Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
IDOR Vulnerability Testing
This skill should be used when the user asks to "test for insecure direct object references," "find IDOR vulnerabilities," "exploit broken access control," "enumerate user IDs or object references," or "bypass authorization to access other users' data." It provides comprehensive guidance for detecting, exploiting, and remediating IDOR vulnerabilities in web applications.
majiayu000/claude-skill-registry 163
-
generate-api-client-tassadar2499-novatune-2
Generate TypeScript API client from OpenAPI spec using Orval for NovaTune frontend (project)
majiayu000/claude-skill-registry 163
-
ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
majiayu000/claude-skill-registry 163
-
mobile-security-coder
Expert in secure mobile coding practices specializing in input validation, WebView security, and mobile-specific security patterns. Use PROACTIVELY for mobile security implementations or mobile security code reviews.
majiayu000/claude-skill-registry 163
-
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
majiayu000/claude-skill-registry 163
-
Swarm Orchestration
Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.
majiayu000/claude-skill-registry 163
-
ln-632-test-e2e-priority-auditor
E2E Critical Coverage audit worker (L3). Validates E2E coverage for critical paths (Money 20+, Security 20+, Data 15+). Pure risk-based - no pyramid percentages.
majiayu000/claude-skill-registry 163
-
customs-trade-compliance
Codified expertise for customs documentation, tariff classification, duty optimisation, restricted party screening, and regulatory compliance across multiple jurisdictions.
majiayu000/claude-skill-registry 163
-
hypershift:preflight
Run pre-flight checks for HyperShift CI. Verifies tools, AWS auth, OpenShift permissions, and configuration.
majiayu000/claude-skill-registry 163
-
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
majiayu000/claude-skill-registry 163
-
ReasoningBank with AgentDB
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
majiayu000/claude-skill-registry 163
-
kol-engager-icp
Find ICP-fit leads from KOL audiences on LinkedIn. Given a list of KOLs, scrapes their most relevant high-engagement post from the last 30 days, extracts engagers (reactors + commenters), pre-filters by position, enriches top profiles, and ICP-classifies. Cost-controlled: 1 post per KOL. Use when someone wants to "find leads from KOL audiences" or "scrape engagers from influencer posts" or after running kol-discovery.
majiayu000/claude-skill-registry 163
-
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
majiayu000/claude-skill-registry 163
-
tech-debt-check
Detect technical debt patterns in code including duplication, complexity, and maintainability issues. Use at phase checkpoints or on-demand to assess code quality.
majiayu000/claude-skill-registry 163
-
ln-822-nuget-upgrader
Upgrades .NET NuGet packages with breaking change handling. Use when updating .NET dependencies.
majiayu000/claude-skill-registry 163
-
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
majiayu000/claude-skill-registry 163
-
migrate
Import soul data from SQLite or shared chitta files
majiayu000/claude-skill-registry 163
-
call-sites
Find all locations where functions are called in a binary. Use when analyzing callers of a function, checking call relationships, or identifying which functions invoke a specific API.
majiayu000/claude-skill-registry 163
-
webapicontrib
USE FOR: Extending ASP.NET Core Web API with custom formatters, content negotiation, and media type handling using WebApiContrib.Core. Use when you need to serve or consume CSV, BSON, MessagePack, Protocol Buffers, or other non-JSON formats alongside JSON in the same API.
DO NOT USE FOR: Building entire APIs from scratch (use ASP.NET Core minimal APIs or controllers), GraphQL endpoints (use Hot Chocolate), or gRPC services (use ASP.NET Core gRPC).
majiayu000/claude-skill-registry 163
-
telegram-bot
Telegram bot development - chatbots, notifications, AI assistants, and group automation
majiayu000/claude-skill-registry 163
-
pdf
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
majiayu000/claude-skill-registry 163
-
hive-mind-advanced
Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory
majiayu000/claude-skill-registry 163
-
pdf-congdon1207-agents-md
majiayu000/claude-skill-registry 163
-
idea
Use when exploring a new idea before writing formal specifications. Guides users through iterative discovery, research, and critical analysis to crystallize vague ideas into validated requirement drafts. Includes anti-pseudo-requirement checks, competitive research, demand evidence gathering, and "What if we don't build this?" analysis. Supports pause/resume across sessions, stores ideas in the project's ideas/ directory, and graduates validated ideas into the spec-forge auto chain (idea → decompose → tech-design + feature specs).
majiayu000/claude-skill-registry 163