Use when optimizing prompts, skill descriptions, or agent instructions for clarity, specificity, and behavioral effectiveness. — from majiayu000/claude-skill-registry
Analyze review comments from brave-core PRs to discover learnable patterns for improving bot documentation and best practices.
Research technical solutions, analyze architectures, gather requirements thoroughly. Use for technology evaluation, best practices research, solution design, scalability/ — from…
Implement a new synthetic data generator using NeMo Data Designer by defining its configuration and executing a preview job.
Gather facts and context from codebase, docs, and web,... Use when exploring patterns, finding implementations, looking up documentation, or researching before decisions.
Creates new specialized agents using the 5-phase workflow (ANALYZE > DESIGN > CREATE > VALIDATE > REFINE).
Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or…
Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships — from majiayu000/claude-skill-registry
Track and analyze trends, breaking news, and market shifts. Measures velocity across web, social, news, GitHub, and academic signals.
Interactive interview to formalize a research idea into a structured specification with hypotheses and empirical strategy
Delete a keyvalue namespace and all its keys. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Research a task, problem, bug, or feature by exploring the codebase. Use when starting new work, encountering bugs, or needing to understand how existing implementation r — from…
This skill should be used when the user asks to "optimize a DSPy program", "use MIPROv2", "tune instructions and demos", "get best DSPy performance", "run Bayesian optimi — from…
Get query logs for a specific database. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle.
Generate probability-weighted alternative options that challenge default thinking. Forces unconventional alternatives and exposes hidden assumptions behind the "obvious" — from…
Gestion des modules Git (submodules). Ajouter, synchroniser et gérer les maquettes.
Analyze Rust project structure using LSP symbols. Triggers on: /symbols, project structure, list structs, list traits, list functions, 符号分析, 项目结构, 列出所有, 有哪些struct
Routes a vague symptom or complaint to the most relevant Clairvoyance skill via a decision tree. Use when someone describes a problem but doesn't know which skill to reach for.
Iterative development team with Generator-Critic loop, dynamic pipeline selection (patch/sprint/multi-sprint), task ledger for progress tracking, and shared wisdom for…
Explain a topic in "Explain Like I'm 5" (ELI5) style, optionally grounded in Internet/Web facts. Use when the user wants a topic explained in a very simple, child-friendly way, or…
DeliveryManager — Commit + push + PR con convenciones Intrale en un solo comando — from majiayu000/claude-skill-registry
Use this skill to add planned work discovered during execution to the end of the current milestone in the roadmap.
Reverse engineer and analyze a specific feature in Claude Code's source. Use when the user wants to understand how a Claude Code feature works internally, or when asked to analyze…
Add a new GraphQL query endpoint with type safety, GraphORM integration, and tests
Manage voice assistant personalities. List, create, switch, edit, delete, export, or import personalities.
Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop) → Workflow 3 (paper writing, optional).
Claude Code 커스텀 에이전트를 만들고 실행할 때 사용하는 스킬. 사용자가 "에이전트 만들어", "Claude agent 생성", "--agents 설정"을 요청하면 활성화됩니다.
Universal execution engine consuming .task/*.json directory format. Serial task execution with convergence verification, progress tracking via execution.md + execution-events.md.
Deep research with cross-verification and source tiering. Use when investigating technologies, comparing tools, fact-checking claims, evaluating architectures, or any tas — from…
Analyze GitHub issues, Pull Requests (PRs), Discussions, and repo health for an Open Source Software (OSS) project.
Deep analysis workflow for codebases, architectures, systems, products, markets, or research topics. Use when the user asks to analyze, investigate, assess, evaluate, compare, or…
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge.
Use this skill when switch model profile for kata agents (quality/balanced/budget). Triggers include "set profile", "set profile".
Get statistics for keyvalue storage. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
Deep web research on any topic — multi-source investigation, structured markdown report saved to file
Analyze a session transcript with AI and generate structured insights (prompt quality, strategy critique, key decisions, takeaways) for the rewind viewer.
Competitive intelligence for companies, products, markets, or websites. Maps sites, analyzes products and pricing, tracks news and sentiment, profiles the competitive landscape,…
SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention.
Execute iterative development loop through user stories. Implements one story at a time with quality gates, commits, and learning persistence. Ships features autonomously.
Structured literature search and synthesis with citation extraction and gap identification
Research and compare the Stateless Agent Methodology (SAM) against other methodologies using only verifiable reference material.
Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses.
Explain a file, function, or system — architectural walkthrough using query tools
Produce a structured codebase analysis report with architecture overview, critical files, patterns, and actionable recommendations.
Analyze trends across session metrics. Computes windowed aggregates, deltas, and compares against MEMORY.md findings. Use periodically for progress tracking.
Search codebase and git history for keywords. Use when investigating code changes, finding where features were added, or tracking down when bugs were introduced.
Use when optimizing prompts, skill descriptions, or agent instructions for clarity, specificity, and behavioral effectiveness. — from majiayu000/claude-skill-registry
Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition — from…
Zero-assumption API design review. Uses the API as a consumer first, then audits contracts, error shapes, auth model, pagination, versioning, idempotency, and rate limiting.
Start autonomous execution with stop hook feedback loop. Works until all tasks complete or max iterations reached. Use when you want continuous unattended execution.
Execute SQL query on a database. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Get an external patent examiner review of a patent application. Use when user says \"专利审查\", \"patent review\", \"审查意见\", \"examiner review\", or wants critical feedback — from…
Use when analyzing backlink profiles, link authority, toxic links, link-building opportunities, or competitor link gaps. 外链分析/反向链接
Convert legacy subagents, slash commands, and rules to the unified Agent Skills format. Use when migrating agent resources, consolidating legacy directories, or standardi — from…
Build AI agents with Google ADK Python. Multi-agent systems, A2A protocol, MCP tools, workflow agents, state/memory, callbacks/plugins, Vertex AI deployment, evaluation.
Install Chrome DevTools MCP server for debugging and network inspection in Claude Code
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Comprehensive Polish plot evaluation with full due diligence (~20-30 min). Use when user wants deep analysis of a property listing after initial triage, or needs complete risk…