精选 Skills 索引（第 150 页）
按质量分排序的前 8,000 个 Skills，每个都有可收录的独立页面。需要全库 15.8 万条检索时，请使用 Skills 目录。
- speckit-plan
Generate technical implementation plans from feature specifications. Use after creating a spec to define architecture, tech stack, and implementation phases. Creates plan.md with detailed technical design.
- speckit-specify
Create or update feature specifications from natural language descriptions. Use when starting new features or refining requirements. Generates spec.md with user stories, functional requirements, and acceptance criteria following spec-drive…
- speckit-tasks
Break down implementation plans into actionable task lists. Use after planning to create a structured task breakdown. Generates tasks.md with ordered, dependency-aware tasks.
- speckit-taskstoissues
Convert tasks from tasks.md into GitHub issues. Use after task breakdown to track work items in GitHub project management.
- speech
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `…
- splitting-datasets
Split datasets into training, validation, and test partitions with the right stratification and temporal rules. Use as a narrow preprocessing helper once the broader ML workflow is already chosen, not as the main route owner for an end-to-…
- spreadsheet
Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) using Python (`openpyxl`, `pandas`), especially when formulas, references, and formatting need to be preserved and verified.
- stable-baselines3
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with…
- statistics-math
Statistics, probability, linear algebra, and mathematical foundations for data science
- structured-content-storage
Enforces structured, highly documented storage for code and data projects. Use when working on machine learning scripts, data processing, code creation, or script modification that should preserve clear structure and documentation.
- subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
- submission-checklist
Stage-based submission checklists for papers/reports: pre-submission, submission, revision/rebuttal, camera-ready. Includes templates (cover letter, rebuttal matrix) and quality gates.
- systematic-debugging
Root-cause route for actual bugs, failing tests, build errors, crashes, stack traces, and unexpected behavior. Do not use for test-first/TDD feature work, test-report packaging, review-feedback handling, or final completion evidence.
- tdd-guide
Test-first development route for TDD, writing failing tests first, RED -> GREEN -> REFACTOR, and behavior-changing feature/bug/refactor work. Do not use for already-failing test root-cause debugging, test-report packaging, or final complet…
- think-harder
4-phase structured analysis wrapper for vibe pre-routing (compatible with claude-code-settings think-harder semantics).
- tiledbvcf
Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.
- timesfm-forecasting
Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements…
- torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
- transcribe
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
- treatment-plans
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care,…
- uniprot-database
Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For broader biological evidence lookup across databases, use bio-database-evidence. Use this for direct HTTP/REST work or UniProt-specific…
- usfiscaldata
Query the U.S. Treasury Fiscal Data API for federal financial data including national debt, government spending, revenue, interest rates, exchange rates, and savings bonds. Access 54 datasets and 182 data tables with no API key required. U…
- uspto-database
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
- ux-researcher-designer
UX research and design toolkit for Senior UX Designer/Researcher including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use for user research, persona creation, journey mapping, and…
- vaex
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and…
- venue-templates
Use when preparing manuscripts, conference papers, or academic posters that need venue-specific templates, LaTeX style files, author guidelines, page limits, anonymity rules, camera-ready formatting, or submission compliance checks.
- vercel-deploy
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
- Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
- verification-before-completion
Completion-evidence route used before claiming work is complete, fixed, passing, committed, or PR-ready. Requires fresh verification output before success claims. Do not use for root-cause debugging, TDD implementation, test-report packagi…
- vibe
Vibe Code Orchestrator (VCO) is a governed runtime entry that freezes requirements, bounds execution, and enforces verification and phase cleanup.
- video-studio
Use when the user asks to create or edit videos end-to-end (script→video, auto-cut/jumpcut, captions/subtitles, polishing for Shorts/Reels/TikTok). Current implemented backend: local FFmpeg (probe/render/jumpcut/burn-subtitles/polish). Pla…
- visualization-best-practices
Review chart choice, labeling, accessibility, and storytelling quality for existing visualizations. Use as an explicit/manual helper for critique and cleanup, not as the main owner for scientific figure production or general chart generati…
- vscode-release-notes-writer
Guidelines for writing and reviewing Insiders and Stable release notes for Visual Studio Code.
- webthinker-deep-research
Deep web research for VCO: multi-hop search+browse+extract with an auditable action trace and a structured report (WebThinker-style).
- windows-hook-debugging
Windows环境下Claude Code插件Hook执行错误的诊断与修复。当遇到hook error、cannot execute binary file、.sh regex误匹配、WSL/Git Bash冲突时使用。
- writing-docs
Guides for writing and editing Remotion documentation. Use when adding docs pages, editing MDX files in packages/docs, or writing documentation content.
- writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
- xan
High-performance CSV processing with xan CLI for large tabular datasets, streaming transformations, and low-memory pipelines.
- yeet
Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).
- zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.