codymaster 7.0.1 → 7.0.3

package/skills/cm-continuity/references/cm-uri-scheme.md

@@ -0,0 +1,23 @@
+# `cm://` URI Scheme
+
+> Use when referencing memory or skill resources symbolically.
+
+## Common URIs
+```text
+cm://memory/working
+cm://memory/learnings
+cm://memory/learnings/{id}
+cm://memory/decisions
+cm://skills/{name}
+cm://skills/{name}/L0
+cm://resources/skeleton
+cm://pipeline/current
+```
+
+## Purpose
+- depth-aware resource loading
+- cheap L0/L1 reads before full content
+- stable references for memory and skill resources
+
+## Rule
+Use symbolic `cm://` access when you need portable, depth-aware references rather than hardcoded file reads.

package/skills/cm-continuity/references/continuity-template.md

@@ -0,0 +1,48 @@
+# Continuity Template
+
+> Use when creating or repairing `.cm/CONTINUITY.md`.
+
+```markdown
+# CodyMaster Working Memory
+Last Updated: [ISO timestamp]
+Current Phase: [planning|executing|testing|deploying|reviewing]
+Current Iteration: [number]
+Project: [project name]
+
+## Active Goal
+[1-2 sentences]
+
+## Current Task
+- ID: [task-id]
+- Title: [task title]
+- Status: [in-progress|blocked|reviewing]
+- Skill: [cm-skill]
+- Started: [timestamp]
+
+## Just Completed
+- [recent accomplishment]
+
+## Next Actions (Priority Order)
+1. [next step]
+2. [follow-up]
+
+## Active Blockers
+- [current blockers]
+
+## Key Decisions This Session
+- [decision]: [rationale] — [timestamp]
+
+## Mistakes & Learnings
+- **What Failed:** [...]
+- **Why It Failed:** [...]
+- **How to Prevent:** [...]
+
+## Working Context
+[critical current context, no secrets]
+
+## Files Currently Being Modified
+- [path]: [why]
+```
+
+## Rule
+Keep it short, current, and operational. Do not turn it into a long diary.

package/skills/cm-continuity/references/mcp-context-server.md

@@ -0,0 +1,27 @@
+# MCP Context Server
+
+> Use when configuring or consuming the continuity MCP bridge.
+
+## Start
+```bash
+cm mcp-serve --project /path/to/project
+cm mcp-serve --print-config
+```
+
+## Key Tool Groups
+| Tool | Purpose |
+|---|---|
+| `cm_query` / `cm_search` | search learnings and decisions |
+| `cm_resolve` | resolve `cm://` resources |
+| `cm_bus_read` / `cm_bus_write` | interact with live context bus |
+| `cm_budget_check` | token pre-flight checks |
+| `cm_memory_decay` / `cm_index_refresh` | memory hygiene and index refresh |
+| `cm_plan` / `cm_review` / `cm_qa` / `cm_deploy` | workflow bridge helpers |
+
+## Use When
+- another client needs continuity-aware context
+- you are wiring memory access into tools or agents
+- you need memory operations without reading raw files directly
+
+## Rule
+Treat MCP as the structured access path; do not duplicate its behavior ad hoc when it already covers the need.

package/skills/cm-continuity/references/memory-architecture.md

@@ -0,0 +1,26 @@
+# Memory Architecture
+
+> Use when the task touches memory design, load strategy, or cross-session recall internals.
+
+## Tiers
+| Tier | Purpose |
+|---|---|
+| 1 | sensory / in-call transient thinking |
+| 2 | working memory: current session and near-term state |
+| 3 | long-term memory: learnings, decisions, outputs, indexes |
+| 4 | external semantic memory for very large projects |
+| 5 | structural code memory via `cm-codeintell` |
+
+## Core Components
+- `CONTINUITY.md` for active session scratchpad
+- context bus for live chain state
+- `context.db` or compat storage for reinforced learnings and decisions
+- L0 indexes for cheap memory loads
+
+## Design Intent
+- cheap default context load
+- stronger memory only when reinforced or queried
+- structural and semantic memory separated from active session state
+
+## Rule
+Do not load advanced memory tiers by default when working memory is enough.

