Recall project-first and global-supplement ChatCrystal memories before substantive implementation, refactoring, migration, configuration, investigation, or optimization work.
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth…
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI.
Build FastAPI backend for OpenAI ChatKit with SSE streaming, conversation persistence, and AI agent integration.
Have a fast, conversational analysis with the AWS DevOps Agent. Use for cost optimization, architecture review, topology mapping, knowledge / runbook discovery, security audits,…
Manual QA testing of Allegro Lister product listings end-to-end. Use when testing upload flow, AI-generated content, photo generation, or full pipeline.
Did I actually verify this, or am I assuming? - Challenges technical decisions against behavioral patterns before proceeding. Be direct. Be challenging. Point out BS.
Detects MSBuild projects with conflicting OutputPath or IntermediateOutputPath. Only activate in MSBuild/.NET build context.
Check for pending Codex (GitHub AI) feedback on current branch's PR. Use to review and address AI suggestions before merge. This is the rate-limiting step before merge.
Validates an in-progress PR or feature branch of dart_skills_lint against known downstream ecosystem consumers.
Verifies required tools (Quarto, uv, Python, R, Stata, TeX) and Jupyter kernels are installed. Use when setting up or troubleshooting.
Verify the development environment is ready for Director Mode: claude CLI, git, python3, jq, project runtime, and installed skills/agents/hooks.
Validate the examples/test-repo fixture submodule and drive the built CLI against it end to end -- resolution schemes, groups, hooks, guidance precedence, executables, MCP presets…
Run a benchmark-driven posture check on Kubernetes nodes and control planes before an audit, upgrade, or hardening sprint starts.
Slack で自分へのメンションを確認する。「メンション確認」「Slackメンション」「自分へのメンション」「@mention を見せて」などで起動。Pythonスクリプト `slack_message.py mentions` を使用。
Analyze performance-related HTML issues on web pages. Use when users ask to check page performance, audit resource loading, verify lazy loading, check preload hints, or analyze…
Review past bug-fix postmortem reports stored under `.agents/postmortem` and surface likely relevant historical fixes.
Use BEFORE starting any non-trivial coding task in an existing project — feature work, refactors, bugfixes, or "look at this codebase" requests.
Validates development tool installations across Python, Node.js, Java, Go, Rust, C/C++, Git, and system utilities. Use when verifying environments or troubleshooting dependencies.
TypeScriptの書き方をレビューするときに利用します。「TypeScriptをチェックして」「tsの書き方を確認して」「check-ts-writingを実行して」で実行できます。
Deploy validation and reality-testing consciousness mode. Use when need to find edge cases, test assumptions, catch fatal flaws before they're expensive.
Check Python logging levels and patterns for correctness. Focus on identifying wrong severity levels and missing exception handling. Use when reviewing code quality.
Ensures code quality through comprehensive checks including TDD practices, lint/test/build validation, and prevention of common mistakes.
Expertise in generating domain-specific quality checklists for specifications. Activates when user discusses quality validation or requirement testing.
Configure Playwright test suites with Checkly including playwright.config.ts integration, multiple projects, and full test suite deployment.
An ASE skill built on Checkmate, the open source self-hosted monitoring platform for uptime, incidents, response times, and infrastructure visibility.
Checkout flow with cart, shipping, Stripe/PayPal payments, and order completion. Use when modifying checkout, debugging payment issues, or implementing checkout features.
Reference for reusable checkout UI components. Use when working with SignInForm, AddressSelector, PaymentMethodSelector, or composing checkout step views.
Scans IaC files with Bridgecrew Checkov for policy violations across Terraform, CloudFormation, Kubernetes, and Dockerfile configurations.
Rate-limit-resilient pipeline with checkpoint/resume for long multi-phase sessions. Saves progress to .claude/pipeline-state.json after each phase.
Standard Operating Procedure for /fix-ci phase. Fix CI/deployment blockers after PR creation.
Query ChEMBL via Python SDK. Search compounds by structure/properties, retrieve bioactivity (IC50, Ki, EC50), find target inhibitors, run SAR, access drug mechanism/indication…
Use when you have a GNPS mass spectral molecular network (in graphml or cytoscape format) and want to enrich its nodes with chemical class information derived from GNPS public…
Use when targeting Chemical Engineering Journal or deciding whether an applied chemical-engineering / functional-materials manuscript fits this venue.
