Browse the registry

Every entry, alphabetically — 81,496 in total. Page 268 of 326.

• public-exportPublish a clean public version of a private living-docs project — the method/scaffold and a curated showcase —
• public-plugin-packagingUse when packaging this meta-agent for public Codex plugin registration, Claude Code installation, GitHub rele
• public-policyEconomic analysis of government intervention -- taxation (incidence, efficiency, optimal design), regulation (
• public-relationsWhen the user wants to plan PR, write a press release, or manage media relations. Also use when the user menti
• public-repo-creationCreate production-ready public GitHub repositories with comprehensive documentation, automated setup, and qual
• public-repo-hygieneOfficial catalog registry for skill-hub
• public-speakingHelp users master the art of public speaking by decomposing the skill into manageable components, leveraging s
• public-speaking-coachCoaches a speaker to prepare and deliver a talk, presentation, toast, or pitch — shaping a core message and na
• public-speaking-persuasionKnowledge base on public speaking, persuasion theory, storytelling, argumentation, and cognitive bias. Use whe
• public-status-pageE-commerce skills for AI agents — product research, marketing automation, supply chain optimization, and busin
• public-web-deployPublish a public website safely: DNS, web server, HTTPS, hardening, verify. Routes raw dev servers through ngi
• publication-pipeline-trackerTracks every manuscript, paper, and research output currently in the publication pipeline from email — where e
• publication-trustAssess the scientific integrity and trustworthiness of publications before relying on their findings. Use this
• publicsafetyapi-mcpUS police, fire, EMS and hospital locations near any address, from federal HIFLD data
• publishPublish a packaged product to myclaude.sh via the CLI. Shows summary, requires confirmation, runs myclaude val
• publish-artifactPublish a self-contained HTML artifact or page to a self-hosted static site with a project make publish-artifa
• publish-contentPublish an existing draft to one or more platform accounts. Wraps `postall-agent publish`. Activates when the
• publish-fdd-vs-self-containedChoose and implement .NET publish modes: framework-dependent vs self-contained, single-file, RID graphs. Use w
• publish-hotlineTurn a local program into a callable hotline on the delegated-execution network — write the worker, declare it
• publish-html-pagePublish a self-contained HTML file to a shareable encrypted Cloudflare-hosted artifact URL using html-artifact
• publish-learningPublish only a curated and approved learning. Generate and show a preview first, obtain human approval for AGE
• publish-plugins(project) Use when editing any file under skills/ or plugins/ to bump the plugin version and check the manifes
• publish-prRebase on develop, push the branch, and open a pull request.
• publish-prepRun the finished draft through the full pre-publish check before it goes live. Verifies the SEO basics, the im
• publish-pythonPrepares and triggers a new Python package release: runs cleanup, validates semantic versioning, updates pypro
• publish-releaseRelease moi-computer to npm — verify locally, hand off to the gated GitHub Actions workflow, then verify the p
• publish-reportHelp publish local HTML, Markdown, or built static web projects by asking whether to use Claude Code Artifacts
• publish-rustVerify and release a Rust crate or workspace. Bumps version, commits, tags, pushes. CI-driven by default; --lo
• publish-seo-batchUse when publishing SEO blog articles to qaskills.sh, e.g. "publish today's articles", "daily SEO batch", "wri
• publish-skillConvert a personal agent skill into a distributable, open-source-ready skill. Runs PII audit, generalization,
• publish-skill-bundleUse this skill when the user has a working AI rule or skill file and wants to take it from local draft to a pu
• publish-to-confluencePublish any markdown file from the vault to Confluence with format conversion and approval gate
• publish-to-githubUse this skill when the user is ready to push their local AI skill or rule repository to GitHub for the first
• publish-to-npmPublish a new package to npm under an existing scope, with GitHub Actions release automation, provenance attes
• publish-xPrepare and publish the current moviola project to X (Twitter). Validates platform constraints, renders with t
• publisherPublish HTML frontend projects to the PushWebly publishing platform, list published projects, obtain shareable
• publisher-revenue-audit-mcpPublisher revenue audit: ads.txt and ad-stack checks, Sulvo onboarding, and Boost ad-block recovery
• publisher-wechatsyncUse when the user has a finished blog master draft and wants to publish it to multiple content platforms (知乎/掘
• pubmed-searchSearch PubMed for scientific literature. Use when the user asks to find papers, search literature, look up res
• pueue-job-orchestrationManage long-running jobs and batch processing with pueue queue orchestration, CLI telemetry, and companion mon
• pufferlibVersion-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL tra
• pull-context-dispatchDispatch bounded work to sub/peripheral agents by pointer-reference — pass identity + directive + tool access
• pull-request-guideUse when authoring a pull or merge request - writing the description, sizing and splitting the change, documen
• pull-request-templateOpen-source library of AI agent skills — SKILL.md files for Claude Code, Codex, Gemini CLI, Cursor
• pulling-updates-from-skills-repositorySync local skills repository with upstream changes from obra/superpowers-skills
• pulseDefining KPIs, tracking events, and dashboards: North Star Metric, funnel and cohort analysis, test-intelligen
• pulse-find-exact-same-productFinds product listings that appear to represent the same real-world product as a reference item. Use this skil
• pulse-mcpMCP server for Pulse — free, agent-first social-post metrics (YouTube, X, TikTok, Bluesky, Mastodon, Instagram
• pulse-verityRead crypto reference prices and verify signed receipts. Includes limited keyless samples.