package/skills/cm-continuity/references/memory-audit.md

@@ -0,0 +1,18 @@
+# Memory Audit
+
+> Use when recall quality, stale memory, or conflicting learnings become a problem.
+
+## Audit Steps
+1. Decay check for stale learnings
+2. Conflict detection across overlapping memories
+3. Integrity scan for contradictory or harmful recall
+4. Scope-filtered reading
+5. Reinforcement without duplication
+
+## Use When
+- the same mistake keeps repeating
+- a learning appears stale or over-generalized
+- memory seems to be steering work incorrectly
+
+## Rule
+Audit memory before adding more memory when the existing memory may be the real problem.

package/skills/cm-continuity/references/session-protocol.md

@@ -0,0 +1,31 @@
+# Session Protocol
+
+> Default reference for normal continuity usage.
+
+## Start of Session
+1. Read `.cm/CONTINUITY.md`.
+2. Review active goal, next actions, and blockers.
+3. Review recent mistakes and learnings to avoid repeated errors.
+
+## During Work
+Use a pre-action attention check:
+- re-read the active goal
+- ask whether the next action serves that goal
+- detect drift and return to the main objective
+
+## End of Session
+1. Update recent accomplishments.
+2. Update next actions.
+3. Record new mistakes and learnings.
+4. Record key decisions.
+5. Update files being modified and current phase.
+
+## On Error
+- capture the error
+- analyze root cause
+- record a prevention-oriented learning
+- retry with the corrected approach
+- escalate after repeated failure patterns
+
+## Rule
+Continuity is only valuable if it is current and action-oriented.

package/skills/cm-continuity/references/storage-formats.md

@@ -0,0 +1,20 @@
+# Storage Formats
+
+> Use only when editing persistence, migration, or compat logic.
+
+## Primary Stores
+- `.cm/CONTINUITY.md`
+- `.cm/context-bus.json`
+- `.cm/context.db`
+- fallback / compat JSON files for learnings and decisions
+- L0 indexes such as `.cm/learnings-index.md` and `.cm/skeleton-index.md`
+
+## Stored Concepts
+- learnings
+- decisions
+- skill outputs
+- cached indexes
+- continuity scratch state
+
+## Rule
+Default to supported runtime storage behavior. Treat older formats as compatibility, not the primary model.

