agent-creation
121majiayu000/claude-skill-registry
Skill Claude CodeCodex
/============================================================================/.
not rated 606
+11 today A SkillSpector: warn 7 tokens
original MIT
606Stars on the repository
200Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
majiayu000/claude-skill-registry
Skill Claude CodeCodex
Procedural guide for creating new agents from templates when project complexity requires delegation.
not rated 606
+11 today A SkillSpector: pass 0 tokens
original MIT
agent-creation
123majiayu000/claude-skill-registry
Skill Claude CodeCodex
Guides agents and users to create standards-compliant agent definitions using templates in markdown frontmatter format, ensuring context gathering, clarity, and proper metadata. Forces agents to ask clarifying questions when context is insufficient. Token-efficient documentation required. All content must be in…
not rated 606
+11 today A SkillSpector: warn 77 tokens
original MIT
agent-creator
124majiayu000/claude-skill-registry
Skill Claude CodeCodex
This skill should be used when the user asks to "create an agent", "write a subagent", "generate agent definition", "add agent to plugin", "write agent frontmatter", "create autonomous agent", "build subagent", needs agent structure guidance, YAML frontmatter configuration, invocation criteria with examples, or wants…
not rated 606
+11 today A SkillSpector: warn 87 tokens
original MIT
agent-creator
125majiayu000/claude-skill-registry
Skill Claude Code
Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use…
not rated 606
+11 today A SkillSpector: pass 84 tokens
original MIT
agent-creator
126majiayu000/claude-skill-registry
Skill Claude CodeCodex
Creates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .claude-flow, combined with evidence-based prompting techniques and Claude Agent SDK implementation. Use this skill when creating production-ready agents for specific domains, workflows, or tasks…
not rated 606
+11 today A SkillSpector: warn 66 tokens
original MIT
agent-creator
127majiayu000/claude-skill-registry
Skill Claude CodeCodex
Creates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .claude-flow, combined with evidence-based prompting techniques and Claude Agent SDK implementation. Use this skill when creating production-ready agents for specific domains, workflows, or tasks…
not rated 606
+11 today A 66 tokens
copy · 100% MIT
agent-creator
128majiayu000/claude-skill-registry
Skill Claude Code
Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use…
not rated 606
+11 today A 84 tokens
copy · 100% MIT
agent-creator
129majiayu000/claude-skill-registry
Skill Claude CodeCodex
Guide for creating effective Claude Code agents. This skill should be used when users want to create a new agent (or update an existing agent) that configures Claude with specialized system prompts, tool restrictions, model selection, and MCP/skill integrations.
not rated 606
+11 today A SkillSpector: pass 53 tokens
original MIT
agent-creator
130majiayu000/claude-skill-registry
Skill Claude CodeCodex needs its repo
Purpose: Guide creation of Claude Code agents following Anthropic official best practices.
not rated 606
+11 today A SkillSpector: pass 19 tokens
original MIT
majiayu000/claude-skill-registry
Skill Claude CodeCodex
Structured cross-review protocol between specialized agents. Ensures scope alignment, priority calibration, and domain-aware feedback. Use when one agent reviews another's work, during handoffs, or when validating cross-cutting concerns.
not rated 606
+11 today A SkillSpector: pass 46 tokens
original MIT
majiayu000/claude-skill-registry
Skill Claude CodeCodex
Structured cross-review protocol between specialized agents. Ensures scope alignment, priority calibration, and domain-aware feedback. Use when one agent reviews another's work, during handoffs, or when validating cross-cutting concerns.
not rated 606
+11 today A 46 tokens
copy · 100% MIT
agent-curator
133majiayu000/claude-skill-registry
Skill Claude CodeCodex
Deep curation of a single agent definition through structured human conversation. Coordinates knowledge research, persona refinement, tooling optimization, and instruction quality improvement. One agent at a time, with due care.
not rated 606
+11 today A SkillSpector: pass 39 tokens
original MIT
majiayu000/claude-skill-registry
Skill Claude CodeCodex
Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). Use for: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool…
not rated 606
+11 today A SkillSpector: pass 92 tokens
original MIT
agent-debugging
135majiayu000/claude-skill-registry
Skill Claude Code
Debug and troubleshoot ElevenLabs conversational AI agents and Twilio calls. Use when diagnosing agent issues, analyzing failed calls, troubleshooting audio problems, investigating conversation breakdowns, reviewing error logs, or optimizing underperforming agents. Includes transcript analysis, error diagnosis, and…
not rated 606
+11 today B SkillSpector: warn 58 tokens
original MIT
agent-debugging
136majiayu000/claude-skill-registry
Skill Claude Code
Debug and troubleshoot ElevenLabs conversational AI agents and Twilio calls. Use when diagnosing agent issues, analyzing failed calls, troubleshooting audio problems, investigating conversation breakdowns, reviewing error logs, or optimizing underperforming agents. Includes transcript analysis, error diagnosis, and…
not rated 606
+11 today B 58 tokens
copy · 100% MIT
agent-deck
137majiayu000/claude-skill-registry
Skill Claude CodeCodex
Terminal session manager for AI coding agents. Use when user mentions "agent-deck", "session", "sub-agent", "MCP attach", or needs to (1) create/start/stop/restart/fork sessions, (2) attach/detach MCPs, (3) manage groups/profiles, (4) get session output, (5) configure agent-deck, (6) troubleshoot issues, or (7) launch…
not rated 606
+11 today A SkillSpector: warn 113 tokens
original MIT
majiayu000/claude-skill-registry
Skill Claude CodeCodex
A template-driven method for defining an AI agent’s role, responsibilities, specialist skills, and collaboration needs. It takes system requirements and available skills as input and produces an agent definition.
not rated 606
+11 today A SkillSpector: pass 23 tokens
original MIT
majiayu000/claude-skill-registry
Skill Claude CodeCodex
Design effective AI agent systems with clear architecture, capability planning, and tool integration. Use when building agent systems, designing agent workflows, planning tool ecosystems, defining agent roles and boundaries, or architecting multi-agent systems. Covers agent patterns, agentic loops, capability design…
not rated 606
+11 today A SkillSpector: pass 62 tokens
original MIT
majiayu000/claude-skill-registry
Skill Claude CodeCodex
Best practices for designing Claude Code agent files (.claude/agents/.md). This skill should be used when writing or reviewing agent markdown files to ensure proper design with focused domains, correct tool access, reusable definitions, and separation of capabilities from lifecycle. Combines Anthropic's official…
not rated 606
+11 today A SkillSpector: warn 73 tokens
original MIT
agent-design
141majiayu000/claude-skill-registry
Skill Claude CodeCodex
Guidelines for designing tools and action spaces for AI agents. Use when building agent harnesses, designing tool interfaces, creating elicitation mechanisms, or optimizing agent-tool interactions. Covers progressive disclosure, tool design patterns, and lessons from Claude Code development.
not rated 606
+11 today A SkillSpector: pass 52 tokens
original MIT
agent-design
142majiayu000/claude-skill-registry
Skill Claude Code
Design AI agents with recommended patterns and architectures.
not rated 606
+11 today A SkillSpector: pass 11 tokens
original MIT
agent-designer
143majiayu000/claude-skill-registry
Skill Claude CodeCodex
Use when the user asks to design multi-agent systems, create agent architectures, define agent communication patterns, or build autonomous agent workflows.
not rated 606
+11 today A 30 tokens
copy · 98% MIT
majiayu000/claude-skill-registry
Skill Claude CodeCodex
Agent skill for dev-backend-api - invoke with $agent-dev-backend-api.
not rated 606
+11 today A 22 tokens
copy · 100% MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: