sdlc
claudeTask lifecycle: new-task (BA authoring + contradiction gate + Gherkin), requirements, plan-task, task-review, debug, qa skills + architect, debugger and requirements-analyst subagents.
8 skills · 3 agents
Selling and retention design: conversion-review, paywall-and-pricing, habit-loop, landing-builder and ux-copy skills + conversion-reviewer subagent. Honest by default (no dark patterns), every finding names the event that proves it.
Plugin product-design from marketplace personal in kulykivska/claude-plugins. Commands read from the repo's manifest — yesterday.
conversion-reviewAudit a page, screen, screenshot, artifact or URL against conversion heuristics: value proposition on the first screen, one primary action per screen, proof, sign-up and checkout friction, trust, pricing clarity and mobile. Returns prioritized findings, each with the fix, a severity and the metric o
habit-loopDesign the return loop for a product: trigger, action, variable reward and investment, mapped to the product's real calendar (for a sports product: race weekends, qualifying, results, off weeks). Produces the notification plan with frequency caps and quiet hours, streak rules, and the analytics even
landing-builderWrite the structure and copy for a selling landing page: hero, proof, features as outcomes, pricing, FAQ and a final call to action, with variants per audience and an A/B test plan. Trigger on "write a landing page", "landing for", "homepage copy", "page for teams", "page for bookmakers", "B2B landi
paywall-and-pricingDesign paywalls, Pro gates and pricing pages that sell without annoying: partial or blurred previews instead of hard locks, anchoring and decoy tiers, the annual toggle, trial rules, upgrade moments tied to user success, copy patterns and what to measure. Honest by default, with an explicit list of
ux-copyWrite or fix product microcopy: empty states, errors, loading, success and confirmation messages, buttons and labels that replace jargon with plain words (for example "average error in places" instead of "MAE"), and dates and times in the viewer's local time and a human format. Final text always goe
conversion-reviewerRead-only conversion reviewer for pages, screens, screenshots, artifacts and URLs. Runs the conversion-review heuristics plus the paywall and pricing checks (including the forbidden dark patterns) and returns one ranked list of findings with fix, severity and the event that proves it. Use to review
Task lifecycle: new-task (BA authoring + contradiction gate + Gherkin), requirements, plan-task, task-review, debug, qa skills + architect, debugger and requirements-analyst subagents.
8 skills · 3 agents
content-writer and fact-checker subagents + social-post, linkedin-post-writer, humanizer and remove-ai-marks skills: one idea into platform-native posts for LinkedIn, Threads, X, Instagram; EN/UK, owner's voice, fact-checked, humanized, and stripped of AI provenance marks.
4 skills · 2 agents
Per-stack reviewer subagents: Python/FastAPI, web (Vite/React/TS), SwiftUI, and ML pipeline (LORO gate, FEATURE_COLS sync, leakage).
4 agents
Apple-grade UX and the toy feel: delight-spec (spring, haptic and motion tokens with CSS and SwiftUI snippets), hig-review, and the design-first redesign orchestrator (5-6 directions, design system, screens, then plan) + hig-reviewer subagent.
3 skills · 1 agent
Business growth subagents: aso-optimizer (App Store), growth-analyst (funnel/conversion), outreach-writer (partnership and consulting pitches).
3 agents
Fly.io ops runbooks: deploy (with release_command gotcha), fly-logs, incident triage.
3 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.