Claude Skills by vibeeval

Lossless session context compression for token efficiency. Extracts entities, decisions, and state into compact format before context window fills. 10-30x reduction in context size while preserving all actionable information.

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.

Autonomous skill lifecycle manager. Reviews skill-compounder drafts, promotes high-confidence patterns, merges duplicates, archives low-quality drafts. Zero manual review required - runs on every session start.

Self-evolving skill system. Skills are scored after execution (0-100) on 5 dimensions. Score 90+ over 5 runs = crystallized (locked). Score below 30 = auto-repair attempted. Skills improve themselves through usage feedback.

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.

SOC2 Type II compliance - Trust Service Criteria, access controls, audit logging, change management, incident response, evidence collection

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

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.

Typosquatting detection, install script analysis, dependency confusion prevention, and phantom dependency detection for npm/pip.

Multi-agent coordination, critical path method, dependency DAG, and agent allocation optimization

Tum ekibi ayni anda devreye sok. Agent'lar paralel calisir, birbirine soru sorar, birlikte gelistirir. Kullanim: /swarm <gorev>

SwiftUI view composition, @Observable patterns, async/await concurrency, TCA architecture, and Combine reactive streams.

Show how vibecosystem works - agents, skills, hooks, and self-learning pipeline.

TDD workflow for migrations - orchestrate agents, zero main context growth

ThoughtWorks Radar model, technology evaluation framework, ADR format, and stack compatibility analysis

Module composition, state management, workspace strategy, provider versioning, and infrastructure-as-code best practices.

Test pyramid decision matrix, coverage targets, when to write which test type, mock vs real dependency decisions, and test ROI analysis.

Run full 5-layer analysis (AST, call graph, CFG, DFG, slice) on a specific function for deep debugging or understanding.

Get a token-efficient overview of any project using file tree, code structure, and call graph analysis.

Map code questions to the optimal tldr command by detecting intent and routing to the right analysis layer.

Show full session token usage, costs, TLDR savings, and hook activity

Friendly onboarding tour of Claude Code capabilities for users asking what it can do.

OpenTelemetry setup, span context propagation, sampling strategies, Jaeger queries

50+ named UX rules with numeric thresholds, 30+ UI styles catalog, industry anti-patterns, pre-delivery checklist

Codebase'i derinlemesine anla. Onboarding, architecture discovery, dependency mapping.

User story generation - INVEST criteria, acceptance criteria (BDD/Given-When-Then), story mapping, epic decomposition, edge case stories, NFR stories

Validation agent that validates plan tech choices against current best practices

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 pattern exists elsewhere.

Comprehensive verification system covering build, types, lint, tests, security, and diff review before a PR.

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 reference or verifying visual correctness.

Connection management, room patterns, reconnection strategies, message buffering, and binary protocol design.

Goal-based workflow orchestration - routes tasks to specialist agents based on user goals

Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)

Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available