• pulse8-ai-cortex-knowledge-vaultAgent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.
• pulsefeed-x402-mcpVerify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
• pulserDiagnose and test Claude Code skills against Anthropic's 7 principles. Scans SKILL.md files, checks 8 rules (g
• pulumiProduction-ready AI coding skills for APIs. Installable skills for Claude Code, Cursor, Codex CLI, Gemini CLI,
• pulumi-arm-to-pulumiConvert or migrate Azure ARM (Azure Resource Manager) templates, Bicep templates, or code to Pulumi, including
• pulumi-automation-apiLoad this skill when a user asks how to run Pulumi programmatically, embed Pulumi in an application, orchestra
• pulumi-best-practicesLoad when the user is writing, reviewing, or debugging Pulumi TypeScript/Python programs; asks about Output<T>
• pulumi-cdk-to-pulumiLoad this skill when a user wants to migrate, convert, port, translate, or move an AWS CDK application (includ
• pulumi-componentGuide for authoring Pulumi ComponentResource classes. Use when creating reusable infrastructure components, de
• pulumi-debug-failed-operationDebug a Pulumi update or preview that failed: read the failure Pulumi already recorded, find what caused it, a
• pulumi-escGuidance for working with Pulumi ESC (Environments, Secrets, and Configuration). Use when users ask about mana
• pulumi-migrate-from-discovered-stackMigrate a CloudFormation or ARM stack into a Pulumi stack, sourced from a stack that Pulumi Cloud's Discovery
• pulumi-neo-handoffHand off the current thread to a new Pulumi Neo task as a one-way transfer. Use when the user explicitly asks
• pulumi-overviewUse this skill for any task that creates, modifies, inspects, or destroys cloud infrastructure or SaaS configu
• pulumi-terraform-to-pulumiMigrate Terraform/OpenTofu projects to Pulumi, including translating HCL source code and/or importing Terrafor
• pulumi-upgrade-providerAutomate Pulumi provider repo upgrades with the `upgrade-provider` tool. Use when upgrading a pulumi provider
• pump-fun-mcpModel Context Protocol server for the Pump SDK — 53 tools for token creation, trading, fees, analytics, and wa
• pumpfunComplete PumpFun Protocol guide for building token launches, bonding curves, and AMM integrations on Solana. C
• punch-list-managerManage construction punch lists for project closeout. Track deficiencies, assign corrections, and monitor comp
• punkpeye/awesome-mcp-serversA collection of MCP servers.
• punkpeye/fastmcpA TypeScript framework for building MCP servers.
