Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
kotlin-specialist
Expert Kotlin developer specializing in Kotlin 2.0, Kotlin Multiplatform Mobile (KMP), Coroutines, and Ktor for building modern cross-platform applications and backend services.
majiayu000/claude-skill-registry 163
-
setup-events
Configure event-driven architecture with event emitter and base service. Use when adding real-time updates or event system. Triggers on "setup events", "add events", "event system", "SSE", "real-time".
majiayu000/claude-skill-registry 163
-
system-design-draft
Draft a practical system design for a feature. Use when a mid-level developer needs a starting architecture.
majiayu000/claude-skill-registry 163
-
workflow-validator
Quality Gate Teacher for Spec-Kit-Plus workflow. Acts as a strict reviewer that
validates quality (not just existence) of each phase's output before allowing
progression. Generates detailed reports and grades work like a teacher.
Triggers: validate, quality gate, phase check, workflow status, q-status
majiayu000/claude-skill-registry 163
-
growth-roadmap-audit-filter
A framework for auditing growth roadmaps to eliminate low-ROI activities and traps. Use this when planning a new growth cycle, evaluating a head of growth hire, or vetting major UI/UX changes intended to drive conversion.
majiayu000/claude-skill-registry 163
-
curriculum-assess-design
Design assessment blueprints mapping learning objectives to valid assessment types and create detailed rubrics with performance criteria. Use when planning assessments, creating rubrics, or ensuring constructive alignment. Activates on "create assessment blueprint", "design rubric", "assessment alignment", or "backwards design assessment".
majiayu000/claude-skill-registry 163
-
prompt-enhancer
Prompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve structure, add constraints, optimize for specific models, backward-compatible rewrites. Actions: improve, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, prompt optimization, token efficiency, LLM prompt, AI prompt, clarity, structure, system prompt, user prompt, few-shot, chain-of-thought, instruction tuning, prompt compression, token reduction, prompt rewrite, semantic preservation. Use when: improving unclear prompts, reducing token consumption, optimizing LLM outputs, restructuring verbose requests, creating system prompts, enhancing prompt clarity.
majiayu000/claude-skill-registry 163
-
agent-assistant
Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents
Trigger terms: agent stuck, loop detected, session memory, agent learning, condense memory, stuck detection, agent memory, session learnings, extraction
Use when: User reports agent is stuck, looping, or needs memory/learning management
majiayu000/claude-skill-registry 163
-
risk-management-specialist
Senior Risk Management specialist for medical device companies implementing ISO 14971 risk management throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production information analysis. Use for risk management planning, risk assessments, risk control verification, and risk management file maintenance.
majiayu000/claude-skill-registry 163
-
js-tosorted-immutable
Use toSorted() instead of sort() to avoid mutating arrays. Apply when sorting arrays that are React props, state, or otherwise shared/referenced elsewhere.
majiayu000/claude-skill-registry 163
-
qdrant-manager
Manage Qdrant Cloud collections, including vectorization of textbook chapters and metadata tagging for RAG retrieval.
Agent: AIEngineer
majiayu000/claude-skill-registry 163
-
Actor Isolation Fixer
Fix Swift 6 actor isolation errors in Leavn app - deinit accessing @MainActor properties, nonisolated contexts, concurrent access violations
majiayu000/claude-skill-registry 163
-
predict-issues
Proactive problem identification through code analysis and pattern detection
majiayu000/claude-skill-registry 163
-
Red Team Tools and Methodology
This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate subdomains", or needs security researcher techniques and tool configurations from top bug bounty hunters.
majiayu000/claude-skill-registry 163
-
bio-metabolomics-pathway-mapping
Map metabolites to biological pathways using KEGG, Reactome, and MetaboAnalyst. Perform pathway enrichment and topology analysis. Use when interpreting metabolomics results in the context of biochemical pathways.
majiayu000/claude-skill-registry 163
-
apps-script-update
Google Apps Script のコードを更新する。「GAS 更新」「Apps Script 更新」「スクリプト編集」「コードを更新」などで起動。
majiayu000/claude-skill-registry 163
-
cloudflare-agents
Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and multi-agent coordination. Prevents 23 documented errors.
Use when: building WebSocket agents, RAG with Vectorize, MCP servers, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors, WebSocket payload limits.
majiayu000/claude-skill-registry 163
-
ux-design
UX design expert for user research, personas, journey mapping, information architecture, wireframing, prototyping, usability testing, and accessibility. Creates user-centered designs with WCAG 2.1 AA/AAA compliance.
majiayu000/claude-skill-registry 163
-
abaqus-step
Define analysis steps and procedures. Use when user mentions static analysis, dynamic step, frequency analysis, heat transfer step, or asks about analysis type, time increments, or nlgeom.
majiayu000/claude-skill-registry 163
-
valid-basic
A minimal valid skill with all required fields
majiayu000/claude-skill-registry 163
-
pnpm
Node.js package manager with strict dependency resolution. Use when running pnpm specific commands, configuring workspaces, or managing dependencies with catalogs, patches, or overrides.
majiayu000/claude-skill-registry 163
-
specialization-loader
Compose technology-specific agent identity and patterns. Invoke before spawning agents (Developer, SSE, QA, Tech Lead, RE, Investigator) to enhance expertise based on project stack. Returns composed specialization block with token budgeting.
majiayu000/claude-skill-registry 163
-
speckit-plan
Execute implementation planning workflow using the plan template to generate design artifacts
majiayu000/claude-skill-registry 163
-
sla-tracking
Generic SLA (Service Level Agreement) tracking for lead response times. Use when monitoring response performance, ensuring timely follow-ups, or building accountability systems. Framework for project-specific implementations.
majiayu000/claude-skill-registry 163