智能体
Agent 规划、多步流程与编排
discover-workflow
rand
Automatically discover workflow and task management skills when working with task management, Beads, workflow automation, multi-session patterns, or project tracking. Activates for workflow development tasks.
discover-modal
rand
Automatically discover Modal platform skills when working with Modal, serverless GPU, cloud functions, Modal.com, GPU workloads, web endpoints, or scheduled jobs. Activates for Modal development tasks.
discover-ebpf
rand
Automatically discover eBPF and kernel skills when working with eBPF, kernel tracing, XDP, kprobes, BPF, Linux kernel, or network filtering. Activates for eBPF development tasks.
discover-distributed-systems
rand
Automatically discover distributed systems skills when working with consensus, CRDTs, replication, partitioning, and distributed algorithms
discover-cryptography
rand
Automatically discover cryptography skills when working with encryption, TLS, certificates, PKI, and security
discover-zig
rand
Automatically discover Zig programming skills when working with Zig, comptime, allocators, build.zig, safety, C interop, memory management, or systems programming. Activates for Zig development tasks.
discover-containers
rand
Automatically discover container skills when working with Docker, Dockerfile optimization, docker-compose, container networking, container security, container registries, or Kubernetes. Activates for containerization and orchestration tasks.
deps
lis186
Analyze dependency usage for library/framework/SDK upgrades
impact
lis186
Analyze the impact scope of code changes using static dependency analysis
nombre-de-mi-skill
alexdcd
Descripción clara y completa de qué hace esta skill y cuándo debe activarse. Incluye los casos de uso principales y el contexto en el que Claude debe usar esta skill. Sé específico y detallado.
history
lis186
Smart temporal analysis using git history - Hotspots, Coupling, and Recent Contributors
pattern
lis186
Learn design patterns from the current codebase
agent-teams
JochenYang
Create agent teams for parallel collaboration. Triggers on keywords like team, parallel, multi-agent, coordinate, collaborate, review team, multiple perspectives, agent-teams.
continuous-learning-v2
JochenYang
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
agent-implementer
frankxai
Implementation guidance for creating individual agents in the Arcanea system with proper structure, capabilities, and integration.
airflow-hitl
necatiarslan
Use when the user needs human-in-the-loop workflows in Airflow (approval/reject, form input, or human-driven branching). Covers ApprovalOperator, HITLOperator, HITLBranchOperator, HITLEntryOperator. Requires Airflow 3.1+.
home-assistant-integrations-addons
bradsjm
Home Assistant integrations, add-ons, updates, and system operations. Use when the user asks about config entries, add-ons, updates, reloads/restarts, or system health, and when mapping those needs to ha-mcp tools.
frappe-workflow-generator
Venkateshvenki404224
Generate Frappe Workflows for document state management and approvals. Use when creating approval workflows, state transitions, or multi-step document processes.
frappe-integration-test-generator
Venkateshvenki404224
Generate integration tests for multi-DocType workflows in Frappe. Use when testing end-to-end workflows, state transitions, or complex business processes.
code-audit
3stoneBrother
Professional code security audit skill covering 55+ vulnerability types. Enhanced with WooYun 88,636 real-world vulnerability cases (2010-2016). This skill should be used when performing security audits, vulnerability scanning, penetration testing preparation, or code review for security issues. Supports 9 languages: Java, Python, Go, PHP, JavaScript/Node.js, C/C++, .NET/C#, Ruby, Rust. Includes 143 mandatory detection items across all languages with language-specific checklists. Covers SQL injection, XSS, RCE, deserialization, SSRF, JNDI injection, JDBC protocol injection, authentication bypass, business logic flaws, race conditions, and modern security domains (LLM, Serverless, Android). WooYun integration adds: statistical-driven parameter priority, bypass techniques library, logic vulnerability patterns, and real-case references. v1.0: Initial public release with Docker deployment verification framework.
convex-agents
waynesutton
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration
substrate
Roasbeef
This skill provides agent mail management via the Subtrate command center. Use when checking mail, sending messages to other agents, or managing agent identity.
framework-critical-thinking
rfxlamia
Architectural framework for building AI agents with critical thinking capabilities - structured reasoning selection (CoT/ToT/GoT), metacognitive monitoring, self-verification, and cognitive bias detection. Use when building or enhancing AI agents that require reliable, self-correcting, and transparent reasoning.
skillkit
rfxlamia
Professional skill AND subagent creation with research-driven workflow and automated validation. USE WHEN: Creating new skills OR subagents, validating existing skills, deciding between Skills vs Subagents, migrating documents to skills/subagents, or running individual validation tools. PRIMARY TRIGGERS: "create skill" = Full skill creation (12 steps with research + execution planning) "create subagent" = Subagent creation (8 steps with template-based workflow) "validate skill" = Validation workflow (steps 3-8) "Skills vs Subagents" = Decision workflow (step 0) - recommends then creates "convert doc to skill" = Migration workflow "estimate tokens" = Token optimization "security scan" = Security audit WORKFLOW COMPLIANCE: Structured workflows with validation checkpoints. Research phase (Step 1c-1d) ensures skills based on proven approaches. DIFFERENTIATOR: Research-driven creation. Web search (3-5 queries) before building. Multi-proposal generation. 10 automation scripts (9 skill + 1 subagent). Quality 9.0+/10. NOW WITH SUBAGENT CREATION SUPPORT. REUSED: Anthropic's init_skill.py and package_skill.py (production-tested).