• purchase-order-trackerTracks every purchase order referenced in email — what has been ordered, from which supplier, at what price, w
• purchasingCreate approved purchase orders with the create-purchase-order tool
• purchasing-specialistExpert purchasing specialist with 10+ years experience in procurement, vendor negotiation, supply chain manage
• purple-cow-marketingCreate remarkable products and experiences that spread through word of mouth using Seth Godin's Purple Cow met
• purple-teamUse when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they o
• pursers-centralCoordinate AI-agent work on a local-first, owner-controlled MCP board
• pushCloses the gaps from the most recent /honest and moves the score toward 9. Fires on "push", "push to 9", "clos
• push-ciPush to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then mo
• push-ingestionExpert guide for Monte Carlo's push ingestion model. Use this skill whenever a customer or engineer mentions:
• push-is-publicationLocal commits are cheap and reversible; `git push` is publication — once on origin, CI runs, deploys trigger,
• push-notification-testerTest VoIP push notifications for Telnyx WebRTC iOS (APNs) and Android (FCM) apps. Use when debugging push noti
• push-notificationsGenerate push notification infrastructure with APNs registration, handling, and rich notifications. Use when a
• push-to-productionRelease to production by pushing to main and release branches, verifying Railway auto-deploy, creating a GitHu
• pushbackStress-tests ideas by surfacing assumptions, counterarguments, and confidence gaps. Use when evaluating claims
• pushengageUse when integrating, debugging, asking about, or auditing PushEngage push notifications in any mobile app (iO
• pushengage-androidUse ONLY when the active repo is a native Android app (build.gradle or build.gradle.kts at root with AndroidMa
• pushengage-debugUse when invoked by a PushEngage platform spoke (pushengage-ios, etc.) to diagnose a broken integration. Runs
• pushengage-flutterUse ONLY when the active repo is a Flutter app (`pubspec.yaml` with a `flutter:` SDK block). Handles full Push
• pushengage-iosUse ONLY when the active repo is a native iOS app (Podfile, Package.swift, or *.xcodeproj present at the proje
• pushengage-react-nativeUse ONLY when the active repo is a React Native app (`package.json` with `react-native` dep, typically alongsi
• pusher-mcpQuery the Pusher HTTP API (free tier; set PUSHER_APP_ID, PUSHER_KEY, PUSHER_SECRET, PUSHER_CLUSTER; requests H
• pushtodisplayPushToDisplay CLI and MCP server — send real-time updates to display boards from your terminal or AI agents
• puzzleBuild a puzzle game: grid/board state, move input, rule-based resolution (match-3 cascades, sokoban pushes, ti
• puzzletide-mcpWord search, crossword, and sudoku generators, printable PDF worksheets, and verifiable LLM evals.
• pvliesdonk-paperless-mcpPaperless-NGX over MCP: search, read, upload and tag documents; manage correspondents and types.
• pvliesdonk-scholar-mcpFastMCP server for scholarly papers, patents, books and standards with docling PDF conversion
• pw.algo.ai/agent-commonsPublic and private rooms for agents, with messages, files, search, and resumable events.
• pw.hubris/hubris-mcpOpenAI-compatible LLM gateway for Russia, billed in rubles — catalog, balance, chat via MCP.
• pwa-developmentProgressive Web App development for installable, offline-capable web applications. Use when building PWAs, imp
• pwsh-execA minimal, transparent PowerShell 7 MCP for Windows — one tool: raw exit code, stdout, stderr.
• pxtreeMeasures how a webpage actually renders and prints it as compact text for AI coding agents.
• py-refactorUse when refactoring Python code, cleaning up legacy codebases, optimizing performance, enforcing type safety,
• pyarrow-format-conversion-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• pycacheRule matrix security fixture for pycache used by security rule matrix integration tests; not intended for prod
• pycseA curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.tx
• pydanticPython data validation using type hints and runtime type checking with Pydantic v2's Rust-powered core.
• pydantic-ai-agent-creationCreate PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when b
• pydantic-ai-agentsBuild and debug Pydantic AI v2 agents using best practices for dependencies, instructions, tools, capabilities
• pydantic-ai-common-pitfallsAvoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior
• pydantic-ai-dependency-injectionImplement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need datab
• pydantic-ai-model-integrationConfigure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use w
• pydantic-ai-testingTest PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing u
• pydantic-ai-tool-systemRegister and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use wh
• pydantic-evalsTest and evaluate AI agents and LLM outputs using code-first evaluation framework with strong typing. Use when
• pydantic-model🛠️ Curate and enhance your coding skills with Claude Skills Vault, a collection of commands and MCP server gu
• pydantic-models-pyCreate Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variant
• pydanticai-docsUse this skill whenever the user is working with the Pydantic AI framework — including building AI agents, def
• pydeseq2Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests,
• pydeseq2-differential-expressionBulk RNA-seq DE with PyDESeq2: load counts, normalize, fit negative binomial models, Wald test (BH-FDR), LFC s
• pydicomPython library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill w
• pydicom-medical-imagingPure Python DICOM for medical imaging (CT, MRI, X-ray, ultrasound). Read/write DICOM, pixels as NumPy, edit ta
• pydio-mcpPydio Cells workspaces and tree statistics.
