Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Guide for integrating with the OpenJung (OEJTS) personality test API - a free, open-source alternative to MBTI. Use when building applications that need personality assessment, integrating MBTI-style tests, or working with the OpenJung API endpoints. Covers: (1) Fetching test questions, (2) Submitting answers and calculating results, (3) Understanding the scoring system, (4) Recording test sessions, (5) Retrieving aggregate statistics.
Query Open Targets GraphQL API for target-disease associations, evidence, drug links, safety. Search targets by gene, diseases by EFO ID; scores from 20+ sources, drug mechanisms, tractability. For ChEMBL use chembl-database-bioactivity; for trials use clinicaltrials-database-search.
Perform complete database health, correctness, performance, reliability, and scalability audits across SQL, NoSQL, key-value, cache, search, and managed database systems. Detects the existing database and query layer, then checks indexes, query plans, schemas, constraints, relations, transactions, locks, pagination, pooling, caching, migrations, backups, observability, security, retention, replication, partitioning, and capacity. Use when diagnosing slow queries, reviewing an entire data layer, preparing for growth, reducing database cost, or safely optimizing production workloads.
This skill should be used when converting academic papers into promotional and presentation formats including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster). Use for paper dissemination, conference preparation, creating explorable academic homepages, generating video abstracts, or producing print-ready posters from LaTeX or PDF sources.
Find academic papers across up to 8 sources (OpenAlex / Semantic Scholar / CrossRef / PubMed / arXiv for English, OpenReview for AI venues, plus native-Chinese retrieval via NSSD 国家哲社文献中心 + yiigle 中华医学期刊) with adjustable depth — Quick scan (5 min) to Audit prep (3 hr). Use when the user wants to find papers, run a literature search, gather references, scope a research topic, search Chinese-language / 中文原生 literature (中文文献/中文核心/CSSCI/C刊/国内研究/国内文献/中华××期刊/心理学报/经济研究), or filter results by journal tier (中科院分区/一区/几区, Q1, JCR/SJR quartile, 影响因子/impact factor, 期刊分区, 顶刊/top journal, '按分区筛'), or export paste-ready professional search strategies / 检索式 for external databases (PubMed / WOS / Scopus / Embase / 知网 CNKI / 万方 / SinoMed — '写检索式', '导出检索式', 'WOS 检索式', '知网专业检索', 'search strategy', 'boolean search strategy'). Triggers on search verbs ('find papers', 'literature search', 'papers about X'), review types ('scoping review', 'systematic review', 'SR prep', 'literature review', 'lit review', 'help me write a lit review'), Chinese ('找文献', '找论文', '论文搜索', '学术检索', '文献检索', '文献综述', '综述前期', '求文献', '中文文献', '中文核心', 'CSSCI', 'C刊', '国内研究', '找中文的'). Outputs Shadcn HTML report + BibTeX/RIS/CSV + PRISMA-S log. Do NOT use for: concept explanations ('what is X' / 'X 是什么', e.g. '影响因子怎么算'), writing ('帮我写' / 'help me write a paragraph'), single-paper interpretation or PDF download with metadata (use paper-downloader-portable), or when the user already has a literature set (use literature-set-review).
Use when the user wants to verify paper claims against code or data, audit numerical accuracy, check formula-code alignment, or validate citation accuracy. Triggers on phrases like "verify claims", "check numbers", "do the numbers match", "formula vs code", "audit the paper", or "cross-check results".
Develop and operate a local Paperclip instance — start and stop servers, pull updates from master, run builds and tests, manage worktrees, back up databases, and diagnose problems. Use whenever you need to work on the Paperclip codebase itself or keep a running instance healthy.
Multi-agent parallel development cycle with requirement analysis, exploration planning, code development, and validation. Orchestration runs inline in main flow (no separate orchestrator agent). Supports continuous iteration with markdown progress documentation. Triggers on "parallel-dev-cycle".
Startup and life advice channeling Paul Graham's essays, YC experience, and Twitter wisdom. Use this skill when: (1) Evaluating startup ideas or finding new ones (2) Early-stage strategy and user acquisition (3) Growth and survival decisions (default alive?) (4) Fundraising and investor relations (5) Founder leadership and team building (6) Avoiding common startup mistakes (7) Career and life decisions Invoke with /paul-graham or auto-triggers for startup advice topics.
When validating system performance under load, identifying bottlenecks through profiling, or optimizing application responsiveness. Covers load testing (k6, Locust), profiling (CPU, memory, I/O), and optimization strategies (caching, query optimization, Core Web Vitals). Use for capacity planning, regression detection, and establishing performance SLOs.
PHP web archive extraction (Zip Slip / path traversal) auditing tool. Identifies how extraction entry names are joined with the target directory and whether the base dir constraint is missing, and outputs exploitability grading, an observable PoC and remediation advice (omission is not allowed).
