Skills directory · page 20

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

Use before analysis or model training on any dataset, or when asked to profile data or hunt missing values and outliers. Profiles it with data_profiler.py, missing_value_analyzer.py and outlier_detector.py and writes a remediation plan.

Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.

Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Runs on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.

Build a fully automated AI-powered data-collection agent for any public source, including job boards, pricing, news, GitHub, and sports. Runs on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs entirely free on GitHub Actions. Use when the user wants to automatically monitor, collect, or track any public data.

任意のパブリックソース（ジョブボード、価格、ニュース、GitHub、スポーツなど）用の完全自動化されたAI搭載データ収集エージェントを構築します。スケジュールでスクレイプし、無料LLM（Gemini Flash）でデータを豊かにし、Notion/Sheets/Supabaseに結果を保存し、ユーザーフィードバックから学習します。GitHub Actions上で100％無料で実行。ユーザーがパブリックデータを自動的に監視、収集、または追跡したい場合に使用します。

Diagnose and accelerate large data movement — ingestion, backfill, export, ETL, warehouse loading, manifest catch-up, and table synchronization — by isolating the true bottleneck, benchmarking variants, and codifying the fastest path with a hard accounting block proving rows and timestamps cohere. Use when a pipeline or backfill is too slow and must get faster without losing data correctness.

Expert database architect specializing in data layer design from scratch, technology selection, schema modeling, and scalable database architectures.

Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.

Design a database schema: tables, relationships, indexes, normalization, SQL vs NoSQL, migration plans. Use whenever the user asks how to structure their data, which database to pick, or before writing DDL.

Master database schema and data migrations across ORMs (Sequelize, TypeORM, Prisma), including rollback strategies and zero-downtime deployments.

Safe, reversible database migration patterns: forward-only production changes, expand-contract zero-downtime renames, concurrent indexes, batched backfills, and per-tool workflows for PostgreSQL, Prisma, Drizzle, Kysely, Django, and golang-migrate. Use when writing a schema or data migration, adding a column or index to a large table, planning a rollback, or preparing a zero-downtime deploy.

Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Django, TypeORM, golang-migrate). Use when planning or implementing database schema changes.

PostgreSQL、MySQL、一般的なORM（Prisma、Drizzle、Kysely、Django、TypeORM、golang-migrate）全体のスキーマ変更、データマイグレーション、ロールバック、ゼロダウンタイムデプロイメントのためのデータベースマイグレーションベストプラクティス。

Buenas prácticas de migración de base de datos para cambios de esquema, migraciones de datos, rollbacks y despliegues de tiempo cero en PostgreSQL, MySQL y ORMs comunes (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).

数据库迁移最佳实践，涵盖模式变更、数据迁移、回滚以及零停机部署，适用于PostgreSQL、MySQL及常用ORM（Prisma、Drizzle、Django、TypeORM、golang-migrate）。

Şema değişiklikleri, veri migration'ları, rollback'ler ve PostgreSQL, MySQL ve yaygın ORM'ler (Prisma, Drizzle, Django, TypeORM, golang-migrate) arasında sıfır kesinti deployment'ları için veritabanı migration en iyi uygulamaları.

Expert database optimizer specializing in modern performance tuning, query optimization, and scalable architectures.

Use when asked for an ERD, table relationships, normalization or a schema migration plan. Produces the ERD and normalized DDL with migration steps.

Design robust, scalable database schemas for SQL and NoSQL databases. Provides normalization guidelines, indexing strategies, migration patterns, constraint design, and performance optimization. Ensures data integrity, query performance, and maintainable data models.

Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use this skill when working with demographic data, economic indicators, health statistics, environmental data, or any public datasets available through Data Commons. Applicable for querying population statistics, GDP figures, unemployment rates, disease prevalence, geographic entity resolution, and exploring relationships between statistical entities.

Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery: SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

Domain-Driven Design guidance for modeling complex domains. Use when designing Bounded Contexts or Subdomains, discovering Aggregate boundaries from invariants and transactions, defining Aggregate Roots, designing Domain Events, typed domain failures, or repository contracts, choosing exception vs Result/Either/Option semantics, choosing Repository vs DAO/query service/gateway, splitting oversized Aggregates, coordinating cross-Aggregate consistency, applying Context Mapping patterns, implementing CQRS or Event Sourcing, building a Ubiquitous Language, applying Hexagonal Architecture, or reviewing layer ownership.

Generate a structured demo outline from your session's change log and git history. Reads .claude/critical_log_changes.csv and git log to produce presentation-ready talking points for end-of-day demos, standups, or delivery deadlines.

Use before closing a deal that needs a discount beyond AE authority, has a redlined MSA or unclear per-deal economics. Scores it with deal_scorer.py, names approvers with discount_approval_router.py and flags risky terms with terms_redliner.py. Never auto-approves.

Handle confidential GitHub Security Advisory response for Paperclip. Use when coordinating advisory triage, private-fork fixes, CVE/publication steps, and immediate security releases.

