直近の内容を markdown 形式で保存
Handle vulnerability reports with coordinated disclosure, timely patches, and clear communication.
Integrate Excel (.xlsx) data into Playwright codegen scripts by replacing hardcoded values with config-driven lookups, loading data with polars, and validating every step with Playwright CLI plus the Playwright CLI skill. Use for Playwright automation updates that require Excel-backed data, config.yaml centralization, or CLI-based validation/reporting.
Generate weekly KPI report (3PL/WMS) from shipments/events
Design and build LLM-powered projects from ideation through deployment. Use when starting new agent projects, choosing between LLM and traditional approaches, or structuring batch processing pipelines.
Improve test coverage in the OpenAI Agents Python repository: run `make coverage`, inspect coverage artifacts, identify low-coverage files, propose high-impact tests, and confirm with the user before writing tests.
[51] EXECUTE. Commitment to maximum quality work with 150% coverage. Use when you need the highest quality output for critical tasks, complex problems, important decisions, or when standard work isn't enough. Triggers on "maximum quality", "150% mode", "full quality", "critical task", or when you explicitly want AI to work at its best.
Génère des contrats API cohérents entre Frontend (Next.js) et Backend (NestJS) avec types synchronisés, validation standardisée et error handling uniforme. À utiliser lors de la création d'APIs, DTOs, types frontend/backend, ou quand l'utilisateur mentionne "API", "DTO", "types", "contract", "validation", "frontend-backend", "synchronisation".
Comprehensive security and quality code review agent that checks for OWASP vulnerabilities, GDPR compliance, accessibility standards, and code quality issues.
Display the list of files in the current directory with optional detailed information.
Document architectural decisions with context and consequences.
"Add a new Convex query to get all reviews for a specific user, ordered by most recent first, including venue name and average rating for each venue"
Claude Skills are a set of Markdown files that live in your `.claude` folder (or that you can upload in your Claude web/desktop). They are automatically loaded by Claude when it thinks they are appropriate for the current task.
Build Claude Code extensions - skills, agents, hooks, plugins, marketplaces, slash commands. Use when creating Claude Code components, building new skills, writing agents, creating hooks, making plugins, setting up marketplaces, writing slash commands, fixing extension configurations, or troubleshooting Claude Code extensions. Includes builder agents for autonomous creation. Not for looking up docs - use claude-code-docs-reference for that.
Run in-session task loops via the codex-taskloop-plugin MCP server and stop hook.
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
Format recipes using Cooklang markup syntax. Use when creating, editing, or converting recipes to Cooklang format. Covers ingredients, equipment, timers, metadata, and file organization.
Create semantik plugins (connectors, embeddings, chunkers, rerankers, extractors, agents). Use when developing plugins, creating new integrations, or asking about plugin patterns, protocols, or testing.
Build and optimize MongoDB queries, aggregation pipelines, and CRUD operations. Use when the user asks to query data, filter documents, join collections, aggregate results, update documents, or work with MongoDB data in any way.
**Status:** READY