package/skills/cm-cro-methodology/SKILL.md

@@ -0,0 +1,290 @@
+---
+name: cm-cro-methodology
+description: 'Audit websites and landing pages for conversion issues and design evidence-based A/B tests. Use when the user mentions "landing page isn''t converting", "conversion rate", "A/B test", "why visitors leave", or "objection handling". Covers funnel mapping, persuasion assets, and objection/counter-objection frameworks. For overall marketing strategy, see one-page-marketing. For usability issues, see ux-heuristics.'
+license: MIT
+metadata:
+  author: wondelai
+  version: "1.1.1"
+---
+
+# CRO Methodology
+
+Scientific, customer-centric approach to conversion rate optimization based on the CRE Methodology(TM). Extraordinary improvements come from understanding WHY visitors don't convert, not from copying competitors or applying generic tips.
+
+## Core Principle
+
+**Don't guess -- discover.** The methodology rejects "best practices" and "magic buttons" in favor of evidence-based optimization. Most websites underperform not because of bad design, but because no one has systematically researched why visitors leave without converting.
+
+**The foundation:** Every visitor who doesn't convert has a reason. Your job is to discover those reasons through research, then systematically eliminate them with evidence and proof. This customer-centric approach consistently outperforms intuition, competitor copying, and "expert" opinions.
+
+## Scoring
+
+**Goal: 10/10.** When reviewing or creating landing pages, funnels, or conversion flows, rate them 0-10 based on adherence to the principles below. A 10/10 means full alignment with all guidelines; lower scores indicate gaps to address. Always provide the current score and specific improvements needed to reach 10/10.
+
+## The CRO Frameworks
+
+### 1. The CRO Process
+
+**Core concept:** A systematic 9-step process for optimizing conversion rates, moving from defining success metrics through research, experimentation, and scaling wins across the business.
+
+**Why it works:** Random optimization efforts fail because they skip the critical research steps. The CRE process forces you to understand visitors before changing anything, ensuring changes are based on evidence rather than opinion.
+
+**Key insights:**
+- Define success metrics aligned with business KPIs before touching any page
+- Map the entire conversion funnel to find "blocked arteries" (high-traffic underperforming paths) and "missing links" (absent funnel stages)
+- Understand visitors in three dimensions: who they are (types and intentions), what blocks them (UX problems), and what stops them (objections)
+- Gather market intelligence from competitors, reviews, and other industries
+- Prioritize ideas using ICE scoring (Impact, Confidence, Ease) before testing
+- Create bold experimental designs based on research, not "meek tweaks"
+- Run experiments with proper statistical rigor (95% confidence minimum, full business cycles)
+- Scale wins across landing pages, ad copy, email sequences, and offline materials
+
+**Product applications:**
+
+| Context | CRO Process Step | Example |
+|---------|-----------------|---------|
+| **Landing page audit** | Steps 1-3: Define goals, map funnel, research visitors | Identify that 70% of traffic bounces because value prop is unclear |
+| **Checkout optimization** | Step 2: Map funnel for blocked arteries | Discover shipping cost shock causes 40% cart abandonment |
+| **New feature launch** | Steps 6-8: Strategize, design, experiment | A/B test two positioning approaches before full rollout |
+| **Email sequence** | Step 9: Scale wins | Apply winning objection-handling copy from landing page to drip emails |
+| **Competitor response** | Step 4: Market intelligence | Transfer proven strategies from adjacent industries |
+
+**Copy patterns:**
+- "What's preventing you from [action] today?" (exit survey question to discover objections)
+- "Here's what [X] customers found..." (counter-objection with social proof)
+- Document hypothesis: "If we [change X], then [metric Y] will improve because [reason from research]"
+- Always calculate required sample size BEFORE starting any test
+
+**Ethical boundary:** Never manipulate test results or cherry-pick data. Report all tests, including failures, and wait for genuine statistical significance.
+
+See: [testing-methodology.md](references/testing-methodology.md) for detailed ICE scoring, A/B vs. multivariate guidance, and statistical rigor.
+
+### 2. Customer Research & Objections
