productivity▌

Micro-prompt that reinforces interactive programming workflows with live REPL access. \n \n Designed for Clojure with Copilot integration via Backseat Driver, but adaptable to any system with a live REPL \n Reminds the agent to use the REPL as the source of truth for exploration and system modification \n Encourages clear communication about evaluated code and preference for structural editing tools over text replacement \n Includes guidance on maintaining a todo list during interactive developm

Detect code smells, security vulnerabilities, anomalies, and trends across codebases using regex, AST analysis, and statistical methods. \n \n Identifies problematic patterns including long functions, duplicate code, magic numbers, empty catch blocks, and TODO/FIXME markers \n Scans for security risks such as SQL injection, hard-coded secrets, dangerous function usage (eval, innerHTML), and credential exposure patterns \n Performs statistical anomaly detection using Z-score and IQR methods to fl

soul-self-evolution \n 对 SOUL.md 或 docs/reference/SOUL.md 进行受控更新： \n \n 只允许改动可演进段 \n 记录 checkpoint \n 支持一键回滚 \n \n 调用 \n python3 skills/soul-self-evolution/run.py apply --path docs/reference/SOUL.md --changes '[{\"section\":\"## Collaboration Preferences\",\"content\":\"- Keep updates concise.\"}]' \n python3 skills/soul-self-evolution/run.py list_checkpoints\n

Establish AI agent environment policies, security guardrails, and team configuration standards. \n \n Configure project description files as AI manuals with tech stack, coding standards, and DO NOT rules; use /init for auto-generation from codebase analysis \n Set up security hooks to block dangerous commands (rm -rf, sudo, curl | sh) and auto-approve only safe operations via PreToolUse and PostToolUse events \n Define skills, slash commands, and plugins with token efficiency in mind; skills loa

Guide the user through diagnosing and fixing application-side query patterns that cause excessive data transfer (egress) from their Postgres database. Most high egress bills come from the application fetching more data than it uses.

Persistent memory and context management for AI agents across sessions, repositories, and dates. \n \n Load project background before work, search prior conclusions during tasks, and store decisions afterward using slash commands ( /opencontext-context , /opencontext-search , /opencontext-iterate ) \n Supports keyword, vector, and hybrid search modes with optional semantic indexing via embeddings API \n Integrates with multi-agent workflows (Claude, Gemini, Codex) through MCP tools for knowledge

Comprehensive evaluation framework for designing, building, and monitoring AI agent performance across coding, conversational, research, and computer-use agents. \n \n Covers three grader types (code-based, model-based, human) with trade-offs and best practices for each agent category \n Provides an 8-step roadmap from initial task creation through production monitoring, including environment isolation, outcome-focused grading, and saturation detection \n Includes benchmarks for major agent type

ちょっと、いいか。

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Complete authentication and authorization system with JWT, OAuth, and role-based access control. \n \n Covers five core authentication methods: JWT tokens, session management, OAuth 2.0, password hashing (bcrypt/argon2), and multi-factor authentication support \n Includes step-by-step implementation for user registration, login, token refresh, and logout endpoints with database schema design \n Provides authentication middleware for protecting API routes and role-based authorization for permissi