Синхронизация .serena/memories - fact-only заметки из кода/диффов/тестов. Используй для: обнови memories, синхронизируй память, после коммита, после Stop-хука, .serena/plans,…
gotcha/learned 관찰에서 스킬 개선점을 추출하여 autoresearch로 연결하는 자기 개선 루프. 축적된 오답노트와 성공 패턴을 스킬에 매핑 → 체크리스트 자동 생성 → autoresearch 실행. gotcha-analyzer가 패턴 감지 후 이 스킬 실행을 제안합니다. /skill-evolve로 실행.
Create phased implementation plans from research findings. Invoke when a task needs an implementation plan.
Conduct general research using web search, documentation, and codebase exploration. Invoke for general research tasks.
Dispatch the current milestone's slices to a Claude Code Agent Team. Each teammate works on a slice in parallel with its own 200k context (replaces GSD's fresh-subprocess-per-task…
Canonical Hone equity-research skill covering single-stock analysis, valuation framing, and criteria-based screening
TensorFlow machine learning skill specialized for physics applications including neural network potentials and surrogate models
Use when an agent needs structured market, macro, portfolio, calendar, fundamentals, valuation (DCF / reverse DCF / S&P 500 DCF, including turnaround mode), SEC filings,…
Run a cited research pass for TERRAIN design, benchmarks, routing, GIS, or territory-planning decisions.
Automated thermodynamic property method selection based on component characteristics and operating conditions
Construct, analyze, and evaluate philosophical thought experiments to test intuitions, reveal conceptual commitments, and probe theoretical implications
Cambridge Quantum (Quantinuum) t|ket> compiler skill for platform-independent circuit optimization
Time-of-Flight Secondary Ion Mass Spectrometry skill for molecular surface analysis and imaging
AI-powered ternary complex prediction for targeted protein degradation, modeling POI-degrader-E3 ligase assemblies to optimize PROTAC and molecular glue efficacy.
Research latest UI/UX trends from Dribbble and design communities. Use when starting a design project to understand current visual trends, color palettes, and layout patterns.
UCSC Genome Browser query skill for genome annotation retrieval and track data access
Use when citekeys (`@Name2023`, bare `Name2023`), paper/book/chapter references, phrasing like "what does X argue", "from my library", "cite this", or any request that could…
AI-powered virtual laboratory orchestrating multi-agent scientific research teams for autonomous hypothesis generation, experimental design, and validation in biomedical research.
Detect and humanize AI-generated Chinese text. 20+ rule detection categories plus statistical features (sentence-length CV, short-sentence fraction, comma density, perplexity,…
Weights & Biases integration skill for experiment tracking, hyperparameter sweeps, and artifact versioning.
Specialized skill for correlating CFD predictions with experimental wind tunnel data
ALWAYS use when managing GitLab Merge Requests via glab CLI: create, list, view, merge, comment (glab mr note), close, and link to OpenProject issues.
Load an agent profile on demand to adopt a specific role for the current session. Applies the profile's identity, governance scope, boundaries, and initialization declaration…
Pesquisa solucoes, benchmarks e alternativas antes de especificar. Compara trade-offs com dados. Use when researching solutions, comparing alternatives, or evaluating technologies.
Fast codebase scouting using shell search and optional parallel research agents. Use for file discovery, task context gathering, and quick scoped searches across directories.
Wraps the Research Preview `claude agents` CLI (CC 2.1.139+) and `claude plugin details ork` for live observability of parallel agent sessions.
Полное AJTBD-исследование продукта — от сегментации до лендинга, RAT и рекрута. Запускает все AJTBD-скиллы последовательно в одной сессии.
Reproduce core algorithms from research papers. Reads paper from Zotero, extracts key algorithms, implements in Python, runs numerical simulation verification.
Author custom amq-squad roles that are not in the built-in persona catalog, then wire them into a team.
Guides Claude through creating analysis design documents for hypothesis-driven EDA. Use when the user wants to create, manage, or review analysis designs.
Explores existing data and analyses to help frame a hypothesis. Triggers: "framing", "何を分析する", "分析テーマ", "仮説を考えたい", "データを探して", "既存分析を確認", "analysis framing".
Records reasoning steps during hypothesis-driven analysis as an Insight Journal. Supports observation logging, evidence tracking, method decisions, question management, and…
Compare Figma design system components against the Breeze design graph component registry. First builds existingcomponents.json by iteratively fetching all Component nodes from…
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental…
Build rule-based and statistical anomaly detection systems for business metrics — revenue drops, traffic spikes, churn increases, cost overruns
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find…
Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached.
Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germ — from…
Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on…
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle.
Keyword research and strategy for iOS and Android apps. Analyzes keyword difficulty, search volume, relevance, and optimal placement across metadata fields.
Generate physically-based atmospheric scattering shaders — sky domes, planetary atmospheres, LUT-optimized pipelines, depth-aware post-processing.
Deep research on a triaged System Backlog item. Reads the vault, the user's infrastructure, and external best practices, then writes an ideation brief plus a draft plan directory.
[OMX] Bounded best-practice research wrapper using official/upstream evidence first
Load research corpus into the database by processing files, directories, or URLs through semantic chunking, embedding generation, entity extraction, and relationship building
Quasi-experimental design and analysis (diff-in-diff, synthetic control, ITS, regression discontinuity) for when randomised testing is infeasible. Routes to stats-reviewer.
Run metric-driven iterative optimization loops. Define a measurable goal, build measurement scaffolding, then run parallel experiments that try many approaches, measure e — from…
[BETA] Execute work with external delegate support. Same as ce-work but includes experimental Codex delegation mode for token-conserving code implementation.
Generate research-backed content briefs with keywords, competitors, intent, and SEO strategy from a topic.
ALWAYS use when reviewing GitLab MR diff and posting review findings as MR comments via glab CLI. ALWAYS use when user mentions MR 리뷰, MR review, MR 검토, MR 코드 리뷰, MR 안전성 리뷰, MR…
This skill should be used when creating or organizing working files in the .claude/ directory. It enforces consistent structure, naming conventions, and required cross-references…
Analiza críticamente textos argumentativos: framework Paul & Elder (8 elementos + 9 estándares), detección de falacias lógicas y sesgos cognitivos. Evalúa solidez de argumentos.
Audit and optimize Claude Code configuration with dynamic best-practice research
Extract full paper details from a CNKI paper page including title, authors, affiliations, abstract, keywords, fund, classification.
Auto-generates a Markdown codebook from a dataset (CSV, DTA, Excel, Parquet) with types and summary statistics. Use when documenting variables.
Deep-dive research using Codex with Claude's cross-model synthesis. Use when asked \"codex research\", \"codex 리서치\", \"딥다이브\". Not for code review or plan verification.
Add Kaggle/Colab/local environment branching to a notebook copied from Kaggle. Use when you have a Kaggle notebook that needs to run on Colab or locally — inserts ENV detection…
Research new Claude Code features, compare against coide's VISION.md, and suggest what to add to the roadmap
สร้างเอกสารการเรียนรู้ระดับ world-class สำหรับหัวข้อใดก็ได้ — research จาก official docs, verification โดยรัน code จริง, quality review loop จนได้ 100 ทุก dimension, และ learning…
Create detailed implementation plans with codebase research and, after explicit user approval, publish the approved phased plan to Linear by creating a project under a chosen…