Menu
Skills neste repositório
O SkillsMP coletou 330 skills de vibeeval/vibecosystem. Abra uma skill para revisar a origem e os detalhes.
vibeeval/vibecosystemMostrando 40 de 330 skills coletadas.
RevenueCat SDK entegrasyon pattern'leri. iOS (Swift), Android (Kotlin), React Native ve Flutter icin setup, offerings, entitlement checking, webhook integration, StoreKit 2 migration ve sandbox testing.
Idioma do texto original: Indeterminado
Abonelik fiyatlama stratejileri. 3-tier framework, price anchoring, charm pricing, regional pricing (18 ulke), introductory offers, win-back campaigns, churn prevention ve A/B testing methodology.
Idioma do texto original: inglês
Use this skill when context compression is imminent, when resuming a session, or when preserving critical decisions across long tasks. Provides a durable notepad that survives compaction and lets any agent pick up exactly where the previous context left off.
Idioma do texto original: inglês
Dynamic model selection based on task complexity scoring. Replaces static model mappings with a weighted signal system that picks Opus, Sonnet, or Haiku-class speed per task. Works with agent-assignment-matrix.md.
Idioma do texto original: inglês
Security-focused differential code review with blast radius analysis, risk-adaptive depth (DEEP/FOCUSED/SURGICAL), git history correlation, and structured finding format. Adapted from Trail of Bits. Use when reviewing PRs, commits, or code changes for…
Idioma do texto original: inglês
Systematic false positive verification for security findings. Provides structured methodology to confirm or dismiss scanner results, manual audit findings, and automated alerts. Adapted from Trail of Bits. Use when triaging security scan results or verifying…
Idioma do texto original: inglês
Detect fail-open configurations, hardcoded secrets, weak authentication defaults, permissive CORS, disabled security features, and other insecure-by-default patterns. Adapted from Trail of Bits. Use during security review or when auditing configuration and…
Idioma do texto original: inglês
Property-based testing (PBT) patterns with fast-check (JS/TS), Hypothesis (Python), and gopter (Go). Generate random inputs, define invariants, shrink failures to minimal cases. Adapted from Trail of Bits. Use when testing pure functions, parsers,…
Idioma do texto original: inglês
Identify dangerous API footguns, surprising default behaviors, and sharp edges in codebases and dependencies. Adapted from Trail of Bits. Use during code review to catch APIs that are easy to misuse, configurations that surprise, and abstractions that leak.
Idioma do texto original: inglês
Typosquatting detection, install script analysis, dependency confusion prevention, and phantom dependency detection for npm/pip.
Idioma do texto original: inglês
Find similar vulnerabilities across a codebase after discovering one instance. Uses pattern matching, AST search, Semgrep/CodeQL queries, and manual tracing to propagate findings. Adapted from Trail of Bits. Use after finding a bug to check if the same…
Idioma do texto original: inglês
Framework for measuring and tracking agent response quality over time. Detects regressions before they reach production. Use when evaluating agent changes, auditing quality, or establishing performance baselines.
Idioma do texto original: inglês
Post-implementation cleanup that removes AI-generated bloat while preserving functionality. Runs pass-by-pass with test verification after each pass. Activate after kraken/spark complete a feature, or when a codebase needs hygiene work.
Idioma do texto original: inglês
Mathematically rigorous Socratic interview system that drives ambiguity below 20% before any code is written. One question per message, weighted ambiguity scoring, brownfield-aware, outputs a complete PRD. Replaces discovery-interview with a stricter protocol.
Idioma do texto original: inglês
Use this skill when making any factual claim about the codebase — existence, absence, or behavior. Converts the claim-verification rule into a systematic action protocol that prevents false assertions from grep-only results.
Idioma do texto original: inglês
Screenshot comparison QA for frontend development. Takes a screenshot of the current implementation, scores it across multiple visual dimensions, and returns a structured PASS/REVISE/FAIL verdict with concrete fixes. Use when implementing UI from a design…
Idioma do texto original: inglês
Reverse-engineer and clone a website in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild,…
Idioma do texto original: inglês
Full-stack frontend development combining premium UI design, cinematic animations, AI-generated media assets, persuasive copywriting, and visual art. Builds complete, visually striking web pages with real media, advanced motion, and compelling copy. Use when:…
Idioma do texto original: inglês
AI browser automation - navigate, interact, extract, verify via browser-use MCP
Idioma do texto original: inglês
Scan .claude/ directory for security misconfigurations, exposed secrets, unsafe permissions
Idioma do texto original: inglês
Adaptive content summarization - auto-detect content type and produce relevant summary
Idioma do texto original: inglês
Competitive intelligence - extract features, pricing, tech stack from competitor sites
Idioma do texto original: inglês
Multi-page deep crawling - documentation sites, wikis, knowledge bases
Idioma do texto original: inglês
Web change monitoring - track changes on pages, detect updates, changelog diffs
Idioma do texto original: inglês
Single page smart extraction - articles, docs, blog posts to clean markdown
Idioma do texto original: inglês
Structured data extraction - tables, pricing, products, API endpoints with schema
Idioma do texto original: inglês
API design, versioning, testing, schema validation, and contract testing patterns for REST and GraphQL APIs.
Idioma do texto original: inglês
Email delivery infrastructure - DNS authentication (SPF/DKIM/DMARC), subdomain isolation, provider abstraction, template systems, bounce handling, warmup strategy, and deliverability monitoring.
Idioma do texto original: inglês
KVKK and GDPR compliance patterns - consent management, right to erasure, breach notification, audit logging, cookie consent, and data classification.
Idioma do texto original: inglês
SaaS analytics event taxonomy, metric formulas (MRR, churn, LTV), provider-agnostic tracking, funnel analysis, cohort setup, and privacy-respecting instrumentation.
Idioma do texto original: inglês
SaaS authentication and authorization patterns including JWT vs session strategies, multi-tenant isolation, RBAC, API key management, passwordless flows, MFA, and secure session handling.
Idioma do texto original: inglês
Pre-launch verification across infrastructure, security, legal, payment, email, analytics, and performance. Day-1 monitoring, rollback plan, incident response skeleton, and post-launch week-1 checklist.
Idioma do texto original: inglês
Payment provider abstraction, webhook security, subscription lifecycle, dunning flows, pricing models, invoicing, tax handling, and refund patterns for SaaS applications.
Idioma do texto original: inglês
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
Idioma do texto original: inglês
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
Idioma do texto original: inglês
Search Mathlib for lemmas by type signature pattern using Loogle.
Idioma do texto original: inglês
Example template for project-specific skill files covering architecture, patterns, testing, and deployment.
Idioma do texto original: inglês
Query the memory system for relevant learnings from past sessions using semantic search.
Idioma do texto original: inglês
Store a learning, pattern, or decision in the memory system for future recall.
Idioma do texto original: inglês
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Idioma do texto original: inglês