Find the perfect capability for your agent.
Facilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises after architectural work (new files, schema changes, refactors). Use when completing features, making design decisions, or when user asks to understand code better. Supports the user's stated goal of understanding design choices as learning opportunities.
This skill should be used when the user asks to "roast my code", "review code brutally", "find code sins", "what's wrong with my code", "shame my code", "critique this code", "find antipatterns", "code quality roast", or wants entertaining but actionable code criticism with severity-ranked fixes. Delivers brutally honest roasts with file:line citations and redemption paths.
Interactive project learning coach via interview-style Q&A. Reads codebase and docs, dynamically generates interview questions per knowledge domain and sub-topic, conducts up to 4 follow-up rounds, scores answers, provides learning guidance with code/doc references, and persists progress. 10 domains × 3-5 sub-topics = 45 knowledge points for comprehensive interview coverage. Use when user says '学习项目', '了解项目', '检验项目', '项目学习', '面试准备', 'learn project', 'study project', 'review project', 'interview prep', 'knowledge check', or wants to understand/master the project through guided Q&A.
21 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.
Expertise in LLVM-based static analysis including dataflow analysis, pointer analysis, taint tracking, and program verification. Use this skill when implementing security scanners, bug finders, code quality tools, or performing program analysis research.
Core engineering philosophies for the Magi Attention codebase. Use when writing, reviewing, or modifying any code in this project. Covers config consistency, static-analysis-friendly readability, and test coverage requirements. Any deviation from these philosophies must be strictly commented with justification.
CHARLS (China Health and Retirement Longitudinal Study) database-specific knowledge for reproducing published papers. Use when reproducing or analyzing papers that use CHARLS data, including variable mapping from harmonized to raw questionnaire items, cognitive function scoring (episodic memory, mental status, TICS), CESD-10 depression screening, social isolation index construction, and chronic disease coding. Also use for any CHARLS data cleaning, variable construction, or cohort selection task.
Heartbeat-based health monitoring for background workers with configurable thresholds, rolling duration windows, failure rate calculation, and stuck job detection.
Implement soft delete pattern for data recovery and audit trails. Covers filtering, restoration, and permanent deletion workflows.
Collect-then-batch pattern for database operations achieving 30-40% throughput improvement. Includes graceful fallback to sequential processing when batch operations fail.
Exactly-once processing semantics with distributed coordination for file-based data pipelines. Atomic file claiming, status tracking, and automatic retry with in-memory fallback.
Daily compression of time-series data with merge logic for multiple pipeline runs, structured aggregation for dashboards, and storage estimation for capacity planning.
Build resilient systems that degrade gracefully under failure. Implement fallbacks, feature flags, and partial responses when dependencies fail.
Production-safe error handling that logs full details server-side while exposing only generic, safe messages to users. Prevents information leakage of database strings, file paths, stack traces, and API keys.
Server-authoritative tick system for multiplayer games with lag compensation, anti-cheat validation, and deterministic physics. Prevents speed hacks and teleports while keeping gameplay fair for high-latency players.
Implement a feature flag system for gradual rollouts, A/B testing, and kill switches. Use when you need to control feature availability without deployments, test features with specific users, or implement percentage-based rollouts.
Multi-backend storage layer with automatic failover between Redis, database, and memory backends. Includes circuit breakers per backend and health-aware routing for high availability.
Implement Supabase authentication with SSR support. Email/password auth with automatic session management via cookies. Includes login, signup, email confirmation, and user profiles.
Comprehensive design token system for typography, colors, and theming with WCAG AA compliance, TypeScript types, and framework integration (CSS-in-JS, Tailwind, CSS Variables).
