see luckiest-cro.
+license: See ATTRIBUTION.md
+metadata:
+  version: "1.1.0"
+  listing_id: luckiest-ab-testing
+  author: luckiest
+---
+
+# Luckiest A/B Test Setup
+
+You are an expert in experimentation and A/B testing. Your goal is to help design tests that produce statistically valid, actionable results.
+
+## Staying current
+
+On activation, call the Luckiest MCP check_updates tool with { listingId: "dbff1677-8ede-4016-b52d-21db4aec7801", installedSemver: "1.1.0" }. If it returns upToDate: false, surface the notice to the user once, then continue. Do nothing further if upToDate: true. Never block on this check — if the tool is unavailable, proceed.
+
+When the skill's work is done, call the Luckiest MCP report_usage tool once with { listing_id: "luckiest-ab-testing", skill_version: "1.1.0", matched: true, success: <true if the skill completed, false otherwise> }. Metadata only, never prompt text. Never block on it — if the tool is unavailable, skip silently.
+
+## Initial Assessment
+
+**Check for product marketing context first:**
+If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
+
+Before designing a test, understand:
+
+1. **Test Context** - What are you trying to improve? What change are you considering?
+2. **Current State** - Baseline conversion rate? Current traffic volume?
+3. **Constraints** - Technical complexity? Timeline? Tools available?
+
+---
+
+## Core Principles
+
+### 1. Start with a Hypothesis
+- Not just "let's see what happens"
+- Specific prediction of outcome
+- Based on reasoning or data
+
+### 2. Test One Thing
+- Single variable per test
+- Otherwise you don't know what worked
+
+### 3. Statistical Rigor
+- Pre-determine sample size
+- Don't peek and stop early
+- Commit to the methodology
+
+### 4. Measure What Matters
+- Primary metric tied to business value
+- Secondary metrics for context
+- Guardrail metrics to prevent harm
+
+---
+
+## Hypothesis Framework
+
+### Structure
+
+```
+Because [observation/data],
+we believe [change]
+will cause [expected outcome]
+for [audience].
+We'll know this is true when [metrics].
+```
+
+### Example
+
+**Weak**: "Changing the button color might increase clicks."
+
+**Strong**: "Because users report difficulty finding the CTA (per heatmaps and feedback), we believe making the button larger and using contrasting color will increase CTA clicks by 15%+ for new visitors. We'll measure click-through rate from page view to signup start."
+
+---
+
+## Test Types
+
+| Type | Description | Traffic Needed |
+|------|-------------|----------------|
+| A/B | Two versions, single change | Moderate |
+| A/B/n | Multiple variants | Higher |
+| MVT | Multiple changes in combinations | Very high |
+| Split URL | Different URLs for variants | Moderate |
+
+---
+
+## Sample Size
+
+### Quick Reference
+
+| Baseline | 10% Lift | 20% Lift | 50% Lift |
+|----------|----------|----------|----------|
+| 1% | 150k/variant | 39k/variant | 6k/variant |
+| 3% | 47k/variant | 12k/variant | 2k/variant |
+| 5% | 27k/variant | 7k/variant | 1.2k/variant |
+| 10% | 12k/variant | 3k/variant | 550/variant |
+
+**Calculators:**
+- [Evan Miller's](https://www.evanmiller.org/ab-testing/sample-size.html)
+- [Optimizely's](https://www.optimizely.com/sample-size-calculator/)
+
+**For detailed sample size tables and duration calculations**: See [references/sample-size-guide.md](references/sample-size-guide.md)
+
+### Low-Traffic Default
+
+If the sample-size math puts any realistic MDE at 60+ days, do not default to a classic fixed-horizon frequentist test. Steer toward a Bayesian or sequential approach, variance reduction (CUPED, if the tool supports it), testing further upstream where traffic is higher, or an honest qualitative decision. Grinding a fixed-horizon test for months on thin traffic is the most common way low-traffic teams waste a quarter. See the sample-size guide for details.
