Apply MAKER (Massively Decomposed Agentic Processes) to solve long sequential tasks using task decomposition, multi-agent voting, and error correction.
Expert in Gravito operations and deployment. Trigger this for Docker, Fly.toml, CI/CD, or infrastructure management.
Implement images into page sections. Converts from /public/raw/[page]/ to WebP with responsive variants, replaces CDN placeholders with Next.js Image component.
Parallel 120-probe reconnaissance using G-2 RECON agents. Deploy 12 G-2s commanding 10 D&D-inspired probes each. Use for comprehensive codebase exploration.
When the user wants to optimize procurement decisions, allocate orders across suppliers, or determine optimal order quantities.
High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection — from…
Systematically analyze an AI agent's source code across 8 core + 4 optional platform dimensions and output structured analysis to docs/<agent>.md
Descreve como usar MCPs relevantes (filesystem, git, runtime) para trabalhar com o projeto Daylyou. — from majiayu000/claude-skill-registry-data
Apply RE11 Calibration Loops to repeatedly check predictions against outcomes to improve forecasting accuracy.
学習目的で、あらゆる提案変更に WHY / VERIFY / RISK とロールバックを必ず付ける（コード・コマンド・AWS手順）。WHYは「選択肢→特徴→結論（最適案）」で統一する。
Expert photography composition critic grounded in graduate-level visual aesthetics education, computational aesthetics research (AVA, NIMA, LAION-Aesthetics, VisualQualit — from…
Merge Request나 Pull Request 생성 시 컨벤션과 품질 검사를 따르도록 적용. Use when creating pull requests or merge requests to follow PR conventions and quality checks.
Ordered Locales (Heunen-van der Schaaf 2024): Point-free topology with direction. Frame + compatible preorder with open cone conditions.
Distill a verbose developer-facing prompt into a concise, token-efficient LLM-facing prompt while retaining essential instructions.
Taxonomic classification of ASVs using reference databases like SILVA, GTDB, or UNITE. Covers naive Bayes classifiers (DADA2, IDTAXA) and exact matching approaches.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
Analyze AI/ML technical content (papers, articles, blog posts) and extract actionable insights filtered through enterprise AI engineering lens.
Use when vitest configuration, Vite integration, workspace setup, and test environment configuration for modern testing.
Creates response procedures for security incidents with containment steps, communication templates, and evidence collection.
Mandatory protocol for all SME (Subject Matter Expert) agents. Defines fact-finding requirements, output contracts, confidence/risk assessment, and qualification of advice.
Use when choosing a logging approach, configuring slog, writing structured log statements, or deciding log levels in Go.
Structure scenes and control pacing using scene-sequel rhythm. Use when individual scenes work but don't accumulate, when pacing feels off (too rushed or too slow), when…
Modern Go Web application architecture guide. Use when creating new Go web projects, APIs, or microservices.
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me…
Gene set enrichment analysis with correct geneset format handling. Critical guidance for loading pathway databases and running enrichment in OmicVerse.
Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration.
Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming.
Synthesizes findings across multiple PRs to identify cross-repository dependencies, interface mismatches, and coordination gaps.
When the user wants to solve VRP with Backhauls (VRPB), optimize routes with both deliveries and pickups, or handle reverse logistics.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking.
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator — from majiayu000/claude-skill-registry
Agent skill for spec-mobile-react-native - invoke with $agent-spec-mobile-react-native — from majiayu000/claude-skill-registry
Plans resource allocation and agent assignments to tasks. Use when you need to allocate agents to tasks, balance workload, or plan resource usage.
Generate and edit images using AI models via OpenRouter. Supports Nano Banana Pro (Gemini 3 Pro Image), FLUX, and other image generation models.
Track and compare affiliate offers including network, payout, caps, restrictions, performance history, and payout changes over time.
Implementation workflows and decision trees for Frappe Whitelisted Methods (REST APIs). Use when determining HOW to implement API endpoints: public vs authenticated, perm — from…
Work with BigCommerce catalog — products, variants, options, modifiers, categories, brands, metafields, images, and bulk operations.
Fusion/Comparison Thread for architecture decisions. Use when: - User says "compare approaches", "which is better" - User asks to "evaluate options", "architecture decision" -…
Use when the user asks for a deep codebase analysis to identify and rank improvements, optimizations, architectural enhancements, or potential bugs aligned to developer — from…
Use when choosing between mutually exclusive strategic paths or building a repeatable decision process—constructs Decision Matrices with probability estimates and runs Pre-Mortems.
Testing toolkit for the FHIR Writing Clinical Notes specification at connectathons. Use when the user needs to test FHIR DocumentReference write operations, validate conf — from…
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production.
Borrow from Aave via credit delegation. Agent self-funds by borrowing against delegator collateral. Supports borrow, repay, health checks. Works on Aave V2/V3.
Translate SKILL.md and README.md files into multiple languages for sharing skills internationally — from majiayu000/claude-skill-registry
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional — from…
[31] ANALYZE. Universal deep thinking methodology for any situation requiring quality reasoning. Use when solving problems, debugging, making decisions, analyzing code, p — from…
Cynefin sense-making framework categorizing problems as Simple, Complicated, Complex, Chaotic, or Confused to select the right approach.
Professional network graph analyst identifying Gladwellian superconnectors, mavens, and influence brokers using betweenness centrality, structural holes theory, and multi — from…
Generate security assessment reports in docx format with findings, risk ratings, and remediation recommendations.
Use when iteratively improving agent prompts through automated LLM-as-Judge evaluation. Runs eval→fix→commit loop with circuit breakers.
Detect and alert on emerging anomalies and risk flags from pilot metrics and data streams. Use when monitoring live data, threshold breaches, or statistical outliers to t — from…
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
When the user wants to solve knapsack optimization problems, select items with constraints, or maximize value with limited capacity.
Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate mul — from…
Iteration 6 of Multiplicity Cascade - Documentation that modifies itself when read — from majiayu000/claude-skill-registry
Use when switching between LLM providers, accessing provider-specific features (Anthropic caching, OpenAI logprobs), or using raw SDK clients - covers multi-provider patterns and…
Run quantitative or thematic stock screens to surface investment ideas. Supports AR (BYMA, CEDEARs) and US markets.
Creates detailed technical specifications including architecture, data models, APIs, and technology choices.
Create or update project brief through interactive discovery. Use when starting any new idea, revisiting an idea after time away, or when vision feels unclear.
Get a deep critical review of research from GPT using a secondary Codex agent. Use when user says \"review my research\", \"help me review\", \"get external review\", or wants…