• pydub-automationAutomate repetitive audio tasks with Python using PyDub for batch processing, format conversion, normalization
• pyeuropepmcSearch and analyse scientific literature across Europe PMC, PubMed, arXiv, and ClinicalTrials.gov
• pyfixest-cupy64-absorbed-regressorspyfixest demeaner_backend="cupy64" (including its CPU fallback when cupy is absent) is NOT numerically identic
• pyfixest-grid-shardingDiagnose and fix slow pyfixest regression GRIDS (many feols/fepois calls run sequentially) that stay slow desp
• pygame-coreStructure a pygame (pygame-ce) game in Python: the init/event/update/draw loop, delta-time movement, Surface/R
• pyimagej-fiji-bridgePython bridge to ImageJ2/Fiji for macros, plugins (Bio-Formats, TrackMate, Analyze Particles), NumPy↔ImagePlus
• pyinx-brainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or
• pyinx-frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the use
• pyinx-using-git-worktreesUse when starting feature work that needs isolation from current workspace or before executing implementation
• pyinx-webapp-testingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend
• pylabrobotHardware-agnostic Python liquid-handler library: portable scripts run on Hamilton STAR, Tecan Freedom EVO, Ope
• pylips-mcpControl a Philips Android TV over JointSpace and ADB: power, volume, apps, keys, screen, Ambilight.
• pylon-webhooksReceive and verify Pylon webhooks. Use when setting up Pylon webhook handlers, debugging Pylon signature verif
• pylos-mcpRead-focused, prompt-injection-hardened email MCP server for any IMAP provider
• pymatgen-structureStructure manipulation and crystal analysis workflows based on pymatgen. USE WHEN you need to read/write commo
• pymc-bayesian-modelingBayesian modeling with PyMC 5: priors, likelihood, NUTS/ADVI sampling, diagnostics (R-hat, ESS), LOO/WAIC comp
• pymooMulti-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchma
• pyobfus-mcpObfuscate Python before shipping; reverse-map tracebacks with your AI agent. No phone-home.
• pypi-download-counterFast utility scanning test resources.
• pypi-mcpKeyless MCP server for PyPI: Python package versions, summaries, authors, requirements, release...
• pypi-upload-distdist 配下の配布物（wheel / sdist）を PYPI_TOKEN で PyPI へアップロードするための手順を規定化したスキル。
• pypi-version-probeCompact tool verifying data state.
• pyramid-principleStructure a recommendation top-down — Barbara Minto's Pyramid Principle. Outputs a single-sentence top-line an
• pyrecrawlWeb scraping + research toolkit for AI agents: scrape, crawl, monitor URLs with anti-bot bypass.
• pysam-genomic-filesRead/write SAM/BAM/CRAM, VCF/BCF, FASTA/FASTQ. Region queries, pileup, variant filtering, read groups. Python
• pysam-sam-bam-summary-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• pyscn-mcpPython code analysis for AI agents: complexity, dead code, clones, coupling, and a health score.
• pyscrappyWeb-scraping toolkit with 22 tools for structured web data as JSON for AI agents.
• pyside6-engineerDesign, implement, refactor, and review PySide6 desktop applications. Use for Qt for Python widgets, signals a
• pyside6-mcpPlaywright-style MCP to inspect, control, and debug PySide6 desktop GUIs.
• pytest-code-reviewReviews pytest test code for async patterns, fixtures, parametrize, and mocking. Use when reviewing test_*.py
• pytest-patternsPytest testing patterns, anti-patterns, and quality rules
• pythComplete guide for Pyth Network - decentralized oracle providing real-time price feeds for DeFi. Covers price
• pyth-oracleIntegrate Pyth oracle prices into a Sui Move package. Use when the user mentions Pyth or wants price oracles o
• pythia-oracle-mcpEvery smart contract deserves intelligence, not just data. On-chain indicators via Chainlink.
• pythonInstall the right AI skills for your project stack in one command
• python-313-modern-syntaxPython 3.13 modern syntax and typing reference. Use this skill when answering questions about or applying Pyth
• python-anti-patternsUse this skill when reviewing Python code for common anti-patterns to avoid. Use as a checklist when reviewing
• python-api-docsRender Python docstrings into a browsable, published API reference with Sphinx, autodoc, napoleon, and MyST.