+
+**Core concept:** Visitors don't convert for specific, discoverable reasons. Research methods -- exit surveys, chat logs, support tickets, sales calls, reviews -- reveal the "voice of the customer" and their real objections.
+
+**Why it works:** Companies guess why visitors leave, but guesses are almost always wrong. Direct research consistently uncovers objections that teams never anticipated, and the language customers use is more persuasive than any copywriter's invention.
+
+**Key insights:**
+- Primary sources (exit surveys, live chat logs, support tickets, sales call recordings) give you direct visitor language
+- Secondary sources (reviews, social media, competitor analysis) reveal industry-wide objections
+- Objections fall into two categories: explicit ("too expensive") and implicit ("I'm not sure I'll follow through")
+- The "Big 5" universal objections are Trust, Price, Fit, Timing, and Effort
+- Post-purchase surveys ("What almost stopped you from buying?") reveal the objections that matter most
+- Non-converter surveys should ask ONE question for maximum response rate
+- Quantitative research (analytics, heatmaps) shows WHERE problems are; qualitative research (surveys, interviews) shows WHY
+
+**Product applications:**
+
+| Context | Research Method | Example |
+|---------|---------------|---------|
+| **Exit intent** | On-site survey (Hotjar, Qualaroo) | "What's preventing you from signing up today?" |
+| **Post-purchase** | Email survey within 7 days | "What almost stopped you from buying?" |
+| **Objection mining** | Support ticket analysis | Search for "but", "however", "worried about" patterns |
+| **Voice of customer** | Sales call recordings | Capture exact language customers use to describe problems |
+| **Competitive gaps** | Review mining (yours and competitors') | Negative reviews = unaddressed objections |
+
+**Copy patterns:**
+- Use exact customer language in headlines and body copy (more persuasive than polished marketing copy)
+- "What's the one thing we could change to make you [action]?"
+- "How would you describe [product] to a friend?" (reveals positioning in customer terms)
+- Ask open-ended questions for discovery; save multiple choice for validation
+
+**Ethical boundary:** Respect customer privacy in research. Anonymize data, get consent for recordings, and don't survey so aggressively that you degrade the user experience.
+
+See: [RESEARCH.md](references/RESEARCH.md) for tools, survey questions, and data analysis methods.
+
+### 3. Persuasion Assets
+
+**Core concept:** Every company has overlooked proof elements -- testimonials not displayed, awards not mentioned, statistics not highlighted, guarantees not prominent, team credentials hidden. These are "persuasion assets" that must be inventoried, acquired, and displayed.
+
+**Why it works:** Visitors make decisions based on evidence and proof, not claims. A bold claim without proof is just noise. A modest claim with overwhelming proof is irresistible. Most companies sit on goldmines of proof they never use.
+
+**Key insights:**
+- Audit five categories: Credentials & Authority, Social Proof, Risk Reversal, Data & Specificity, Process & Methodology
+- Create a "wish list" for missing assets and actively acquire them (request testimonials, apply for awards, compile statistics)
+- The "proof sandwich" structure: Claim (bold promise) then Proof (evidence) then Reinforcement (secondary proof)
+- Hierarchy of proof from strongest to weakest: specific results with context, named testimonials with photos, case studies, statistics, logos/badges, generic testimonials
+- Place proof at points of friction, not hidden in FAQs
+- Specific numbers beat round numbers ("47,832 customers" beats "About 50,000")
+
+**Product applications:**
+
+| Context | Persuasion Asset | Example |
+|---------|-----------------|---------|
+| **Landing page header** | Logo bar + rating | "Trusted by 10,000+ companies" with 5 recognizable logos |
+| **Pricing page** | Risk reversal | "30-day money-back guarantee, no questions asked" |
+| **Product page** | Specific testimonial | Photo + name + company + "Increased conversion by 47% in 3 weeks" |
+| **Checkout flow** | Trust badges near forms | Security certification, payment logos, guarantee seal |
+| **About page** | Team credentials | Years of experience, certifications, publications, patents |
+
+**Copy patterns:**
+- "Here's how we did it for [Company X]..." (case study proof)
