Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
QuantConnect Optimization
QuantConnect optimization API and Phase 4 parameter tuning (project)
majiayu000/claude-skill-registry 163
-
changelog-maintenance-skill
majiayu000/claude-skill-registry 163
-
ui-libraries-components
Integrate modern UI libraries and reusable components into the project.
majiayu000/claude-skill-registry 163
-
building-with-observability
Build Kubernetes observability stacks with Prometheus, Grafana, OpenTelemetry, Jaeger, and Loki. Use when implementing metrics, tracing, logging, SRE practices, or cost engineering for cloud-native applications.
majiayu000/claude-skill-registry 163
-
Debugging
Systematic debugging framework ensuring root cause investigation before fixes. Includes four-phase debugging process, backward call stack tracing, multi-layer validation, and verification protocols. Use when encountering bugs, test failures, unexpected behavior, performance issues, or before claiming work complete. Prevents random fixes, masks over symptoms, and false completion claims.
majiayu000/claude-skill-registry 163
-
groq-rate-limits
Implement Groq rate limiting, backoff, and idempotency patterns.
Use when handling rate limit errors, implementing retry logic,
or optimizing API request throughput for Groq.
Trigger with phrases like "groq rate limit", "groq throttling",
"groq 429", "groq retry", "groq backoff".
majiayu000/claude-skill-registry 163
-
xlsx
Expert in automating Excel workflows using Node.js (ExcelJS, SheetJS) and Python (pandas, openpyxl).
majiayu000/claude-skill-registry 163
-
alto-self-fix
Use when ALTO needs to fix itself via GitHub issues. Procedural workflow for running /alto-self-fix or solving issues through ALTO's self-improvement process.
majiayu000/claude-skill-registry 163
-
readme-guilhermedemorais-de-context-engineering-
majiayu000/claude-skill-registry 163
-
Smart Intent Detection
Automatic workflow suggestion and utility agent routing based on prompt analysis. Trigger keywords: auto-detect, intent, suggest, trigger, routing, workflow detection, utility agents, prompt analysis, smart routing
majiayu000/claude-skill-registry 163
-
write-pr-desc
Generate a GitHub Pull Request description. Creates structured, reviewer-centric PR descriptions with title, summary, why (before/after), implementation details, and impact. Use when user says "write PR description", "PR desc", "describe this PR", or "generate PR description".
majiayu000/claude-skill-registry 163
-
hqq-quantization
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.
majiayu000/claude-skill-registry 163
-
kolmogorov-compression
Kolmogorov complexity as the ultimate intelligence measure. Shortest
majiayu000/claude-skill-registry 163
-
external-reference-research
Specialized agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. Use proactively when unfamiliar libraries or frameworks are involved, working with external dependencies, or needing examples from open-source projects to understand best practices and real-world implementations.
majiayu000/claude-skill-registry 163
-
ui-skills
Opinionated constraints for building better interfaces with agents.
majiayu000/claude-skill-registry 163
-
Session Checker
Check if Interstellio/NebularStack client sessions are active. Analyzes CDR records to determine connection status, session history, and terminate causes.
majiayu000/claude-skill-registry 163
-
expropriation-statutory-deadline-tracking
Expert in managing critical statutory timelines under Ontario Expropriations Act including 3-month registration window, Form 2/7 service timing, and escalation protocols by timeline urgency. Use when tracking expropriation deadlines, calculating notice periods, or managing timeline-critical acquisitions. Key terms include statutory deadlines, 3-month registration, Form 2 service, Form 7 notice, approval expiry, escalation protocols
majiayu000/claude-skill-registry 163
-
video-notify
majiayu000/claude-skill-registry 163
-
cloud-deploy-blueprint
End-to-end cloud deployment skill for Kubernetes (AKS/GKE/DOKS) with CI/CD pipelines. Covers managed services integration (Neon, Upstash), ingress configuration, SSL certificates, GitHub Actions workflows with selective builds, and Next.js build-time vs runtime environment handling. Battle-tested from 9-hour deployment session.
majiayu000/claude-skill-registry 163
-
conductor-revert
Git-aware undo by logical work unit (track, phase, or task)
majiayu000/claude-skill-registry 163
-
crewai
Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.
majiayu000/claude-skill-registry 163
-
matchms
Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing.
majiayu000/claude-skill-registry 163
-
gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
majiayu000/claude-skill-registry 163
-
prompt-architect
Create and enhance prompts, system instructions, and principle files. Capabilities: transform verbose prompts, add patterns/heuristics, optimize token usage, structure CLAUDE.md principles, improve agent/persona definitions, apply prompt engineering techniques (CoT, few-shot, ReAct). Actions: create, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, system prompt, CLAUDE.md, principle files, instruction optimization, agent prompt, persona prompt, token efficiency, prompt structure, workflow prompts, rules, constraints, few-shot, chain-of-thought. Use when: creating new prompts, enhancing principle files, improving system instructions, optimizing CLAUDE.md, restructuring verbose prompts, adding patterns to workflows, defining agent behaviors.
majiayu000/claude-skill-registry 163