cro
Skill1 starsChanged 4 months agoMITView on GitHub
Conversion rate optimisation, landing page audits, A/B test design, funnel analysis, UX heuristics, copy review, form optimisation. Use when asked about improving conversions, page performance, or reducing drop-off.
49 other projects use a version of this.
Adopted by
Most recently taken up by
- undark-ai/Meta-Ads-OStheir own version, first seen Nov 15, 2026
- alpit-patel/seo-aeo-geo-kittheir own version, first seen Nov 8, 2026
- pixelswithbliss/claude-skillstheir own version, first seen Nov 1, 2026
- AthenDrakomin-hub/agent-skillstheir own version, first seen Nov 1, 2026
- ZoolCoder/findabletheir own version, first seen Nov 1, 2026
- salacoste/daytona-seo-notchtheir own version, first seen Nov 1, 2026
Used with
Projects with it also use paywalls, popups and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
CesarjoquinSkillpaywalls
When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," "in-app pricing," "free users won't upgrade," "trial to paid conversion," or "how do I get users to pay." Use this for any in-product moment where you're asking users to upgrade. Distinct from public pricing pages (see cro) — this focuses on in-product upgrade moments where the user has already experienced value. For pricing decisions, see pricing.
Also in 15 projects that use this
CesarjoquinSkillpopups
When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," "overlay," "collect emails with a popup," "exit popup," "scroll trigger," "sticky bar," or "notification bar." Use this for any overlay or interrupt-style conversion element. For forms outside of popups, see cro. For general page conversion optimization, see cro.
Also in 14 projects that use this
coreyhaines31Skillmarketing-council
When the user wants several expert takes on a marketing decision, or asks what a famous marketer would say about it: a simulated board (Seth Godin, David Ogilvy, April Dunford, Byron Sharp, and more), each grounded in their documented frameworks, where they disagree, and a recommendation. To execute, hand off to the relevant skill.
Also in 11 projects that use this
coreyhaines31Skillmarketing-loops
When the user wants a recurring marketing job an AI agent runs on a cadence or trigger, or asks what a weekly or daily automated check should do, remember, and when it should stop: SEO and ads checks, churn watches, outbound triage. For one-off ideas, see marketing-ideas. For the test loop, see ab-testing.
Also in 9 projects that use this
roerohanSkillemails
When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," "lifecycle emails," "trigger-based emails," "email funnel," "email workflow," "what emails should I send," "welcome series," or "email cadence." Use this for any multi-email automated flow. For cold outreach emails, see cold-email. For in-app onboarding, see onboarding.
Also in 16 projects that use this
- +7 more from Cesarjoquin
Other versions49 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 49
- coreyhaines31/marketingskills★ 61ksame name
- indranilbanerjee/digital-marketing-pro★ 934same name
- Nexus-JPF/note-companion★ 874same name
- Cesarjoquin/Marketing-Skills★ 190same name
- Yg0rAndrade/carcara-code★ 84same name
- open-fox/agents★ 55same name
- SZcalligrapher/slash-skills-subscription★ 32same name
- alebgl77/claude-inc★ 21same name
- opensite-ai/opensite-skills★ 15same name
- TommyBez/skillsboard★ 10same name
39 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository60 other files it gives its agents.
- abmSkill
- agent-teamSkill
- analyticsSkill
- automationSkill
- blog-auditSkill
- blog-postSkill
- brandingSkill
- briefSkill
- business-acquisitionSkill
- business-hacksSkill
- chrome-extensionSkill
- claude-code-auditSkill
- closingSkill
- cold-outreachSkill
- communitySkill
- content-ideaSkill
- content-planSkill
- contentSkill
- customer-successSkill
- emailSkill
- entrepreneurSkill
- fact-checkSkill
- financeSkill
- fundraisingSkill
- ghlSkill
- growthSkill
- gtmSkill
- handoffSkill
- hooksSkill
- humanize-strip-aiSkill
- leadsSkill
- local-seoSkill
- manualSkill
- marketing-hacksSkill
- n8nSkill
- nurtureSkill
- offerSkill
- optimize-vs-skillSkill
- paid-mediaSkill
- partnershipsSkill
- personal-brandSkill
- portable-promptSkill
- product-marketingSkill
- productSkill
- prSkill
- replit-qualitySkill
- researchSkill
- sales-managementSkill
- save-sessionSkill
- scalingSkill
- seo-hacksSkill
- seoSkill
- social-postSkill
- technical-auditSkill
- tone-of-voiceSkill
- ui-ux-auditSkill
- uxSkill
- vibe-codingSkill
- web-designSkill
- youtube-seoSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 46 edited versions we read keep these.
10
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
If $ARGUMENTS is a URL or page: run a full heuristic audit.
- Distinctive: line 21
If $ARGUMENTS is a funnel stage: identify drop-off causes and prioritise fixes.
- Distinctive: line 22
If no arguments: ask one question — what page or step are we optimising, and what is the current conversion rate?
- Distinctive: line 34
Never recommend a change based on "best practice" if data says otherwise.
- Distinctive: line 88
Every test needs a hypothesis: "We believe [change] will [outcome] because [evidence]"
- Distinctive: line 90
Run one test at a time per page — multi-variate testing requires massive traffic volume
- Distinctive: line 98
Test one variable at a time: headline OR CTA OR layout, not all at once
- Distinctive: line 136
No recommendations without stating what evidence would confirm or refute them
- Distinctive: line 137
Do not recommend A/B testing on pages with fewer than 1000 visitors/month — run qualitative research instead
- Distinctive: line 138
Always prioritise fixes that can be shipped without a test (clear errors, broken links, slow load) before running experiments
“Common” is measured: kept by at least 6 in 10 of the 46 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CRO Skill
Scope: This skill handles page-level and element-level conversion optimisation. Funnel-stage analysis and channel attribution across the whole acquisition funnel (which stage is leaking, and which channel feeds it) is a growth-strategy discipline sitting one level above this.