+- "And here's what their CEO says about working with us..." (testimonial reinforcement)
+- "[Specific number] businesses trust us" (not "thousands of customers")
+- Lead with benefits, not features: "Never delete another photo" beats "256GB storage"
+
+**Ethical boundary:** Never fabricate testimonials, inflate statistics, or display fake trust badges. All proof must be genuine and verifiable.
+
+See: [PERSUASION.md](references/PERSUASION.md) for the full persuasion assets checklist and psychological triggers.
+
+### 4. The O/CO Framework
+
+**Core concept:** The Objection/Counter-Objection (O/CO) table is the core CRE technique. Create a two-column table mapping every visitor objection to specific, evidence-backed counter-objections.
+
+**Why it works:** Visitors arrive with objections. If the page doesn't address them, visitors leave. The O/CO framework ensures no objection goes unanswered, and counter-objections are placed exactly where objections naturally arise during the reading flow.
+
+**Key insights:**
+- Don't guess objections -- research them from surveys, chat logs, support tickets, and sales calls
+- Implicit objections (ones visitors won't admit) require "CO Only" approach: address the objection without stating it
+- Place counter-objections at the point of friction (credit card objection near payment form), not buried in FAQ
+- Address primary objections above the fold, secondary objections in the flow
+- Use multiple formats for the same counter-objection: text, video, testimonial, data
+- Canned support responses are goldmines of tested counter-objections
+
+**Product applications:**
+
+| Context | Objection Type | O/CO Example |
+|---------|---------------|-------------|
+| **Trust** | "Why should I believe you?" | Specific testimonials, media logos, awards, money-back guarantee |
+| **Price** | "Is it worth the money?" | ROI calculator, cost comparison vs. alternatives, payment plans |
+| **Fit** | "Will it work for MY situation?" | Case studies from similar customers, segmented landing pages, free trial |
+| **Timing** | "Why should I act now?" | Cost of delay calculation, genuine limited-time offers, seasonal relevance |
+| **Effort** | "How hard will this be?" | "Done for you" framing, "Set up in 5 minutes", step-by-step breakdown |
+
+**Copy patterns:**
+- Bad (stating implicit objection): "Worried you're too lazy to learn a language?"
+- Good (CO Only): "Let the audio do the work for you."
+- "What's preventing you from signing up today?" (survey to discover objections)
+- "What almost stopped you from buying?" (post-purchase survey to validate O/CO table)
+
+**Ethical boundary:** Address real objections with honest counter-objections. Never dismiss legitimate concerns or use deception to overcome valid hesitations.
+
+See: [OBJECTIONS.md](references/OBJECTIONS.md) for the full O/CO framework, research methods, and counter-objection techniques.
+
+### 5. Hypothesis Design
+
+**Core concept:** Every experiment needs a documented hypothesis linking a specific change to an expected outcome with a reason grounded in research. Prioritize using ICE scoring (Impact, Confidence, Ease).
+
+**Why it works:** Without a hypothesis, you're just changing things randomly. The hypothesis forces you to articulate WHY a change should work, which means it must be grounded in customer research. ICE scoring prevents teams from wasting time on low-impact "meek tweaks."
+
+**Key insights:**
+- Hypothesis format: "If we [change X], then [metric Y] will improve because [reason based on research]"
+- Define primary metric (determines winner), secondary metrics (additional monitoring), and guardrail metrics (must not decrease)
+- ICE scores: Impact (1-10: could this double conversion?), Confidence (1-10: is research backing strong?), Ease (1-10: how easy to implement?)
+- Make BOLD changes, not "meek tweaks" -- small changes rarely reach statistical significance and waste resources
+- Before testing, ask: "Could this 10x our results?" If not, reconsider priority
+- Worth testing: complete page redesign, new value proposition, fundamentally different offer
+- Not worth testing: button color, font size, image swap
+
+**Product applications:**
+
+| Context | Hypothesis Example | ICE Score |
+|---------|-------------------|-----------|
+| **Headline rewrite** | "If we use customer language from surveys, conversion will increase because visitors see their own words reflected" | I:8, C:9, E:10 = 9.0 |
+| **Video testimonial** | "If we add video testimonial addressing price objection, signups will increase because visitors need trust proof" | I:7, C:7, E:6 = 6.7 |
