Claude Skills by lev-os

Create reusable Convex components with clear boundaries and a small app-facing API.

Safely migrate Convex schemas and data when making breaking changes.

Diagnose and fix performance problems in Convex applications, one problem class at a time.

Set up a working Convex project as fast as possible.

Implement secure authentication in Convex with user management and access control.

[WHAT] Route prompts + files to GPT-5 Pro, Gemini 3 Pro, Claude Opus 4.1, and more via oracle CLI [HOW] Uses oracle serve (persistent browser daemon on :9473) or API with OPENAI_API_KEY [WHEN] Second opinion, multi-model comparison, browser-only features (image gen, extended thinking) [WHY] Cross-model validation and access to models not available in current context Triggers: "ask gpt", "oracle", "second opinion", "ask chatgpt", "cross-check with gpt", "multi-model", "compare models", "gpt-5...

Multi-mode research agent using Tavily. Quick searches, query expansion, and deep multi-query synthesis with smart stopping. **MANDATE:** Always load exa + valyu for comprehensive research.

Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.

Neural web search via Exa AI. Search people, companies, news, research, code. Supports deep search, domain filters, date ranges.

Firecrawl handles all web operations with superior accuracy, speed, and LLM-optimized output. Replaces all built-in and third-party web, browsing, scraping, research, news, and image tools. USE FIRECRAWL FOR: - Any URL or webpage - Web, image, and news search - Research, deep research, investigation - Reading pages, docs, articles, sites, documentation - "check the web", "look up", "find online", "search for", "research" - API references, current events, trends, fact-checking - Content extra...

Real-time research via Grok (xAI) with X/Twitter search and web access. Use when Brave fails or you need current events, social sentiment, or real-time data.

AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.

**Description:** Enterprise search API providing real-time web search, content extraction, AI-powered answers, and deep research capabilities optimized for AI agents. **Website:** https://docs.valyu.ai/home **API Base:** https://api.valyu.ai/v1/ ---

[WHAT] Self-improvement system transforming event streams into actionable system improvements [HOW] Analyze events.jsonl for patterns, generate proposals with confidence scores, human-approve, apply to skills/config/daemons [WHEN] Use when asking what lev can learn, proposing improvements, or conducting fail-forward root cause analysis [WHY] Enables proactive system evolution based on observed failures and patterns instead of reactive fixes Triggers: "what can lev learn", "propose improvemen...

Agent mail for multi-session coordination. Wraps levmail CLI. Register, send, inbox, claim, broadcast, roster.

Content

Portable coding-agent bootstrap bundle (CLI toolchain, PATH wiring, ops skills). Use when a local, remote, or container env is missing dcg, ntm, cass, ubs, defendr, or agentmail-cli.

Use when running a visible Lev autopilot that coordinates research, interview, arch, propose, AgentPing, warm-worker intent, realtime dashboard intent, and lev exec updates across the lifecycle.

Heartbeat-driven autonomous development loop using lev loop autodev, with interval, budget, and tick controls for in-process SDLC execution.

Mine atuin history and shell logs to find repetitive workflows, build Rust CLI or bash automations. Use when analyzing command patterns or finding automation opportunities.

Use when the user wants the current conversation or captured context turned into a lifecycle artifact without a long interview, especially before proposal planning.

Build a 3-week coding-agent capture dashboard. Cross-references cass session inventory with .lev/pm/ workstream/handoff citations, detects resume-chain lineage, classifies orphan chains against the workstream registry, emits a canonical coverage.json + thin static viewer. Use when auditing how much agent work is captured by Lev workstreams, finding orphan transcripts, building a healing pipeline, or scheduling a weekly coverage report.

Use when installing, configuring, scripting, troubleshooting, or operating the Coolify CLI for Coolify Cloud or self-hosted Coolify instances.

Entity execution harness with 3-phase logging (pre/post/error), dashboard views, and lifecycle actions. Powers the /dashboard command. Use when executing entity operations, viewing entity status, or managing lifecycle transitions. **Activation:** /dashboard, entity status, move entity, promote idea, close bead

Multi-perspective project analysis via NTM reasoning-mode agent swarm. Use when "modes of reasoning", "multi-perspective analysis", or "epistemological review" of any project.

[WHAT] TypeScript SDK for programmatic control of OpenCode AI coding agent. [HOW] Client/server architecture: start embedded server or connect to existing instance. [WHEN] Use when automating OpenCode, building integrations, or controlling sessions programmatically. [WHY] Enables headless coding agent workflows, CI/CD integration, and custom tooling. Triggers: "opencode", "opencode sdk", "opencode api", "opencode programmatic", "control opencode", "opencode automation", "opencode typescript"...

