Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
monitoring-analytics
Monitor Proxmox infrastructure health and performance. Track node statistics, analyze resource utilization, and identify optimization opportunities across your cluster.
majiayu000/claude-skill-registry 163
-
superdisco-moai-sync
Superdisco MoAI fork management - track customizations, sync upstream updates while preserving your changes
majiayu000/claude-skill-registry 163
-
weeknotes-blog-post-composer
Compose weeknotes blog posts in Jekyll-style Markdown from multiple data sources including Mastodon and Linkding. Use this skill when the user requests to create, draft, or generate weeknotes content for a blog post.
majiayu000/claude-skill-registry 163
-
stakeholder-alignment
Align stakeholders and secure buy-in by producing a Stakeholder Alignment Pack (alignment brief, stakeholder map, exec decision principles, pre-brief plan, alignment meeting plan, decision summary + comms). Use for stakeholder alignment, buy-in, executive alignment, cross-functional alignment. Category: Communication.
majiayu000/claude-skill-registry 163
-
fortify-security
Expert in Gravito security and authentication. Trigger this when setting up Auth, configuring CSP, or implementing security middleware.
majiayu000/claude-skill-registry 163
-
bundle-performance
Monitor JavaScript bundle size and execution performance. Use when tracking bundle size, identifying large chunks, or optimizing load performance.
majiayu000/claude-skill-registry 163
-
research-after-failure
Use after 2 consecutive failed attempts at solving a problem - STOP guessing and research documentation, codebase, and online resources before resuming
majiayu000/claude-skill-registry 163
-
exa-known-pitfalls
Identify and avoid Exa anti-patterns and common integration mistakes.
Use when reviewing Exa code for issues, onboarding new developers,
or auditing existing Exa integrations for best practices violations.
Trigger with phrases like "exa mistakes", "exa anti-patterns",
"exa pitfalls", "exa what not to do", "exa code review".
majiayu000/claude-skill-registry 163
-
model-selection-orchestrator
Select the best local Ollama model for a task and emit tuning presets. Use when choosing between reasoning, creative, fast, vision, synthesis, or pre-AGI modes based on available local models.
majiayu000/claude-skill-registry 163
-
optimizing-rag
Optimize RAG performance with reranking, caching, parallel processing, and production deployment patterns. Use when improving retrieval quality, adding rerankers, deploying to production, implementing caching strategies, or optimizing for scale and latency.
majiayu000/claude-skill-registry 163
-
gandalf-the-prompt
Audits prompts and skills against Claude best practices. Finds clarity issues, structural problems, and enhancement opportunities. Provides fixes and grades.
majiayu000/claude-skill-registry 163
-
drafting
Break through blocks and execute first drafts. Use when the outline is done but the draft isn't happening, when writer's block strikes, when the blank page remains blank, or when progress stalls.
majiayu000/claude-skill-registry 163
-
linkerd-patterns
Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.
majiayu000/claude-skill-registry 163
-
bifurcation-generator
Generate bifurcation diagrams for dynamical systems. Use when visualizing parameter-dependent behavior transitions.
majiayu000/claude-skill-registry 163
-
hosted-agents
This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes, self-spawning agents, or remote coding environments.
majiayu000/claude-skill-registry 163
-
phase-validation
Phase 0-6 검증 자동화. 각 Phase별 필수 조건 확인.
majiayu000/claude-skill-registry 163
-
update-doc
Use when user says 'update docs', 'sync documentation', 'refresh docs', or after code changes need documenting. Updates llmdoc system based on recent code changes.
majiayu000/claude-skill-registry 163
-
pop-assessment-anthropic
Validates PopKit compliance with Claude Code patterns using concrete standards and automated checks
majiayu000/claude-skill-registry 163
-
hitl-approval
Implement human-in-the-loop approval flows. Use when adding Slack approvals, dashboard review queues, action gating, or trust-based auto-approval.
majiayu000/claude-skill-registry 163
-
blog-manager
Use for all blog writing tasks including creating articles (Zenn Japanese, dev.to/Medium English), managing ideas, and setting up blog projects. This is the unified entry point for technical blog writing workflow. Supports idea tracking with status management (backlog/in-progress/done).
majiayu000/claude-skill-registry 163
-
causal-inference-root-cause
Use when investigating why something happened and need to distinguish correlation from causation, identify root causes vs symptoms, test competing hypotheses, control for confounding variables, or design experiments to validate causal claims. Invoke when debugging systems, analyzing failures, researching health outcomes, evaluating policy impacts, or when user mentions root cause, causal chain, confounding, spurious correlation, or asks "why did this really happen?"
majiayu000/claude-skill-registry 163
-
sam-gov-ops
Query SAM.gov for federal contracts, entity registrations, exclusions, and opportunities. Uses official GSA APIs for government contractor intelligence and OSINT research.
majiayu000/claude-skill-registry 163
-
literature-review
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
majiayu000/claude-skill-registry 163
-
idb-state-persistence
IndexedDB patterns for local-first state persistence using the idb library. Use when implementing features that require persistent state across navigation and sessions. Covers data modeling, defaults, CRUD operations, state managers, and reset patterns. Integrates with web-components for reactive UI updates.
majiayu000/claude-skill-registry 163