+| **Checkout redesign** | "If we simplify checkout to one page, completion will increase because analytics show 40% drop at step 2" | I:9, C:6, E:3 = 6.0 |
+| **Button color** | "If we change button from blue to green, clicks will increase because green means go" | I:2, C:2, E:10 = 4.7 |
+
+**Copy patterns:**
+- "Based on our research, visitors' #1 objection is [X]. This test addresses it by [Y]."
+- Document before: hypothesis, primary metric, sample size, duration, traffic allocation
+- Document after: raw numbers, confidence interval, practical significance, learnings, next steps
+- Every test adds to organizational knowledge regardless of outcome
+
+**Ethical boundary:** Report all test results honestly, including failures. Never cherry-pick data or run tests until you get the result you want.
+
+See: [testing-methodology.md](references/testing-methodology.md) for ICE scoring tables and detailed prioritization.
+
+### 6. A/B Testing Methodology
+
+**Core concept:** Run controlled experiments comparing page versions to determine which performs better, using proper statistical rigor to ensure results are real, not random noise.
+
+**Why it works:** Without controlled experiments, you can't distinguish real improvements from random variation. Proper A/B testing methodology prevents the most common errors: peeking and stopping early, insufficient sample size, ignoring practical significance, and the multiple comparison problem.
+
+**Key insights:**
+- Calculate required sample size BEFORE starting (inputs: baseline rate, minimum detectable effect, 80% power, 95% significance)
+- Run for at least one full business cycle (1-2 weeks) including weekdays AND weekends
+- Never peek at results and stop early -- this inflates false positive rates dramatically
+- 95% confidence minimum (p-value less than 0.05) before calling a winner
+- A statistically significant 0.1% lift isn't worth implementation complexity (practical significance matters)
+- Start with A/B tests; only move to multivariate when you have 100k+ monthly visitors and a proven winning page
+- A failed test that teaches you something is more valuable than a winning test you don't understand
+- Promote winners to new control and iterate
+
+**Product applications:**
+
+| Context | Test Type | Example |
+|---------|----------|---------|
+| **Concept validation** | A/B test (2-4 variants) | Test two fundamentally different page layouts based on different customer insights |
+| **Element optimization** | Multivariate (100k+ visitors) | Test 3 headlines x 3 images x 2 CTAs on proven winning page |
+| **Low traffic** | Bold A/B test | Make dramatic changes detectable with smaller samples (~4,000 visitors for 50% lift) |
+| **High traffic** | Rapid iteration | Run parallel tests on non-overlapping pages, 10-20 tests/month |
+| **Post-test** | Scale wins | Apply winning insights across landing pages, ad copy, email sequences |
+
+**Copy patterns:**
+- "We increased [metric] by [X]% with [Y]% confidence over [Z] weeks"
+- "Test showed no significant difference, teaching us that [insight about customers]"
+- "Control outperformed challenger, suggesting visitors prefer [existing approach] because [reason]"
+- Always document learnings: Test, Hypothesis, Result, Learning, Applicable to
+
+**Ethical boundary:** Never manipulate statistical methods to manufacture significance. Report confidence intervals honestly and acknowledge when results are inconclusive.
+
+See: [testing-methodology.md](references/testing-methodology.md) for statistical significance, sample size calculations, and platform comparison.
+
+## Common Mistakes
+
+| Mistake | Why It Fails | Fix |
+|---------|-------------|------|
+| **Copying competitors blindly** | You don't know if their approach works for them, let alone for you | Research YOUR visitors' objections and build YOUR evidence |
+| **Testing button colors before understanding objections** | Addresses surface symptoms, not root causes; tiny effects waste sample size | Do customer research first, then test big changes based on findings |
+| **Assuming you know why visitors leave** | Teams are almost always wrong about visitor motivations | Use exit surveys, chat logs, and support analysis to discover real reasons |
+| **Using "best practices" without validation** | What works elsewhere may not work for your audience, product, or context | Treat best practices as hypotheses to test, not rules to follow |