LiDAR and point cloud processing: PDAL pipelines, LAS/LAZ/COPC handling, ground classification, DTM/DSM/CHM generation, canopy and building metrics, and photogrammetric (SfM) point clouds. Use when the primary input is LAS, LAZ, COPC, LiDAR, or an unstructured 3D point cloud. This skill owns vertical datum agreement, co-registration and the vertical-accuracy budget when two acquisitions are differenced with comparability not yet established; once datum, geoid and accuracy are documented, a subsidence or elevation-change question is change-detection's. Route a derived DEM, DTM, DSM or CHM to terrain-hydrology unless point-level classification, comparability, or metrics remain in scope.
Fast in-memory DataFrame with lazy evaluation, parallel execution, Arrow backend. Use for tabular data in RAM (1–100 GB) when pandas is too slow. Expression API: select, filter, group_by, joins, pivots, window. Lazy mode enables predicate/projection pushdown. Reads CSV, Parquet, JSON, Excel, DBs, cloud. Larger-than-RAM: Dask; GPU: cuDF.
The terminal for GoHighLevel. Bulk ops, dedup, and pipeline reports in seconds — local cache, agent-native JSON,... Trigger phrases: `search GHL contacts`, `GHL pipeline funnel`, `stale recruits in GoHighLevel`, `bulk tag GHL contacts`, `dedup GoHighLevel contacts`, `use ghlcli`, `run ghlcli`.
Edit existing PowerPoint files or templates with XML-safe workflows. Use for template-based deck updates: analyze layouts, map content to slides, duplicate/reorder/delete slides safely, edit slide XML in parallel, clean orphaned assets, and repack validated PPTX output.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Comprehensive GitHub Pull Request code review skill. Use when asked to "review this PR", "code review", "review pull request", "check this PR", or when a GitHub PR URL is provided. Fetches PR metadata, diff, comments, commits, and related issues using gh CLI. Creates organized review workspace, analyzes code against industry-standard criteria, and optionally adds inline comments to the PR.
Elicit and check Bayesian prior assumptions in meaningful units. Use for expert quantiles, PreliZ, constrained priors, prior-predictive plausibility and prior sensitivity, including power scaling, regularized horseshoe and R2D2 assumptions.
Use when the user needs product management workflows such as RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, go-to-market strategy, feature prioritization, research synthesis, or requirements documentation.
Expert in designing compelling progression systems that create the "one more turn" hook while respecting player time. Deep knowledge of XP mathematics, skill tree topology, reward pacing psychology, and meta-progression loops. Draws from decades of ARPG evolution (Diablo, Path of Exile), roguelike innovation (Hades, Slay the Spire), and mobile design patterns. Use when "level up system, xp curve, skill tree, progression system, unlock system, prestige system, battle pass, new game plus, loot progression, power curve, meta progression, achievement system, " mentioned.
This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better prompts", "debug prompt issues", "use chain-of-thought", "structured prompting", "few-shot prompting", or wants to apply advanced prompt engineering patterns for production LLM applications.
Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.
Mathematical proof writing skill — a complete proof workflow from claim extraction to LaTeX typesetting. Use this skill whenever the user needs to write or verify formal proofs of mathematical theorems, lemmas or propositions, or needs to derive formulas or organise theoretical analysis. Trigger words include: mathematical proof, prove, theorem, lemma, proposition, derivation, theoretical analysis, write proof, LaTeX math, formal proof. Suitable for machine learning theory, statistical learning theory, optimisation and other scenarios requiring rigorous mathematical derivation.
Complete Python 3.13+ fundamentals system. PROACTIVELY activate for: (1) Python 3.13 free-threading (no-GIL), (2) JIT compiler usage, (3) Pattern matching syntax, (4) Walrus operator, (5) F-string features 3.12+, (6) Type parameter syntax 3.12+, (7) Exception groups, (8) Dataclasses and enums, (9) Context managers. Provides: Modern syntax, performance features, best practices, naming conventions. Ensures correct Python 3.13+ patterns with optimal performance.
Complete Python GitHub Actions system. PROACTIVELY activate for: (1) uv-based CI workflows (10-100x faster), (2) Matrix testing across Python versions, (3) Dependency caching with setup-uv, (4) Parallel test execution, (5) Reusable workflows, (6) Publishing to PyPI with trusted publishing, (7) Code coverage with codecov, (8) Security scanning. Provides: Workflow templates, caching config, matrix strategies, composite actions. Ensures fast, reliable CI/CD pipelines.
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
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.
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
Use when documenting a resolved or contained production incident, outage, near-miss, silent pipeline/service failure, data corruption event, or post-mortem — guides evidence collection while the post-fix state is still observable and produces a rich, reproducible Root Cause Analysis report. Trigger on phrases like “write an RCA,” “post-mortem for X,” “document this incident,” “what went wrong with...,” “the pipeline broke yesterday and we fixed it, write it up,” or when the user wants help structuring evidence for a write-up of a recently resolved incident. Also use proactively when the user finishes resolving an incident in-session and the resolution context is fresh — offer to capture it as an RCA before details fade. If the incident is still live and the user needs help finding the cause or fixing it, use ultrathink-protocol instead and come back here once it is contained.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.