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 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 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 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 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 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

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

Collect a testimonial (name, rating, text, email) and publish it to testimonials.html

Monitors task execution for skill improvement opportunities. Use this skill during ANY multi-step task, agentic workflow, or substantive work session where the agent is using tools and producing deliverables. It captures patterns, user corrections, workflow insights, and methodology worth preserving as reusable skills. Also triggers during post-task feedback discussions and when the user explicitly mentions skill observations, improvements, the observation log, skill taxonomy, or asks the agent to watch for skill opportunities. Also known as "One Skill to Rule Them All" — trigger on this phrase too. IMPORTANT: this skill should be invoked at the start of every task-oriented session — if you are about to use tools to produce deliverables, invoke this skill first. For reliable activation, pair this description with a CLAUDE.md instruction or harness-level session-start hook (see Recommended Activation Setup) — description-level matching alone is not enforceable.

Generate Kubernetes Helm charts backed by Canonical Ubuntu OCI images (rocks). Use when creating a new Helm chart from scratch for a rock; achieving feature parity with an upstream chart (Bitnami, ArtifactHub, GitHub); adding features to an existing chart. Trigger phrases are "generate helm chart", "create helm chart based on upstream chart", "helm chart for app", "feature parity with upstream", "add feature to chart", "scaffold chart", "ubuntu rock helm", "rock-backed chart". Produces chart scaffolding, values.yaml with image.digest, PSS-Restricted security defaults, Pebble-wired probes, tests, and README.md.

Build distinctive, high-quality frontend interfaces. Use when users request web components, pages, landing pages, portfolios, or creative applications. Generates production-ready code with creative typography, layered color systems, fluid motion choreography, and inventive layouts. Eliminates generic AI aesthetics. Say "Prime" for maximum quality.

Fast headless browser for QA testing and site dogfooding. (gstack)

Design a loss function and harness for a long-running /goal optimization run (loss-function development, LFD). Use when the user wants to set up an autonomous optimization loop, distill a product from public artifacts, turn a spec into an optimization target, or asks to design a /goal. Observes the existing environment, interrogates the task, ingests or generates the spec, builds a blinded eval, generates and verifies the harness, red-teams the target for cheats, and emits goal.md ready to launch. Re-invoke in patch mode when a running loop cheated and the loss function needs patching.

Run a prepare → review → revise pass over an agent-written user-facing output (report, status update, strategy doc, review finding, handoff, recommendation) before it is finalized. Builds a short communications brief, reviews the draft against it and against named agent-writing failure modes (assumed context, numbered references without meaning, retained rejected ideas, leaked process history, buried recommendation), then revises or flags residual risk.