pro-vi

Create reflection seeds when you notice opportunities in engineering (security, architecture, complexity), product (UX, features), or meta-patterns (workflow, self-improvement). Seeds get expanded later into actionable improvements.

Create reflection seeds when you notice opportunities in engineering (security, architecture, complexity), product (UX, features), or meta-patterns (workflow, self-improvement). Seeds get expanded later into actionable improvements.

Human-participated design iteration loop driven by claude.ai/design via the `designer` MCP. The human is the designer; AI is translation + plumbing. Human states intent, AI reads what exists and relays intent to Claude Design, human tastes the variants Claude produces, AI interprets reactions and iterates. Promotes accepted result with a decision record (a regenerated decision-record.md).

Compose a repo-specific, /goal-ready loop prompt from a primitive vocabulary — loopgen writes the weather, not just the target. Classifies a task to its nearest archetype (frontier / goal / story / greenfield), composes the prompt from primitive values — defaulting to the archetype, diverging where the task demands — and emits with provenance. Also diagnoses a drifting loop. Triggers: '/loopgen', 'derive a loop for X', 'make me an overnight loop', 'close the findings in X', 'fix the bugs by morning', 'push a benchmark with a loop', 'walk the storyboard', 'build out an idea from zero'.

Compose a runnable multi-agent Workflow script from 4 canonical examples; verify before accepting, every reducer emits a decision ledger. Use on '/wfgen', 'compose a workflow', 'fan this out'.

A general best-of-N selection engine wearing a World Cup-style tournament. Any time a task is "mass-produce many candidates and keep the single best" (or the user hands over a field of them), stage 32 teams (8 groups of 4) or 48 teams (12 groups, 2026 format) through a head-to-head round-robin group stage into a single-elimination knockout, judged by taste-calibrated LLM panels, and emit a World Cup-flavored HTML report of the final bracket graph. The "teams" can be anything comparable: essay or copy variants, taglines, names, API or UI designs, prompts, configs, plans, generated code solutions. Essays/prose are one supported profile, not the required shape. This skill should be used when the user wants to bracket a field and crown a winner with real rigor, or whenever a task reduces to "make N variants and pick the best." Triggers: "/worldcup", "run a worldcup", "tournament these", "bracket these 32", "best of N", "mass-produce and pick the best", "stage 48 variants and crown a winner", "group stage then kno

This skill should be used when: (1) user discusses their daily I Ching reading/cast/hexagram and wants deeper exploration, (2) user wants to capture an insight about today's reading to their journal, (3) user asks about derived hexagrams (mirror/綜卦, polarity/錯卦, nuclear/互卦), (4) user wants to review I Ching history or patterns. Triggers: mentions of hexagram names, 'my cast', 'today's reading', 'note this', or requests for iching journal/history.