• python-appservice-deployDeploy Python (Flask/Django/FastAPI) code to Azure App Service Linux. WHEN: \"Flask App Service\", \"Django Ap
• python-architectCreates high-level Python architecture with protocols, test stubs, and module structure. Use when designing Py
• python-async-patternsPython asyncio patterns for concurrent programming. Triggers on: asyncio, async, await, coroutine, gather, sem
• python-background-jobsPython background job patterns including task queues, workers, and event-driven architecture. Use when impleme
• python-best-practicePython 开发最佳实践，涵盖项目结构、类型提示、异步编程、FastAPI/Django、pytest 测试模式
• python-best-practicesPython development best practices including PEP 8 style guidelines, type hints, docstring conventions, and com
• python-cli-patternsCLI application patterns for Python. Triggers on: cli, command line, typer, click, argparse, terminal, rich, c
• python-codeMake sure to ALWAYS use this skill when working with python code! Help designing, structuring, and maintaining
• python-code-fixerUse this skill when applying fixes to Python 3 code review findings from REVIEW.md. Covers reading source file
• python-code-reviewReviews Python code for type safety, async patterns, error handling, and common mistakes. Use when reviewing .
• python-code-stylePython code style, linting, formatting, naming conventions, and documentation standards. Use when writing new
• python-coderImplements Python code following PEP 8, type hints, and project conventions. Use when implementing features de
• python-configurationPython configuration management via environment variables and typed settings. Use when externalizing config, s
• python-conventionsTeam-specific Python conventions — credential management with dotenv, API client rules, LLM response parsing,
• python-csv-generationGenerate structured CSV files from Python data using the csv module for tabular data export.
• python-database-patternsSQLAlchemy and database patterns for Python. Triggers on: sqlalchemy, database, orm, migration, alembic, async
• python-debugpyDebug Python: pdb REPL + debugpy remote (DAP).
• python-design-patternsPython design patterns including KISS, Separation of Concerns, Single Responsibility, and composition over inh
• python-devOpinionated Python development setup with uv, ty, ruff, pytest, and just. Use when creating a new Python proje
• python-developmentProfessional Python development skill covering modern Python 3.10+, FastAPI, Django, Flask, async programming,
• python-docs-mcp-serverThe canonical Python stdlib oracle for AI coding agents — always free, always MIT, token-frugal.
• python-docxProgrammatically read, modify, and create Word documents (.docx) with python-docx library
• python-engineerPython后端工程师技能。当需要实现Python后端功能、异步REST API、数据处理管道、AI/ML推理服务或Web爬虫工作流时使用。关键词：Python、FastAPI、Pydantic、SQLAlchemy、a
• python-envFast Python environment management with uv (10-100x faster than pip). Triggers on: uv, venv, pip, pyproject, p
• python-error-handlingPython error handling patterns including input validation, exception hierarchies, and partial failure handling
• python-expertUse for Python code changes, FastAPI/Django/Flask services, packaging, typing, async, pytest, data scripts, de
• python-expert-best-practices-code-reviewPython best practices for writing production-grade code. This skill should be used when writing, reviewing, or
• python-fastapiPython FastAPI development with uv package manager, modular project structure, SQLAlchemy ORM, and production-
• python-fastapi-patternsFastAPI web framework patterns. Triggers on: fastapi, api endpoint, dependency injection, pydantic model, open
• python-guideUse when writing or editing Python 3.12+ for APIs, data processing, scripting, or tooling. Triggers on `.py` f
• python-guidelinesThis skill should be used when writing, reviewing, or refactoring Python code. Covers code integration, idioma
• python-idioms写 Python 时使用。地道、安全、可维护的 Python 写法。
• python-logging-best-practicesPython logging with loguru, structlog, and orjson. TRIGGERS - loguru, structlog, structured logging
• python-lspSemantic Python code queries via a stdio LSP client driving pyright-langserver. Provides binding-resolved go-t
• python-mcp-server-generatorGenerate a complete MCP server project in Python with tools, resources, and proper configuration
• python-memory-safe-scriptsMemory-safe Python script patterns for long-running processes under systemd MemoryMax constraints. Covers allo
• python-modern-design-patternsModern Python design patterns, typing idioms, and language mechanics. Use whenever the user asks about or is w
• python-observabilityPython observability patterns including structured logging, metrics, and distributed tracing. Use when adding
• python-observability-patternsObservability patterns for Python applications. Triggers on: logging, metrics, tracing, opentelemetry, prometh
• python-packagingCreate distributable Python packages with proper project structure, setup.py/pyproject.toml, and publishing to
• python-patternsPythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintaina
• python-performance-optimizationProfile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when de
• python-pillow-graphicsCreate technical graphics, diagrams, and posters using Python Pillow library with precise color control and ty
• python-pipelinePython data processing pipelines with modular architecture. Use when building content processing workflows, im
• python-proUse when building Python 3.11+ applications requiring type safety, async programming, or robust error handling
• python-projectDebug Python code in this project.
