AI Agent & Automation Workflows

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.

End-to-end workflow for feature requests, enhancements, refactors, and tasks. Covers planning, TDD implementation, verification, integration testing, and PR creation.

Pattern for progressively refining context retrieval to solve the subagent context…

Laravel 12 best practices, design patterns, and coding standards. Use when creating controllers, models, services, middleware, or any PHP backend code in Laravel projects.

Laravel security best practices for authn/authz, validation, CSRF, mass assignment, file uploads, secrets, rate limiting, and secure deployment.

Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.

Verification loop for Laravel projects: env checks, linting, static analysis, tests with coverage, security scans, and deployment readiness.

Persistent cross-session memory for AI agents. Mem0 stores user preferences, past decisions, domain knowledge, and agent learnings across all sessions, all tools, and all users. Complements planning-with-files (task-level memory) with long-term agent intelligence (CRM + personal knowledge base layer). Use when asked to "remember this", "store preference", "mem0", "long-term memory", "user memory", "agent memory", or when building multi-session agents that need to recall past interactions.

Operate and extend NanoClaw v2, ECC's zero-dependency session-aware REPL built on claude -p.

Modern Perl 5.36+ idioms, best practices, and conventions for building robust, maintainable Perl applications.

中文优先:用于Perl安全相关任务,帮助识别、设计、实现或验证对应工作流。English keywords: Comprehensive Perl security covering taint mode, input validation, safe process execution, DBI parameterized queries, web security (XSS/SQLi/CSRF), and perlcritic security policies.

Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.

Example project-specific skill template based on a real production application.

Comprehensive framework for analyzing, creating, and refining prompts for AI systems.

RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.

中文优先:用于正则vsLLM结构化文本相关任务,帮助识别、设计、实现或验证对应工作流。English keywords: Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.

中文优先:用于Swift协议依赖注入测试相关任务,帮助识别、设计、实现或验证对应工作流。English keywords: Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing.

Translate visa application documents (images) to English and create a bilingual PDF with original and…