Score any AI model on the DeepSWE coding-agent benchmark via the OpenRouter API. Use when the user wants an independent, reproducible coding-agent eval — "run DeepSWE", "benchmark this model on DeepSWE", "score model X on the coding benchmark", "test a model via OpenRouter on DeepSWE", or to verify vendor-reported coding scores. Covers setup, the OpenRouter wiring for mini-swe-agent, single-task / subset / full 113-task runs, and leaderboard submission.

Teach the user a new skill or concept, within this workspace.

Register a custom or variant model (e.g. an OpenRouter ":nitro" / ":floor" / ":exacto" slug) in the Pi Agent so it can be set as the global default. Use when Pi silently falls back to a different model (e.g. moonshotai/kimi-k2.6) after setting defaultModel, or when a model slug isn't in Pi's bundled list. Triggers on "Pi reset my model", "Pi won't use this model", "add a model to Pi", "Pi default keeps reverting".

Gauge the user's technical + product knowledge through 7 adaptive questions, log verbatim answers with honest ratings, and grow a learning plan from the gaps found. Use when the user says "level up", "level-up session", "quiz me", "gauge my knowledge", or wants a new assessment round. Differentiator: this finds and maps gaps; the `teach` skill delivers lessons on them.

How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, anti-patterns, testing, security. Read this whenever a skill (Claude Skill, Agent Skill, SKILL.md) is being created, edited, reviewed, or debugged. Use when the user says "create a skill", "new skill", "update this skill", "improve a skill", "why isn't my skill triggering", or anything else involving authoring or editing SKILL.md files.

Use when the user wants to manage his VPS servers and the AI agents running inside them — connecting, deploying, monitoring, restarting, and operating remote hosts and their agents. Triggers on VPS, server management, remote host, SSH into server, manage my servers, agents on the server.

Provision a hardened SELECT-only Postgres role so AI agents can safely read a production database. Works on Supabase and any Postgres. Use when the user wants agents to query prod data, says "read-only role", "safe prod DB access for agents", or is tired of running SQL by hand for agents. Differentiator: this skill CREATES the role and wiring; day-to-day querying belongs in a project-local skill.

Launch OpenAI Codex CLI as a subagent (ChatGPT subscription auth, no API key). Use when delegating a self-contained coding task to Codex from another agent — parallel implementation work, a second opinion, or an independent verification pass.

Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run every N minutes", "schedule a task", "run on a loop", "heartbeat". Covers external clocks (Claude Code, Codex, Pi) vs Hermes' built-in scheduler.

Use when the user (or a sibling skill via --wt flag) wants to spin up an isolated git worktree for a task — wraps the worktrunk `wt` CLI when present, falls back to native `git worktree`, switches the Bash session cwd into the new worktree, auto-applies docker isolation when profile present (skip with --no-isolate), and emits a machine-readable result envelope

Use when the user asks for parallel team-style execution of multiple features in one project — orchestrates a team lead + N dev workers, one feature per worktree, each gated on x-qa E2E tests, with blocker escalation to human via SendMessage. Hard requires `plugin.omc` (TeamCreate/SendMessage primitives) and `.x-skills/x-qa/profile.json` (E2E gate).

Use when the user wants to evaluate x-skill alignment and improve a skill based on real session usage — searches Claude Code session history automatically

Use when user asks for non-Claude model dispatch (GPT-5, Gemini, Codex, o3) or invokes OMO agents (oracle, explore, librarian, multimodal-looker) — bridges Claude Code to OpenCode CLI, handles agent catalog, model routing flags, and prompt-block construction

Use BEFORE implementation when AI has produced a plan, spec, design doc, PRD, or code-bearing proposal and you want a senior-engineer architect-review pass — walks the user through the decisions, tradeoffs, assumptions, blind spots, shape mismatches, and future-debt AI silently embedded. Surfaces "what AI did, what it picked over alternatives, what it took on, and what gets harder later" one item at a time with confirm / modify / reject / skip gates. Hard-blocks code-level details so the human stays at architectural direction.

Use when the user wants a complex input (file, function, directory, PRD, plan, spec, URL, pasted prose, or vague feature name) explained step by step in a comprehension-gated walkthrough — produces a persistent .x-guide/<slug>/GUIDE.md with full TOC and walks the user one part at a time, supports resume across sessions

Use when a long-running skill needs to check "am I done?" — runs the canonical completion cascade with mandatory fallback to prevent silent success claims

Use when the user wants to vendor or track an upstream GitHub repo as a research reference inside the current project — adds, updates, lists, or removes `research/<owner>/<repo>` git submodules pinned to the latest stable release (not main/HEAD). Invoked for upstream code reference, dependency mirroring, or research material management.

Use when the user asks to build, implement, fix, or execute a plan — detects context (existing plan, new feature, bug, quick task, visual input) and routes through brainstorming, planning, debugging, or execution workflows

Use when the user wants to apply a visual design system to a project, references a specific brand's style (Linear-like, Stripe-like, Claude-like), asks for a DESIGN.md, or describes aesthetic intent (warm editorial, dark minimal, stark futuristic) for AI UI generation

Direct Google Gemini bridge via the Antigravity (agy) CLI — uses Google Ultra subscription (no API key), opt-in Google Search grounding (via `--grounded`), and gemini-3.x models without the OpenCode layer