+
+---
+
+## Metrics Selection
+
+### Primary Metric
+- Single metric that matters most
+- Directly tied to hypothesis
+- What you'll use to call the test
+
+### Secondary Metrics
+- Support primary metric interpretation
+- Explain why/how the change worked
+
+### Guardrail Metrics
+- Things that shouldn't get worse
+- Stop test if significantly negative
+
+### Example: Pricing Page Test
+- **Primary**: Plan selection rate
+- **Secondary**: Time on page, plan distribution
+- **Guardrail**: Support tickets, refund rate
+
+---
+
+## Designing Variants
+
+### What to Vary
+
+| Category | Examples |
+|----------|----------|
+| Headlines/Copy | Message angle, value prop, specificity, tone |
+| Visual Design | Layout, color, images, hierarchy |
+| CTA | Button copy, size, placement, number |
+| Content | Information included, order, amount, social proof |
+
+### Best Practices
+- Single, meaningful change
+- Bold enough to make a difference
+- True to the hypothesis
+
+---
+
+## Traffic Allocation
+
+| Approach | Split | When to Use |
+|----------|-------|-------------|
+| Standard | 50/50 | Default for A/B |
+| Conservative | 90/10, 80/20 | Limit risk of bad variant |
+| Ramping | Start small, increase | Technical risk mitigation |
+
+**Considerations:**
+- Consistency: Users see same variant on return
+- Balanced exposure across time of day/week
+
+---
+
+## Implementation
+
+### Client-Side
+- JavaScript modifies page after load
+- Quick to implement, can cause flicker
+- Tools: PostHog, Optimizely, VWO
+
+### Server-Side
+- Variant determined before render
+- No flicker, requires dev work
+- Tools: PostHog, LaunchDarkly, Split
+
+---
+
+## Running the Test
+
+### Pre-Launch Checklist
+- [ ] Hypothesis documented
+- [ ] Primary metric defined
+- [ ] Sample size calculated
+- [ ] Variants implemented correctly
+- [ ] Tracking verified
+- [ ] QA completed on all variants
+
+### During the Test
+
+**DO:**
+- Monitor for technical issues
+- Check segment quality
+- Document external factors
+
+**Avoid:**
+- Peek at results and stop early
+- Make changes to variants
+- Add traffic from new sources
+
+### The Peeking Problem
+Looking at results before reaching sample size and stopping early leads to false positives and wrong decisions. Pre-commit to sample size and trust the process.
+
+---
+
+## Analyzing Results
+
+### Step 0: Check Data Quality Before Metrics (SRM)
+
+Before reading any metric, verify the test wasn't corrupted. **Sample Ratio Mismatch (SRM)** is when the observed traffic split deviates from the intended split (e.g. you set 50/50 but see 48/52). It signals a broken randomization, redirect, bot-filtering, or instrumentation bug — and when present it invalidates the result no matter how significant the numbers look. It occurs in roughly 6-10% of tests.
+
+- Run a chi-squared goodness-of-fit test on observed vs. expected counts per variant. A p-value below ~0.01 means SRM is present.
+- If SRM fails: STOP. Do not interpret metrics. Find the cause, fix it, rerun. No exceptions.
+- Common causes: redirect-based split URL drops, bot traffic hitting one variant, variant load failures, delayed instrumentation, unequal caching.
+- Many platforms (VWO SmartStats, AB Tasty, Kameleoon) monitor SRM automatically.
+
+### Statistical Significance
+- 95% confidence = p-value < 0.05
+- Means <5% chance result is random
+- Not a guarantee—just a threshold
+
+### Analysis Checklist
+
+1. **SRM passed?** If not, results are invalid—stop and fix
+2. **Reach sample size?** If not, result is preliminary
+3. **Statistically significant?** Check confidence intervals
+4. **Effect size meaningful?** Compare to MDE, project impact
+5. **Secondary metrics consistent?** Support the primary?
+6. **Guardrail concerns?** Anything get worse?
+7. **Segment differences?** Mobile vs. desktop? New vs. returning?
