Loading...
Loading...
Found 1,323 Skills
[Manual Only] Record project learnings in FORyusuke.md. Structurally append lessons learned, pitfalls, debugging stories, and improvement points obtained during the session. It only works when explicitly called via /teach (it will not be triggered automatically in normal work).
MUST READ before running any ADK evaluation. ADK evaluation methodology — eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failure causes. Use when evaluating agent quality, running adk eval, or debugging eval results. Do NOT use for API code patterns (use adk-cheatsheet), deployment (use adk-deploy-guide), or project scaffolding (use adk-scaffold).
Use when writing E2E tests with Playwright, setting up test infrastructure, debugging flaky browser tests, organizing project structure, or testing REST APIs. Invoke for browser automation, E2E tests, Page Object Model, test flakiness, visual testing, project scaffolding, folder layout, API testing, JSON schema validation.
Expert knowledge for Azure Monitor development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building, debugging, or optimizing Azure Monitor applications. Not for Azure Managed Grafana (use azure-managed-grafana), Azure Network Watcher (use azure-network-watcher), Azure Service Health (use azure-service-health), Azure Defender For Cloud (use azure-defender-for-cloud).
Web automation, debugging, and E2E testing with Playwright. Handles interactive (login, forms, reproduce bugs) and passive modes (network/console capture). Triggers on "e2e test", "browser test", "playwright", "screenshot", "debug UI", "debug frontend", "reproduce bug", "network trace", "console output", "verify fix", "test that", "verify change", "test the flow", "http://localhost", "open browser", "click button", "fill form", "submit form", "check page", "web scraping", "automation script", "headless browser", "browser automation", "selenium alternative", "puppeteer alternative", "page object", "web testing", "UI testing", "frontend testing", "visual regression", "capture network", "intercept requests", "mock API responses". PROACTIVE: Invoke for security verification, UI fix verification, testing forms/dropdowns, or multi-step UI flows. ON SESSION RESUME - check for pending UI verifications.
Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.
Mobile app debugging for iOS, Android, cross-platform frameworks. Use for crashes, memory leaks, performance issues, network problems, or encountering Xcode instruments, Android Profiler, React Native debugger, native bridge errors.
OpenOCD skill for embedded hardware debugging. Use when configuring OpenOCD for JTAG or SWD targets, flashing firmware, connecting GDB to bare-metal targets, setting hardware watchpoints, or using J-Link with OpenOCD. Activates on queries about OpenOCD, JTAG, SWD, GDB remote target, flash programming, hardware breakpoints, J-Link, or connecting GDB to an MCU.
Regular expression expert for crafting, debugging, and explaining patterns
Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and experiment-craft (5-step diagnostic on failure). Use when: user has a planned experiment, needs to reproduce baselines, organize experiment workflow, or systematically validate a method. Do NOT use for debugging a specific experiment failure (use experiment-craft) or designing which experiments to run (use paper-planning).
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory M_I (feasible/unsuccessful directions) and Experimentation Memory M_E (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after idea-tournament), IVE (after experiment failure — classifies failures as implementation vs fundamental), ESE (after experiment success — extracts reusable strategies). Use when: updating memory after completing idea tournaments or experiment pipelines, classifying why a method failed (implementation vs fundamental failure), starting a new research cycle needing prior knowledge, user mentions 'update memory', 'classify failure', 'what worked before', 'research history', 'evolution'. Do NOT use for running experiments (use experiment-pipeline), debugging experiment code (use experiment-craft), or generating ideas (use idea-tournament).
Baidu Maps WebAPI Development Guide. This skill should be applied when writing, reviewing, or debugging code that uses Baidu Maps WebAPI, and is also suitable for scenarios where Baidu Maps API is directly called to obtain results. It covers: map location search, POI retrieval, route planning, suggested departure time, route travel time prediction, real-time traffic conditions, administrative division query, address-coordinate conversion, traffic events along the route, weather query, intelligent recommended pick-up points, etc. It is automatically triggered when users mention departure time, navigation routes, location queries, coordinate conversion, or map-related development requirements.