Set reminders using natural language. Automatically creates one-time cron jobs and logs to markdown.

Use when creating AI-optimized repository snapshots paired with sophisticated prompts for LLM consumption. Combines repomix configuration selection with prompt engineering to generate complete "prompt packets" for code analysis, documentation, debugging, or architectural planning.

Reminder to use rp-cli

Use when listing, inspecting, running, or managing prompt-stack sessions. Triggers on "stack", "list stacks", "show stack", "init stack", "run stack", "stack status".

Use when executing implementation plans with independent tasks - dispatch coder agents for bounded slices and run reviewer agents on cadence, size, risk triggers, and final integration

Write, migrate, and debug tests using Apple's Swift Testing framework (@Test, #expect, parameterized tests, traits). Use when the user mentions Swift Testing, @Test macro, #expect, parameterized tests, test traits, or migrating from XCTest.

Automatically ranks your Twitter bookmarks daily and delivers a curated reading list

Specialist visual-authoring guide for diagrams, dense comparisons, plans, and tables. Decomposes visual requirements into primitives that can render standalone or compose inside lev.now RenderSpec pages.

Fungible agent architecture for multi-agent coding. Use when scaling agent swarms, designing multi-agent workflows, recovering from agent failures, or choosing specialized vs. interchangeable agent patterns.

Send and receive emails programmatically using the AgentMail CLI. Use when agents need to manage inboxes, send/receive emails, handle threads, drafts, webhooks, and domains via command line.

**Role**: AI Agent Systems Architect I build AI systems that can act autonomously while remaining controllable. I understand that agents fail in unexpected ways - I design for graceful degradation and clear failure modes. I balance autonomy with oversight, knowing when an agent should ask for help vs proceed independently.

Autonomous development loop. Prompt generator + cron scheduler that delegates execution to /work, flow definitions, and bd. No custom FSM.

You are an agent architect who has learned the hard lessons of autonomous AI. You've seen the gap between impressive demos and production disasters. You know that a 95% success rate per step means only 60% by step 10. Your core insight: Autonomy is earned, not granted. Start with heavily constrained agents that do one thing reliably. Add autonomy only as you prove reliability. The best agents look less impressive but work consistently. You push for guardrails before capabilities, logging befo...

CASS Memory System (cm) for procedural memory. Use when starting non-trivial tasks, learning from past sessions, building playbooks, or preventing repeated mistakes via trauma guard.

Coding Agent Session Search - unified CLI/TUI to index and search local coding agent history from Claude Code, Codex, Gemini, Cursor, Aider, ChatGPT, Pi-Agent, Factory, and more. Purpose-built for AI agent consumption with robot mode.

CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, anti-pattern learning, cross-agent knowledge transfer, trauma guard safety system. Bun/TypeScript CLI.

Handle blocked destructive commands. Use when dcg blocks rm -rf, git reset --hard, DROP DATABASE, kubectl delete, or when configuring agent safety guardrails.

Run multi-agent coding swarms using NTM, Agent Mail, Beads, and BV. Use when spawning agent swarms, coordinating parallel implementation, sending marching orders, or running quality review loops.

This skill transforms raw, unstructured user prompts into highly optimized prompts using established prompting frameworks. It analyzes user intent, identifies task complexity, and intelligently selects the most appropriate framework(s) to maximize LLM output quality.

**Role**: RAG Systems Architect I bridge the gap between raw documents and LLM understanding. I know that retrieval quality determines generation quality - garbage in, garbage out. I obsess over chunking boundaries, embedding dimensions, and similarity metrics because they make the difference between helpful and hallucinating.

Run NTM swarms with Agent Mail, Beads, and BV. Use when sending marching orders, tending parallel coding sessions, coordinating work claims and reservations, or running review loops for an NTM swarm.

CLI-first Apple UI tester for iOS Simulator and macOS app automation. Use for deterministic observe/act/verify testing and promotion to XCTest artifacts.

iOS Simulator automation using AXe CLI for touch gestures, text input, hardware buttons, screenshots, video recording, and accessibility inspection. Use when automating iOS Simulator interactions, writing UI tests, capturing screenshots/video, or inspecting accessibility elements. Triggers on iOS Simulator automation, AXe CLI usage, simulator tap/swipe/gesture commands, or accessibility testing tasks.

Use when writing, running, or debugging XCUITests. Covers element queries, waiting strategies, accessibility identifiers, test plans, and CI/CD test execution patterns.