AI & ML

tdimino Bundle

Discover, message, and coordinate AI coding agents (Claude Code, Codex CLI) running on the same machine via a shared Unix socket broker backed by SQLite. Supports cross-session task delegation, peer summaries, and session lifecycle management. Triggers on 'peer agents', 'cross-session communication', 'message Codex', 'inter-agent messaging', 'coordinate agents'.

tdimino Bundle

This skill should be used to spawn specialized OpenAI Codex CLI subagents for code review, debugging, architecture analysis, security audits, refactoring, documentation, comparative evidence adjudication, and autonomous /goal runs via AGENTS.md persona injection. Supports GPT-6-Astra across low, medium, high, xhigh, max, and ultra reasoning with default or priority service tiers, plus GPT-5.6 and GPT-5.5 models. Triggers on 'delegate to Codex', 'Codex Astra', 'Astra subagent', 'Codex subagent', 'code review agent', 'security audit', 'refactor with Codex', 'goal run', 'autonomous goal', 'have Codex weigh this'.

tianzecn Skill

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

abzhaw Skill

Operate, debug, and extend local MCP servers (bridge, future services) using mcporter + Node tooling.

abzhaw Skill

Auth patterns, rate limiting, input validation, CORS, HTTPS. Use when securing Julia's backend API, bridge, or any HTTP endpoint.

abzhaw Bundle

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

abzhaw Skill

Nest.js framework expert specializing in module architecture, dependency injection, middleware, guards, interceptors, testing with Jest/Supertest, TypeORM/Mongoose integration, and Passport.js auth...

abzhaw Skill

Cross-system diagnostics and troubleshooting for the juliaz_agents multi-agent system. Trigger when Raphael reports something is broken, not working, or behaving unexpectedly — messages not arriving, Julia not responding, bridge errors, orchestrator crashes, rate limits, silent failures, queue issues, or any 'why isn't X working' question. Also trigger for: 'debug', 'broken', 'not working', 'error', 'Julia isn't responding', 'messages stuck', 'bridge down', 'check logs', 'what went wrong', or any troubleshooting request. If something in the multi-agent system is misbehaving, this is the skill to reach for.

abzhaw Skill

Role-based access, allowlists, Telegram pairing security. Use when securing Julia's communication channels or implementing authorization for multi-user scenarios.

abzhaw Skill

Structured logging, log rotation, PM2 logs, aggregation. Use when setting up consistent logging across Julia's services or debugging runtime issues.

abzhaw Skill

Receiving webhooks, verification, idempotency, event routing. Use when Julia needs to receive events from external services.

abzhaw Skill

Design, create, and update OpenClaw agent manifests in `agents/` (skills, transports, behaviors).

abzhaw Skill

Cron expression design, PM2 cron, LaunchAgent intervals, and scheduling agents reliably. Use when setting up Julia's scheduled agents like ADHD agent, security sentinel, or task manager.

abzhaw Skill

Bash best practices, startup scripts, error handling in shell. Use when writing or debugging Julia's startup scripts, agent loop scripts, or any shell automation.

tianzecn Skill

使用 Skill Seekers MCP 工具生成 Claude AI 技能的完整工作流指南

tianzecn Skill

⚡ PRIMARY TOOL for: 'comprehensive audit', 'deep analysis', 'full codebase review', 'multi-perspective investigation', 'complex questions'. Combines ALL detective perspectives (architect+developer+tester+debugger). Uses Opus model. REPLACES grep/glob entirely. Uses claudemem v0.3.0 AST with ALL commands (map, symbol, callers, callees, context). GREP/FIND/GLOB ARE FORBIDDEN.

tianzecn Skill

Multi-agent code analysis orchestration using claudemem. Share claudemem output across parallel agents. Enables parallel investigation, consensus analysis, and role-based command mapping.

abzhaw Bundle

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login ...

abzhaw Skill

Writing SOUL.md, HEARTBEAT.md, and identity files for Julia's sub-agents. Use when creating a new agent, configuring its personality, or defining its scheduling and escalation rules.

abzhaw Skill

Design reliable, well-documented tools for LLM agents — input schemas, error returns, idempotency, and naming conventions. Use when adding new MCP tools to bridge, cowork-mcp, or the orchestrator.

abzhaw Skill

Security incident handling, escalation, auto-quarantine patterns. Use when Julia's security sentinel detects a critical finding or when designing incident workflows.

abzhaw Skill

macOS LaunchAgent plists, RunAtLoad, scheduling, debugging. Use when configuring auto-start for Julia's services at login or debugging why a service didn't start on boot.

abzhaw Skill

Dependency audits, SAST, credential leak detection, and daily scans. Use when building or running Julia's security sentinel or setting up automated security checks.

abzhaw Skill

YAML task queues, priority, stale detection, weekly summaries. Use when building or extending Julia's TODO system and task-manager agent.

abzhaw Skill

.env files, secrets management, multi-environment configs, and never-commit rules. Use when dealing with API keys, environment variables, or setting up new services in Julia.

abzhaw Skill

Comprehensive JavaScript reference covering 33+ essential concepts every developer should know. From fundamentals like primitives and closures to advanced patterns like async/await and functional p...

abzhaw Skill

JSON persistence, schema validation, migration patterns. Use when working with JSON files in the bridge queue, memory files, or any file-based agent storage.

abzhaw Skill

Parse and validate structured output from LLMs — JSON mode, Zod validation, retry on bad output. Use when any agent needs reliable structured data from an LLM response.

abzhaw Skill

Objective voice, argumentation, abstract writing, IMRaD structure. Use when Julia's thesis agent writes scientifically structured sections for Raphael's thesis.

abzhaw Skill

Vault patterns, .env.secrets, credential rotation, never-commit rules. Use when handling API keys, tokens, or any sensitive credentials in the Julia system.

abzhaw Skill

WebSocket servers, reconnect logic, event-driven messaging. Use when building real-time features in Julia's bridge or dashboard.

avav25 Skill

Use this skill when running pre-release validation, detecting calibration regression, or tuning a skill — to run plugin evaluation tiers (Tier 1 linters and Tier 2 judge-calibration drift smoke) by wrapping the eval/runner.py harness. Tier 1 is free (no LLM); Tier 2 budgets tokens per `eval/config.json`. Tier 3 (full behavioral suites) is planned but not yet shipped — runner returns error code 3 if invoked.

avav25 Bundle

Use this skill when the user asks to analyze, investigate, assess, evaluate, compare, or research a codebase, architecture, system, product, market, or research topic in a structured way — including requests that need explicit scope, framework-driven reasoning, and separated facts/inference/recommendation but do not use the word "analyze" — to run a deep analysis workflow producing traceable scope, evidence, and conclusions. Not for quick one-off lookups or implementation work — this is an investigation-and-conclusions workflow.

avav25 Bundle

Use this skill when reviewing how the plugin behaved across recent runs, after a release to confirm reliability, before filing a plugin bug report, or when planning the next plugin improvement cycle — to collect and analyze past Claude Code session logs for the ai-skills plugin and surface agent, subagent, skill, command, and hook errors, timeouts, unexpected exits, and other anomalies that point at plugin defects. Defaults to the last 7 days of sessions for the current project. Produces an extended Markdown report on disk plus a brief on-screen summary.

abzhaw Skill

German academic style, thesis structure, citation formats, and formal writing conventions. Use when Julia's thesis agent writes or edits German academic content for Raphael's master's thesis.

abzhaw Skill

APA/AMA/Chicago citations, bibliography generation, DOI lookup. Use when Julia's thesis agent needs to format references for Raphael's master's thesis.