traylinx

Unified LLM proxy for AI agents. Route all model requests through http://localhost:18080/v1. Provides FREE access to Gemini CLI, Claude CLI, Codex, and Vibe via your existing subscriptions. Includes Intelligent Auto-Routing (Cortex) for autonomous model…

Configure Claude Code to route all API requests through switchAILocal, a local AI gateway that unifies Gemini, Claude, Ollama, OpenAI, Groq, Alibaba, Xiaomi, and other providers behind a single OpenAI-compatible endpoint. Run this skill to discover available…

Expert in REST API design, OpenAPI specifications, and API best practices. Has tools to validate specs and generate OpenAPI from Go structs.

Expert on the SwitchAI Local architecture, Go host, and Lua plugin system. Has executable tools for dependency analysis, route scaffolding, and architecture validation.

Expert in Testing Methodologies (Go testing, Vitest, Playwright, TDD). Has tools for coverage analysis and test generation.

Specialized instructions for writing and optimizing Jevvel Labs blog posts. Focuses on SEO, engaging introductions, and the unique 'cyber-brutalist' aesthetic.

Expert in systematic debugging, root cause analysis, profiling, and performance troubleshooting. Use when stuck on bugs, investigating errors, or optimizing performance.

Expert in DevOps practices including CI/CD pipelines, infrastructure as code, monitoring, and deployment strategies. Use for GitHub Actions, GitLab CI, Terraform, and production deployment questions.

Ask every configured validator the same question and return N independent answers — one per model. No sprint framing, no phases, no verdict parsing. Use for any multi-perspective query: 'what do these 5 CLIs think about X?', 'compare how 3 models solve this…

Compare two files across every validator. Each model picks which file is better against explicit criteria (--criteria flag). Tally the picks; print the winner. Use for A/B review, before/after diff evaluation, migration decisions, bake-offs. Criteria is…

Run an Agent-Order-style council deliberation on a decision artifact. Six built-in templates: ADR, PRD, RFC, build-vs-buy, migration-plan, incident-review. The 7-stage protocol — independent positions, anonymized critique, revision, synthesis, rubric review,…

Execute a sprint phase-by-phase with validator-in-the-loop retry. For each phase: implement (code, deliverables, research, etc.) → AI validators review → retry on NEEDS_FIX → advance on PASS. Works with any domain (engineering, business, research).

Run a declarative GRAPH workflow where AI agents negotiate autonomously — no human gates. A flow is a DOT graph: nodes are agent turns, ensemble reviews, shell verify-steps, or judge/routers; edges carry conditions and loops. Each node dispatches into lope's…

Run a sprint with zero-human swarm orchestration. First select implementation agents and escalation agents, then Lope executes phases without further human input. Use when the user says implement the whole sprint, stay out of the loop, use Claude/OpenCode or…

Draft a sprint doc via multi-round negotiation with AI validators. Lope sends your plan to other AI CLIs (Claude, Gemini, OpenCode, Codex, Mistral Vibe, Aider, Ollama, Goose, llama.cpp, Open Interpreter, Copilot, Amazon Q, or any HTTP API) for independent…

Read stdin as the prompt, fan out to every configured validator, print per-model answers. The composable shell verb — anything that produces text on stdout can feed lope in a pipeline. Per-validator isolation by default: one timeout doesn't kill the run. Pass…

Open protocol for AI-readable, candidate-owned professional profiles. Install the CLI, generate Skill Cards from CVs, search jobs, evaluate fit scores, and let AI agents discover and negotiate with candidates on their own terms.

Draft a tailored CV and cover letter for a specific role, grounded entirely in a candidate's Scoutica Skill Card. Runs the deterministic fit scorer as a gate first and refuses to draft when the candidate's own rules reject the role. Use when a candidate asks…

Create a Scoutica Skill Card from candidate documents. Use when asked to generate a professional profile, build a skill card, or convert a CV/resume into a machine-readable format. Reads documents from a folder and outputs 4 structured files (profile.json,…

Build a plugin, SDK, or integration that consumes the Scoutica Protocol. Use when asked to connect Scoutica with a job board, ATS, website, or any external application. Provides the API contract, data schemas, and integration patterns.

Evaluate a candidate's Scoutica Skill Card against a job description or role requirements. Use when asked to match a candidate to a role, score a profile, check if an opportunity fits, or pre-screen applicants. Returns a structured fit report with scores and…

Extend the Scoutica Protocol with new schemas, entity types, rule templates, or CLI commands. Use when asked to add new features, modify the card format, add support for new entity types (agents, teams, robots), or contribute to the protocol specification.

Alice Developer — AI-readable professional profile with automated opportunity filtering

How agents inside a tytus pod (or any S3 client — Mac, Linux, remote box) read and write files in a shared bucket on the droplet so they can collaborate with the user's Mac and with other pods. Covers credential discovery, the S3 endpoint, the three common…

Diagnose + fix problems with a garagetytus install. Symptom- driven decision tree covering the install path, bootstrap path, daemon lifecycle, port collisions, keychain issues, integration failures (boto3 403/400, rclone), and observability gaps. Always reach…

First-run bootstrap of an installed garagetytus daemon — start the service, run admin-API layout assignment, provision the `s3-service` keypair, and verify the daemon is healthy. Idempotent end-to-end. Use after `garagetytus install` and before any bucket /…

Day-to-day operations on a bootstrapped garagetytus daemon — start / stop / restart / status, bucket lifecycle, grant lifecycle (mint / revoke / expire / deny-all), reading metrics + watchdog state, and recovery from unclean shutdown. The catch-all for "the…

Install the garagetytus standalone S3 daemon on a fresh Mac or Linux host end-to-end. Detects the platform, walks the prereq chain (Garage upstream binary, Homebrew on Mac, musl download + SHA verify on Linux), runs `garagetytus install`, and post-verifies…

Use `2md` by Traylinx — a data-extraction API that converts any URL, file, or website into clean, AI-ready Markdown. Supports instant URL-prepend, batch, crawl, sitemap, file conversion, and agent skill generation.

Routing guide for accessing 2md reference documentation.

A powerful tool to scrape, render, and convert any URL or entire website into clean Markdown using headless Chrome (Puppeteer). Use when you need to read a webpage, crawl documentation sites, extract text from JavaScript-heavy apps (React, Next.js, Vue),…

Use `tytus` by Traylinx — a CLI, tray, and TytusOS desktop for private AI pods, OpenAI-compatible gateway access, pod lifecycle, Files, channels, terminal, and MCP integration.