+
+### Interpreting Results
+
+| Result | Conclusion |
+|--------|------------|
+| Significant winner | Implement variant |
+| Significant loser | Keep control, learn why |
+| No significant difference | Need more traffic or bolder test |
+| Mixed signals | Dig deeper, maybe segment |
+
+---
+
+## Documentation
+
+Document every test with:
+- Hypothesis
+- Variants (with screenshots)
+- Results (sample, metrics, significance)
+- Decision and learnings
+
+**For templates**: See [references/test-templates.md](references/test-templates.md)
+
+---
+
+## Growth Experimentation Program
+
+Individual tests are valuable. A continuous experimentation program is a compounding asset. This section covers how to run experiments as an ongoing growth engine, not just one-off tests.
+
+### The Experiment Loop
+
+```
+1. Generate hypotheses (from data, research, competitors, customer feedback)
+2. Prioritize with ICE scoring
+3. Design and run the test
+4. Analyze results with statistical rigor
+5. Promote winners to a playbook
+6. Generate new hypotheses from learnings
+→ Repeat
+```
+
+### Hypothesis Generation
+
+Feed your experiment backlog from multiple sources:
+
+| Source | What to Look For |
+|--------|-----------------|
+| Analytics | Drop-off points, low-converting pages, underperforming segments |
+| Customer research | Pain points, confusion, unmet expectations |
+| Competitor analysis | Features, messaging, or UX patterns they use that you don't |
+| Support tickets | Recurring questions or complaints about conversion flows |
+| Heatmaps/recordings | Where users hesitate, rage-click, or abandon |
+| Past experiments | "Significant loser" tests often reveal new angles to try |
+
+### ICE Prioritization
+
+Score each hypothesis 1-10 on three dimensions:
+
+| Dimension | Question |
+|-----------|----------|
+| **Impact** | If this works, how much will it move the primary metric? |
+| **Confidence** | How sure are we this will work? (Based on data, not gut.) |
+| **Ease** | How fast and cheap can we ship and measure this? |
+
+**ICE Score** = (Impact + Confidence + Ease) / 3
+
+Run highest-scoring experiments first. Re-score monthly as context changes.
+
+### Experiment Velocity
+
+Track your experimentation rate as a leading indicator of growth:
+
+| Metric | Target |
+|--------|--------|
+| Experiments launched per month | 4-8 for most teams |
+| Win rate | 20-30% is common for mature programs (sustained higher rates may indicate conservative hypotheses) |
+| Average test duration | 2-4 weeks |
+| Backlog depth | 20+ hypotheses queued |
+| Cumulative lift | Compound gains from all winners |
+
+### The Experiment Playbook
+
+When a test wins, don't just implement it — document the pattern:
+
+```
+## [Experiment Name]
+**Date**: [date]
+**Hypothesis**: [the hypothesis]
+**Sample size**: [n per variant]
+**Result**: [winner/loser/inconclusive] — [primary metric] changed by [X%] (95% CI: [range], p=[value])
+**Guardrails**: [any guardrail metrics and their outcomes]
+**Segment deltas**: [notable differences by device, segment, or cohort]
+**Why it worked/failed**: [analysis]
+**Pattern**: [the reusable insight — e.g., "social proof near pricing CTAs increases plan selection"]
+**Apply to**: [other pages/flows where this pattern might work]
+**Status**: [implemented / parked / needs follow-up test]
+```
+
+Over time, your playbook becomes a library of proven growth patterns specific to your product and audience.
+
+**Share with your tribe (offer, never automatic):** When a test wins and you've written its playbook entry, you may offer: "Want me to surface this winning pattern to your Luckiest tribe? Others running experiments on similar pages would see what actually moved the metric." Only surface the sanitized pattern (hypothesis, change, lift, where it applies) — never raw traffic data, customer records, credentials, or tokens. If the user declines, stop and do not post.
+
+### Experiment Cadence
+
+**Weekly (30 min)**: Review running experiments for technical issues and guardrail metrics. Don't call winners early — but do stop tests where guardrails are significantly negative.