Systematically find and fix the root cause of bugs, errors, failing tests, and crashes in JavaScript/TypeScript and Python. Use whenever the user pastes an error or stack trace, says something is broken, "not working", "error", "kenapa gagal", "bug", a test fails, or behavior is unexpected — instead of guessing at a fix.

Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.

Transform debugging from frustrating guesswork into systematic problem-solving with proven strategies, powerful tools, and methodical approaches.

Sysinternals DebugView CLI (DbgViewCli) for capturing and analyzing usermode and kernel-mode Windows debug output from the command line. USE FOR: capturing OutputDebugString output, kernel DbgPrint/KdPrint capture, boot-time debug logging, remote debug monitoring, filtering debug output by PID or process name, crash dump analysis, automated debug capture with bounded execution. DO NOT USE FOR: non-Windows platforms, application-level logging frameworks (log4j, serilog), Azure Monitor or cloud telemetry, ETW tracing (use WPR/xperf instead), user-mode crash dumps (use WinDbg). Triggers: "debug output", "DbgView", "DebugView", "kernel debug", "capture debug logs", "boot logging", "OutputDebugString", "DbgPrint", "KdPrint", "remote debug monitor", "debug capture CLI".

Use for /c-level-agents:decide, or right after the founder approves a boardroom memo, to log it as a durable decision.

Use when logging a decision after a board meeting, reviewing past decisions or checking overdue actions. Keeps raw transcripts and approved decisions separately with decision_tracker.py.

Writes an architecture decision record (ADR) for a decision the team has already reached: the context, the options weighed, the choice and its consequences. Use when the user says "record this decision", "write an ADR", "we decided X, capture it", or asks to document a technical choice already made. Not for making the decision itself or for tracking the work it leads to.

Create, build, deploy, and localize declarative agents for M365 Copilot and Teams. USE THIS SKILL for ANY task involving a declarative agent — including localization, scaffolding, editing manifests, adding capabilities, and deploying. Localization requires tokenized manifests and language files that only this skill knows how to produce. Triggers: "create agent", "create a declarative agent", "new declarative agent", "scaffold an agent", "new agent project", "add a capability", "add a plugin", "configure my agent", "deploy my agent", "fix my agent manifest", "edit my agent", "localize my agent", "add localization", "translate my agent", "multi-language agent", "add an API plugin", "add an MCP plugin", "add OAuth to my plugin", "review instructions", "improve instructions", "fix my instructions"

Use when studying or applying Goodfellow, Bengio and Courville's Deep Learning, or asking if its advice still holds. Indexes all 20 chapters with a 2016-to-2026 delta, plans reading paths with reading_path_planner.py and diagnoses training failures with training_diagnostics.py.

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.

Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.

Conduct multi-source deep research using firecrawl and exa MCPs. Search the web, synthesize findings, and deliver reports with source citations. Use when the user wants thorough research on any topic, supported by evidence and citations.

コンテキスト深い研究を実施し、複雑なテーマについての権威ある答えを生成します。複数のソースをキュレート、相互参照、合成してコンテキスト内の完全な画像を構築します。

Produce cited research reports from multiple web sources using firecrawl and exa MCP tools — plan sub-questions, search and deep-read sources, then synthesize findings with inline citations and confidence levels. Use when the user asks to research a topic in depth, run a deep dive or investigation, or do competitive analysis, technology evaluation, market sizing, or due diligence on a company.

Deep research skill powered by NotebookLM MCP. Conducts structured multi-source research (market analysis, competitive intel, trend analysis, prospect research) using Google NotebookLM as the research engine, then delivers formatted briefs and optional studio artifacts (slides, audio podcasts, videos, infographics, reports, mind maps).

Use when someone wants to plan a deep work day, time-block their calendar or task list, budget or cut shallow work, protect focus hours, track deep-work sessions and streaks, run an end-of-day shutdown ritual, or says "/deep-work" or "/time-block". Classifies tasks deep vs shallow, builds an energy-first time-blocked schedule that refuses deep demand past the 4-hour ceiling, batches shallow work into at most two windows, and logs focus sessions against a weekly target.

Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML.

Use when the user asks to deeply read a book, article, PDF, or document set; extract claims and evidence; build a knowledge map; or learn through Feynman explanation and recall. Covers quick, deep, map, Feynman, and whole-book reading modes.

Install and operate Everything Claude Code (ECC) on the DeepSeek Harness (DSH): native skill roots (~/.dsh/skills, .agents/skills), the @deepseek-ai/dsh-hooks-claude-code bridge for command hooks, bare-insert patch mounting, generator usage, event-support limits, and update workflow. Use when setting up ECC on DeepSeek Harness, wiring ECC hooks into a DSH profile, or debugging why ECC skills or hooks do not appear in a DSH session.

NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.

Security checklist for Solidity AMM contracts, liquidity pools, and swap flows. Covers reentrancy, CEI ordering, donation or inflation attacks, oracle manipulation, slippage, admin controls, and integer math. Use when auditing or writing Solidity AMM, liquidity pool, or swap code.