Develop, fix, and profile Cherry Studio in a tracked Electron instance. Use for everyday implementation, UI and interaction work, bug fixing, runtime debugging, DevTools…
Audit existing code, config, or rules before deleting or replacing them. Trigger on "delete this", "remove this", "clean up", "why is this here", "looks unused", "can we drop",…
Writing and debugging Chezmoi .tmpl files using Go text/template — lookPath, stat, joinPath, OS branching, the .chezmoi namespace, and template data from .chezmoidata.
Master Chicago TDD (state-based testing). Create tests that verify observable behavior with real collaborators. Use chicago-tdd-tools 1.4.0 AAA pattern.
Chief Data Officer advisory for startups: AI training data rights and consent provenance, data product strategy (warehouse vs lakehouse vs mesh, build-vs-buy), B2B…
Drive IT strategy, digital transformation, vendor management, architecture decisions, and technology governance.
Implements strict data minimization and retention limits for children''s personal data under GDPR Art. 5(1)(c), Recital 38, UK AADC Standard 8, and COPPA Section 312.7.
Guide AI to write Chinese novels and fiction with structured character creation, plot architecture (起承转合), dialog writing, scene description, and genre-specific techniques for 玄幻,…
Free disk space on macOS by clearing regenerable caches (npm, pip, brew, Xcode, Docker, etc.). Safe to run anytime — only removes data apps will rebuild.
Festlandchina Wirtschaftsverkehr: Critical Infrastructure Risk. Geführter Spezialskill mit Quellenlogik, Prüfroutine, Red-Team-Fragen und verwertbarem Output.
Festlandchina Wirtschaftsverkehr: Platform Ecommerce China. Geführter Spezialskill mit Quellenlogik, Prüfroutine, Red-Team-Fragen und verwertbarem Output.
Nudge-based choice architecture for 3-option selection UI — smart default vs active choice, outcome mapping, channel factors, RECAP, operational transparency with source…
重庆工程造价材料信息采集,从 `http://www.cqsgczjxx.org/Pages/CQZJW/priceInformation.aspx` 抓取数据,按区县跟踪,同步至 Elasticsearch。覆盖 35 个区县。
Choose an F# web application framework before implementation, comparing ASP.NET Core Minimal APIs, Giraffe, Falco, Oxpecker, and Saturn by application shape, composition model,…
Choose the right application transport or real-time protocol before implementation. Use when Codex needs to route work across plain HTTP routes, HTTP/2, HTTP/3, QUIC, WebSocket,…
Choose a supported chat, calling, business-messaging, or collaboration integration shape before implementation.
Choose the right Python project shape before implementation, including uv project versus workspace layout, package, CLI, FastAPI, FastMCP, testing, packaging, tooling, and…
Choose SwiftSyntax, compiler, SourceKit, SourceKitten, IndexStoreDB, or SourceKit-LSP by information and project model.
Choose the right Zoom architecture for a use case. Use when deciding between REST API, Webhooks, WebSockets, Meeting SDK, Video SDK, Zoom Apps SDK, Zoom MCP, Phone, Contact…
Use when deciding which pgdbm pattern to use (standalone, dual-mode library, or shared pool) - provides decision tree based on deployment context without requiring doc exploration
Automates visual regression testing for Storybook components using cloud-based snapshot comparison. Use when setting up visual testing, catching UI regressions, or reviewing…
Connect to and control Google Chrome browser using agent-browser with CDP (Chrome DevTools Protocol).
Browser automation with two integrations - Chrome DevTools MCP (always available, performance tracing) and Claude-in-Chrome extension (authenticated sessions, GIF recording).
Automates Chrome browser workflows for testing web apps, debugging with console/network logs, extracting data, filling forms, and interacting with authenticated web applications…
How to use Chrome DevTools MCP for browser debugging. Use when you need to inspect pages, take screenshots, debug UI issues, or verify visual changes.
Lightweight Chromium DevTools automation via the bundled browser-tools.ts CLI (Puppeteer connect). Use when you need to launch a Chromium-based browser with a remote-debugging…