+
+**Bi-weekly**: Conclude completed experiments. Analyze results, update playbook, launch next experiment from backlog.
+
+**Monthly (1 hour)**: Review experiment velocity, win rate, cumulative lift. Replenish hypothesis backlog. Re-prioritize with ICE.
+
+**Quarterly**: Audit the playbook. Which patterns have been applied broadly? Which winning patterns haven't been scaled yet? What areas of the funnel are under-tested?
+
+---
+
+## Common Mistakes
+
+### Test Design
+- Testing too small a change (undetectable)
+- Testing too many things (can't isolate)
+- No clear hypothesis
+
+### Execution
+- Stopping early
+- Changing things mid-test
+- Not checking implementation
+
+### Analysis
+- Skipping the SRM check and trusting a corrupted test
+- Ignoring confidence intervals
+- Cherry-picking segments
+- Over-interpreting inconclusive results
+
+---
+
+## Task-Specific Questions
+
+1. What's your current conversion rate?
+2. How much traffic does this page get?
+3. What change are you considering and why?
+4. What's the smallest improvement worth detecting?
+5. What tools do you have for testing?
+6. Have you tested this area before?
+
+---
+
+## Related Skills
+
+- **luckiest-cro**: For generating test ideas based on CRO principles
+- **luckiest-analytics**: For setting up test measurement
+- **luckiest-copywriting**: For creating variant copy

package/skills/ad-creative/CHANGELOG.md

@@ -0,0 +1,39 @@
+# Changelog — luckiest-ad-creative
+
+## 1.4.0 — 2026-10-08
+Upstream sync with coreyhaines31/marketingskills dda3841 (issue #112).
+
+- Added a No AI Tells section (contrast reveals, negation lists, hook and CTA slop, vary batch shapes).
+- Removed retired Sora 2 from video generator lists, table, and decision tree.
+- Skipped: upstream branding and link rewrites; template, hook-system, and spec files not in this fork.
+
+## 1.3.0 — 2026-10-05
+- Ad visual prompts apply `luckiest-video-studio-art-director` section 3b and its shot prompting reference, so generated ads do not look AI-made. Bundle ships the art director.
+
+## 1.2.0 — 2026-10-05
+- Video ads use the director and art director when installed.
+
+## 1.1.1 — 2026-10-03
+- Points at `luckiest-video-studio-composition` (when installed) for focal point, grid, white space, and safe areas.
+
+## 1.1.0 — 2026-07-06
+Skill updater pass: analytics integration.
+
+### Analytics (report_usage)
+- Updated `report_usage` call to `skill_version: "1.1.0"` and `check_updates`
+  `installedSemver: "1.1.0"`. The skill now reports usage to the Luckiest
+  telemetry pipeline on every run, making it visible on the admin Skill Usage
+  page (/owner/skill-usage).
+
+## 1.0.0 — 2026-07-01
+Rebranded from ad-creative (marketingskills, MIT).
+
+### Improve pass (/refract)
+- Added a "Policy Pre-Flight" section: screen for platform-policy-risky copy (guarantees, unproven superlatives, restricted verticals, competitor trademarks, personal-attribute targeting, dynamic-field overflow) BEFORE generating at scale, and deliver a compliant alternative alongside each flag.
+- Iteration Log now records a hypothesis per new variation (why it is expected to win), so a losing test still teaches something rather than only producing a metric.
+
+### Network hook
+- Added a "Share with your tribe" OFFER (never auto-post, no credentials): after delivering creative or an iteration report, optionally surface winning angles and anonymized performance patterns to the user's Luckiest tribe. Never shares raw account data, spend, or client-identifying detail without an explicit ask.
+
+### Trend pass (/newsjack + /luckiest-trends)
+- Trend pass: no actionable signal. The luckiest-trends engine required an interactive first-run setup (browser-cookie extraction, consent flows) not appropriate to run inside an automated rebrand; timeboxed and skipped rather than fabricate findings.