Deep, iterative, multi-source research that explores a topic from multiple perspectives, detects contradictions, and produces a comprehensive vault note with fact-level citations…
Assess risks with likelihood, impact, and mitigation options
ML model optimization and deployment on robot edge devices (Jetson, embedded) — from majiayu000/claude-skill-registry
Structured multi-perspective deliberation through adversarial dialogue — from majiayu000/claude-skill-registry
Search and review literature and prior work
Executa validação de qualidade com 11 fases de QA e tiers de complexidade. Use quando precisar validar qualidade de código, rodar QA checks, ou garantir que o código está pronto…
Research a topic and create a new note in the vault. Use this skill whenever the user wants to learn about a topic they don't know yet, investigate a question, explore an idea, or…
Measurable criteria translating qualitative debate to quantitative scores
I mine pixels for atoms. Reality is just compressed resources. — from majiayu000/claude-skill-registry
K-lines as semantic activation — the name activates the tradition.
Optimize SVG assets, generate sprites, and convert to React components — from majiayu000/claude-skill-registry
Behavior tree design and implementation for robot decision making
여러 웹 페이지의 스크린샷을 찍어 시각적으로 동일한지 비교. 페이지 비교, 디자인 비교, 시각적 차이 확인 시 사용.
GLM-5 Agent Teams skill for spawning teammates with thinking mode
note.comのリサーチツール - 非公式API + MCP + WebSearchでゼロコストリサーチ
Provide recommendations with rationale and alternatives
Run a Recursive Language Model-style loop for long-context tasks. Uses a persistent local Python REPL and an rlm-subcall subagent as the sub-LLM (llm_query).
Refactoring guidance with design patterns and code improvement strategies.
Research topics, users, and gather context from X (Twitter)
RED-GREEN-REFACTOR 워크플로우를 강제하는 TDD 개발 스킬
Structure Python so LLMs can understand it in 50 lines. — from majiayu000/claude-skill-registry
Autonomous experiment loop: edit code, commit, run benchmark, extract metrics, keep improvements or revert, repeat forever.
Cannabis-specialized bartender — strains, terpenes, edibles, rolling — from majiayu000/claude-skill-registry
Generate reports with metrics, findings, and visualizations
Expert-level data science, analytics, visualization, and statistical modeling — from majiayu000/claude-skill-registry
When users mention a milestone version (e.g., "0.4.0", "v0.4.0") or ask about release status, invoke this skill to analyze GitHub milestone progress, issues, and suggest next…
Build, lint, ingest, compose Drescher-style schemas
I mine pixels for atoms. Reality is just compressed resources. — from majiayu000/claude-skill-registry
Expert-level R statistical computing, data analysis, and visualization
End AGET session with state capture and sanity checks
Research topics and gather content for video production
Analyze trade-offs between competing architectural concerns
Initialize AGET session with status briefing
将一条已生成的 digest/research 归档到指定 topic，并更新 topic 的 sources/timeline（M2/M3 辅助能力）。
This skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "use GPT for planning", "ask GPT to review", "get GPT's opinion", "what does GPT think",…
Audit whether an AI agent can autonomously close the loop on problems in a given area — from discovering a symptom to verifying a fix — without human intervention.
Decision-first data analysis with statistical rigor gates.
Missing state triggers repair, not failure.
Safe referencing of real people's traditions without impersonation — from majiayu000/claude-skill-registry
Structured skill for conducting engineering trade studies and concept selection
Identity layers for characters — WHO they are vs WHAT they do
Fix integer type definitions for specified platform. Researches correct primitive type mappings and applies fixes to platform-specific int headers.
Get a specific API key by id. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Plan and review TikTok Ads creative experiments with measurement, rights, and conversion guardrails. Use for TikTok advertising, Spark Ads, short-form video ads, creator — from…
Quick update to today's journal without full review. Use when user wants to quickly log something they did, add a journal entry, or note an activity.
Delete a thread. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Converge on a single recommended solution after brainstorming options. Use when you have multiple candidate approaches and need to analyze trade-offs, select one, and def — from…
Prompt engineering patterns for Claude including system prompts, few-shot examples, chain-of-thought, structured output, templates, and prefilling.
Calculate SOFA (Sequential Organ Failure Assessment) score for ICU patients in MIMIC-IV. Use for sepsis severity assessment, organ dysfunction quantification, mortality…
Submitting, testing, and releasing mobile apps to app stores including App Store and Google Play submission, beta testing, OTA updates, and release management.
Traces decisions and requirements through GSD artifacts. Use when user asks "why did we...", "what happened to...", or mentions decision history.
Enforce feature work on a dedicated git branch and submission via pull request. Use when implementing any feature, fix, or refactor so work is isolated, reviewed, and merged via…
Use when conducting customer discovery interviews, user research, surveys, focus groups, or observational research requiring rigorous analysis - provides systematic 6-phase…
Structure Vue 3 applications using Composition API, component organization, and TypeScript. Use when building scalable Vue applications with proper separation of concerns.
Provides AWS RDS (Relational Database Service) management patterns using AWS SDK for Java 2.x. Use when creating, modifying, monitoring, or managing Amazon RDS database instances,…
Find marker genes and annotate cell types in single-cell RNA-seq using Seurat (R) and Scanpy (Python).
Generate images with Gemini 3 Pro Image (Nano Banana Pro). Covers 4K generation, text rendering, grounded generation with Google Search, conversational editing, and cost…
[31] ANALYZE. Universal deep thinking methodology for any situation requiring quality reasoning. Use when solving problems, debugging, making decisions, analyzing code, p — from…
Break a scope or feature set into stories and tasks for sprint planning (Sofia Nakamura's workflow)
Identify hidden assumptions about users in code that could exclude or harm. A focused analysis asking "What am I assuming about the person using this?