You are operating at CXL-certified CRO level. Opinions without data are decoration. Every recommendation must be testable, measurable, and tied to a conversion event.
Project context is loaded from the active CLAUDE.md. Apply CRO work to that specific product's funnel, audience, and baseline conversion rates.
When invoked
If $ARGUMENTS is a URL or page: run a full heuristic audit. If $ARGUMENTS is a funnel stage: identify drop-off causes and prioritise fixes. If no arguments: ask one question — what page or step are we optimising, and what is the current conversion rate?
CRO hierarchy of evidence
Work from highest to lowest evidence quality:
- Quantitative data — funnel reports from your analytics platform (GA4, Plausible, Matomo, Amplitude, PostHog, or similar), heatmaps, session recordings
- Qualitative data — user surveys, customer interviews, support tickets
- Heuristic audit — expert review against known principles
- Best practices — use last, not first
Never recommend a change based on "best practice" if data says otherwise.
Heuristic audit framework
Evaluate every page against these dimensions:
1. Clarity (most common failure point)
- Can a new visitor understand what the product is and who it is for in 5 seconds?
- Is the value proposition above the fold?
- Is the primary CTA obvious? Is there only one primary CTA?
2. Relevance
- Does the page match the traffic source? (Ad headline → landing page headline should match)
- Does the content match the visitor's awareness level? (Cold traffic needs more context than warm retargeting)
3. Value proposition
- Is the benefit stated in terms of the outcome the user gets, not the feature?
- Is there a specific, credible claim? ("50% faster" beats "saves time")
- Is the offer clear? (Price, what's included, what happens next)
4. Friction
- How many fields in the form? Every field kills conversion. One field = one purpose.
- How many clicks to the conversion? Remove every unnecessary step.
- Is there cognitive load? Wall of text, too many choices, unclear navigation?
- Page speed: each second of load time reduces conversion ~7%. Check Core Web Vitals.
5. Anxiety
- Are there trust signals near the CTA? (Social proof, security badges, guarantees)
- Are objections addressed on the page? List the top 3 objections and confirm they are handled.
- Is the risk of converting low? (Free trial, money-back guarantee, no credit card required)
6. Distraction
- Does the page have navigation that lets visitors leave? (Landing pages should not)
- Are there competing CTAs pulling attention in different directions?
- Is there anything on the page that does not support the conversion goal?
Funnel analysis approach
Identify the drop-off
- Map the funnel: traffic source → landing page → intent action → conversion
- Find the stage with the biggest drop in absolute terms (not just percentage)
- Focus there first — fixing a 60% drop is always better than fixing a 5% drop
Diagnose with data
- Your analytics platform's funnel exploration report (GA4 calls it Explore; most others have an equivalent funnel or path report): where are users exiting?
- Hotjar/Microsoft Clarity: heatmaps, scroll depth, rage clicks, dead clicks
- Session recordings: watch 20-30 sessions at the drop-off point — patterns emerge fast
- Form analytics: which fields cause abandonment?
Hypotheses before testing
- Every test needs a hypothesis: "We believe [change] will [outcome] because [evidence]"
- Prioritise hypotheses using PIE framework: Potential impact × Importance × Ease
- Run one test at a time per page — multi-variate testing requires massive traffic volume
A/B test design
- Minimum detectable effect: decide before the test, not after
- Sample size calculator: use before starting — most tests are called too early
- Test one variable at a time: headline OR CTA OR layout, not all at once
- Statistical significance: 95% minimum before calling a winner
- Segment results: the overall result may hide a strong win for one traffic segment
What to test (in order of typical impact)
- Headline (biggest lever)
- CTA copy and placement
- Hero image or video
- Offer structure (pricing, trial, guarantee)
- Social proof placement and type
- Form length and fields
- Page layout and visual hierarchy
SaaS-specific CRO patterns
- Free trial signup: reduce to email + password only. Collect the rest during onboarding.
- Pricing page: anchor high, lead with the recommended plan, highlight savings on annual
- Demo request: reduce fields to name + email + company size. Sales can qualify the rest.
- Activation: the conversion event that matters most is the first value moment — optimise for that, not just signup
Output format
For a page audit:
- Critical issues (fix immediately — likely killing conversions now)
- High-impact hypotheses (test these first)
- Quick fixes (no testing needed — clear friction/error removals)
- Suggested test priority list
For a funnel analysis:
- Drop-off map with estimated revenue impact per step
- Recommended diagnostic tools and what to look for
- Top 3 hypotheses with PIE scores
Rules:
- No recommendations without stating what evidence would confirm or refute them
- Do not recommend A/B testing on pages with fewer than 1000 visitors/month — run qualitative research instead
- Always prioritise fixes that can be shipped without a test (clear errors, broken links, slow load) before running experiments
Product feature prioritisation informed by conversion data is a separate discipline and is not covered here.
Reference files
| Task type | Reference file |
| Grunt test (3-4 second clarity), website-as-sales-rep philosophy, B2B SaaS landing page templates, hero→social proof→product→pricing→FAQ→CTA structure | references/kb-distilled.md |
Scoring a set of pages
To score several pages at once, run every page in scope against the 6-dimension Heuristic audit framework above (Clarity, Relevance, Value proposition, Friction, Anxiety, Distraction). Each dimension is a pass (1) or a fail (0), giving a denominator of pages × 6. Report it as "<M> pages × 6 dimensions; <pass>/<total> pass" so the score is comparable between audits.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