• python-project-setupSets up Python projects with modern tooling including pyproject.toml, linting with ruff, formatting, type chec
• python-project-structurePython project organization, module architecture, and public API design.
• python-pypi-package-builderEnd-to-end skill for building, testing, linting, versioning, and publishing a production-grade Python library
• python-pytest-patternspytest testing patterns for Python. Triggers on: pytest, fixture, mark, parametrize, mock, conftest, test cove
• python-quality-gatePython quality checks: ruff, pytest, mypy, bandit in deterministic order.
• python-refactorPerform AST-aware Python refactors using the rope library. Handles parameter annotations, import management, r
• python-resiliencePython resilience patterns including automatic retries, exponential backoff, timeouts, and fault-tolerant deco
• python-resource-managementPython resource management with context managers, cleanup patterns, and streaming. Use when managing connectio
• python-rope-refactorRope-first workflow for ANY mechanical Python rename/move (functions/methods/classes/variables/modules/package
• python-servicesPython patterns for CLI tools, async parallelism, and backend services. Use when building CLI apps, async/para
• python-styleValidate Python code against style and architectural conventions
• python-testingPython testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requ
• python-testing-patternsImplement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use wh
• python-tkiconAdd a custom icon to any Python Tkinter application. Use this skill whenever the user is working on a Python/T
• python-type-safetyPython type safety with type hints, generics, protocols, and strict type checking.
• python-typing-patternsPython type hints and type safety patterns. Triggers on: type hints, typing, TypeVar, Generic, Protocol, mypy,
• python-visualsPython visual creation and matplotlib/seaborn patterns for PBIR reports. Automatically invoke when the user me
• pytorchPyTorch deep learning framework with dynamic graphs. Use for neural networks.
• pytorch-fsdpExpert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precisi
• pytorch-fsdp2Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload conf
• pytorch-lightningHigh-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callback
• pytorch-loss-implementationImplement loss functions in PyTorch with proper tensor operations.
• pytorch-patternsPyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pi
• pytorch-preference-optimizationPyTorch patterns for implementing preference optimization losses (DPO, SimPO, etc.) for LLM training.
• pyunbrowserChrome-free MCP web access for agents with low-token page maps and browser escalation hints.
• pyvene-interventionsProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative interventio
• pywencai同花顺问财数据查询：使用中文自然语言查询A股、指数、基金、港美股、可转债等市场数据；当用户需要通过自然语言从问财获取选股、财务、资金流、技术指标等数据时使用。
• pywry-orientationWhen to reach for PyWry MCP tools (native webview rendering, Plotly, TradingView, AgGrid, chat) instead of wri
• pyxelUse when creating, modifying, debugging, or verifying a game made with Pyxel or a requested retro Python game
• pyxel-mcpMCP server for Pyxel, a retro game engine for Python
• pyzoteroInteract with Zotero reference management libraries using the pyzotero Python client. Retrieve, create, update
• qFast SQLite-based vault search using FTS5 full-text search index
• q-buildingUse this skill when the user is setting up a workflow, an agent, a research process, or a plan they want to ac
• q-claude-setupUse this skill when the user wants to configure Claude to know them deeply and improve itself over time. Activ
• q-decision-makingUse this skill when the user needs to choose between options, evaluate a path forward, or make a high stakes d
• q-researchUse this skill when the user wants an idea, plan, or position pressure tested before committing to it. Activat
• q-thinkingUse this skill when the user needs to understand a problem before solving it. Activate for complex situations
• q-thinking-chainUse this skill when the user needs to think deeply, stress test an idea, make an important decision, challenge
• qaInteractively draw pipe diagrams for lattice surgery.
• qa-agentAutomated quality assurance agent that validates project deliverables (docx, xlsx, pptx) against skill specifi
• qa-agent-claudeTurn Claude Code into an autonomous QA agent — an explore, generate, run, heal, report loop that maps the app,
• qa-agent-testingBuilds QA harnesses for LLM agents with evals, trace grading, red-team packs, and regression workflows. Use wh
• qa-api-testing-contractsAPI contract testing across REST, GraphQL, gRPC, AsyncAPI, webhooks, and workflow contracts. Use when you need