+| **Making decisions based on HiPPO** | Highest Paid Person's Opinion is not data; authority bias kills optimization | Let research and test results determine changes, not seniority |
+| **Optimizing pages without funnel context** | Improving one step may shift problems to another; miss biggest opportunities | Map entire funnel first, identify blocked arteries, prioritize by impact |
+| **Making "meek tweaks" instead of bold changes** | Small changes rarely reach statistical significance; wastes time and traffic | Test changes that could double conversion, not nudge it 2% |
+| **Giving up after one failed test** | The opportunity still exists; you just haven't found the solution yet | Investigate why, go back to research, try a bolder change |
+
+## Quick Diagnostic
+
+Audit any landing page or conversion flow:
+
+| Question | If No | Action |
+|----------|-------|--------|
+| Do we know the ONE action visitors should take on this page? | Page lacks focus, visitors are confused | Define single primary conversion goal and remove competing CTAs |
+| Have we researched why visitors aren't converting (not guessed)? | Optimization is based on assumptions, not evidence | Run exit surveys, analyze chat logs, review support tickets |
+| Do we have an O/CO table mapping objections to counter-objections? | Visitor objections go unanswered on the page | Build O/CO table from research, place counter-objections at friction points |
+| Is the value proposition crystal clear within 5 seconds? | Visitors bounce before understanding the offer | Run 5-second test, rewrite headline using customer language |
+| Are persuasion assets visible (testimonials, awards, guarantees)? | Page makes claims without proof, visitors don't believe | Audit persuasion assets, acquire missing ones, display prominently |
+| Have we mapped the full funnel and identified blocked arteries? | Optimizing wrong page or missing biggest opportunity | Map traffic volume at each stage, compare to benchmarks, prioritize by impact |
+
+## Quick-Start Checklist
+
+When optimizing any page:
+
+1. [ ] What is the ONE action visitors should take?
+2. [ ] Who are the visitors? What stage of buying journey?
+3. [ ] What are their top 3-5 objections? (Don't guess -- research)
+4. [ ] What proof/counter-objections address each?
+5. [ ] Is the value proposition crystal clear in 5 seconds?
+6. [ ] Are there UX blockers? (speed, mobile, forms)
+7. [ ] What persuasion assets are missing or hidden?
+
+## Reference Files
+
+- [OBJECTIONS.md](references/OBJECTIONS.md): O/CO framework, research methods, counter-objection techniques
+- [COPYWRITING.md](references/COPYWRITING.md): Headlines, proof elements, persuasive writing
+- [PERSUASION.md](references/PERSUASION.md): Persuasion assets checklist, psychological triggers
+- [RESEARCH.md](references/RESEARCH.md): Tools, survey questions, data analysis
+- [testing-methodology.md](references/testing-methodology.md): A/B testing, statistical significance, ICE prioritization, multivariate testing
+- [funnel-analysis.md](references/funnel-analysis.md): Blocked arteries, missing links, industry funnels, cross-sell mapping
+
+## Further Reading
+
+This skill is based on the CRE Methodology(TM) developed by Conversion Rate Experts. For the complete methodology, detailed case studies, and advanced techniques, read the original book:
+
+- [*"Making Websites Win: Apply the Customer-Centric Methodology That Has Doubled the Sales of Many Leading Websites"*](https://www.amazon.com/Making-Websites-Win-Customer-Centric-Methodology/dp/1544500513) by Dr. Karl Blanks and Ben Jesson
+
+## About the Author
+
+**Dr. Karl Blanks and Ben Jesson** are the cofounders of Conversion Rate Experts (CRE), the world's leading agency specializing in conversion rate optimization. Their clients have included Google, Apple, Amazon, Facebook, Dropbox, and many other technology leaders. CRE's methodology has been recognized with a Queen's Award for Enterprise (Innovation), the UK's highest business honor. Blanks holds a PhD in user experience and previously managed teams of usability researchers at Hewlett-Packard. Jesson's background is in direct-response marketing and web development. Together they developed the CRE Methodology, which has been applied across hundreds of websites and consistently delivered significant conversion improvements. Their book *Making Websites Win* distills this methodology into a systematic, repeatable process for evidence-based website optimization.

package/skills/cm-cro-methodology/references/COPYWRITING.md

@@ -0,0 +1,178 @@
+# Persuasive Copywriting for CRO
+
+Evidence-based copywriting principles. Write as much as it takes to communicate your entire sales message—but not one word more.
+
+## Headlines
+
+The headline's job: Get visitors to read the next line.
+
+### Headline Formulas That Work
+
+**Problem-agitate-solve**:
+"Tired of [problem]? [Solution] lets you [benefit]."
+
+**Specificity wins**:
+Bad: "Improve your conversion rate"
+Good: "How we increased conversions by 363%"
+
+**News angle**:
+"[X] facts about [topic] you were never told"
+
+**How-to**:
+"How to [achieve result] without [common pain]"
+
+**Question**:
+"What's stopping your website from converting?"
+
+### Headline Testing Priority
+
+1. Value proposition clarity
+2. Specific numbers/results
+3. Audience targeting
+4. Urgency/timeliness
+5. Emotional hook
+
+## Body Copy Principles
+
+### Length
+Write as much as it takes to:
+- Communicate the complete sales message
+- Address all major objections
+- Provide sufficient proof
+
+Long copy works when visitors are:
+- Unfamiliar with product category
+- Making a high-commitment decision
+- Comparing alternatives
+
+Short copy works when:
+- Brand is well-known
+- Product is simple/commoditized
+- Visitors are already convinced
+
+### Structure
+
+**Lead with benefits, not features**
+Feature: "256GB storage"
+Benefit: "Never delete another photo"
+
+**Use specific numbers**
+Weak: "Thousands of customers"
+Strong: "47,832 businesses trust us"
+
+**Write for scanners**
+- Subheadings that tell the story alone
+- Bold key phrases
+- Bullet points for multiple items
+- Short paragraphs (2-4 sentences)
+
+### Voice
+
+**Clarity over cleverness**
+No reader is too sophisticated for simple sentences.
+
+**Active voice**
+Bad: "Your conversion rate will be improved"
+Good: "We'll improve your conversion rate"
+
+**"You" focus**
+Count "you" vs. "we" in your copy. Visitors care about themselves.
+
+**Circle adjectives and adverbs**
+Replace vague modifiers with specific facts:
+Bad: "incredibly fast delivery"
+Good: "delivery in 2 hours or less"
+
+## Proof Elements
+
+### Hierarchy of proof (strongest to weakest)
+
+1. **Specific results with context**
+   "Increased revenue by $2.4M in 6 months"
+
+2. **Named testimonials with photos**
+   Real people, real companies, specific outcomes
+
+3. **Case studies**
+   Problem → Solution → Results format
+
+4. **Statistics and data**
+   Industry benchmarks, research findings
+
+5. **Logos and badges**
+   Client logos, media mentions, certifications
+
+6. **Generic testimonials**
+   Unnamed quotes (weakest form)
+
+### Testimonial Best Practices
+
+**Include specifics**:
+Bad: "Great product!"
+Good: "Increased our conversion rate from 2.1% to 4.7% in 3 weeks"
+
+**Address objections**:
+Choose testimonials that counter specific fears
+
+**Match the audience**:
+B2B visitors want testimonials from similar companies/roles
+
+**Use photos**:
+Real photos > stock photos > no photos
+
+## Calls-to-Action
+
+### CTA Copy
+
+**Benefit-oriented**:
+Bad: "Submit"
+Good: "Get my free report"
+
+**Reduce perceived commitment**:
+"Start free trial" vs. "Sign up"
+"See pricing" vs. "Buy now"
+
+**Match button to promise**:
+If page promises "10 ways to improve X", CTA should be:
+"Show me the 10 ways" not "Learn more"
+
+### CTA Placement
+
+- Above the fold (for aware visitors)
+- After each major section
+- At moment of peak interest
+- Sticky/floating for long pages
+
+### CTA Testing Ideas
+
+1. Benefit vs. action language
+2. Commitment level (free vs. buy)
+3. Urgency elements
+4. Size and color (test AFTER copy)
+5. Number of CTAs per page
+
+## Common Copywriting Mistakes
+
+1. **Features without benefits**
+   Always answer "So what?"
+
+2. **Vague claims**
+   "Best in class" → "Rated #1 by [source]"
+
+3. **Talking about yourself**
+   Reframe everything around the visitor
+
+4. **Burying the lead**
+   Put most important information first
+
+5. **Assuming knowledge**
+   Explain industry jargon
+
+6. **Missing objections**
+   Address hesitations head-on
+
+7. **Weak proof**
+   Generic testimonials, no specifics
+
+8. **Unclear next step**
+   Always make the action obvious