Si
Superintelligence router — composes /superintelligence reasoning with swarm execution only when verb intent demands it. Defaults to reasoning-only to prevent runaway swarm cost. Triggers — /si <ask>, "think deeply about X", "analyze X with full depth", or any ask requiring multi-perspective + first-principles + contrarian framing.
Install
/plugin marketplace add frankxai/claude-skills-libraryThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add frankxai/claude-skills-library --skill sigit clone --depth 1 https://github.com/frankxai/claude-skills-library.git /tmp/claude-skills-library
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills-library/free-skills/si ~/.claude/skills/siPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# /si — Superintelligence Router Route ANY ask through this 3-step protocol: ## Step 1 — Classify intent Parse $ARGUMENTS for verb. Match against these classes: ### Execution verbs (route to: reasoning + swarm) build, ship, deploy, fix, elevate, create, refactor, migrate, scaffold, wire, sync, audit-and-fix, redesign, rebuild, generate, render ### Reasoning verbs (route to: reasoning only) think, plan, compare, analyze, should, what if, why, evaluate, audit, research, explore, decide ### Bare topic (no verb) Route to: reasoning only, then ASK "Should I dispatch a swarm to execute this?" ## Step 2 — Invoke /superintelligence Always. Pass $ARGUMENTS as the topic. Capture the reasoning output. Cost: ~5K input + ~3K output tokens, ~$0.05. Cheap enough to always run. ## Step 3 — Route based on Step 1 classification ### If execution intent After /superintelligence returns, dispatch the appropriate swarm: - "build / scaffold / create / generate" → BUILD lane (e.g., /v BUILD or feature-dev or frankx-website-builder agent) - "deploy / ship / sync" → DEPLOY lane (e.g., /v DEPLOY) - "fix / refactor / migrate" → FIX lane - "elevate / redesign / rebuild" → ELEVATE lane (e.g., /v ELEVATE) - "audit-and-fix" → /v ELEVATE - Multi-domain ambiguity → ask which lane ### If reasoning intent Return /superintelligence verdict directly. Surface a one-line "Want to execute this?" footer. ### If bare topic
Details
- Skill name
si- Repository
- frankxai/claude-skills-library
- Path
free-skills/si/SKILL.md- License
- MIT
- Repo updated
- 18 November 2026
FAQ
What does the Si skill do?
Superintelligence router — composes /superintelligence reasoning with swarm execution only when verb intent demands it. Defaults to reasoning-only to prevent runaway swarm cost. Triggers — /si <ask>, "think deeply about X", "analyze X with full depth", or any ask requiring multi-perspective + first-principles + contrarian framing.
How do I install the Si skill?
Claude Code plugin: /plugin marketplace add frankxai/claude-skills-library. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Si popular?
It lives in frankxai/claude-skills-library, which has 48 GitHub stars and 6 forks.
Related skills
Acos Meta
48frankxai/claude-skills-library
ACOS self-description and configuration skill. Documents how ACOS works, how to extend it, how to add new skills/commands/agents, and how to debug the hook system. Use when building new ACOS capabilities, understanding the system architecture, or onboarding to ACOS for the first time.
Acos Visual Gen
48frankxai/claude-skills-library
Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.
Agent Harness Construction
48frankxai/claude-skills-library
Shape an agent's tools, observations, and recovery without adding a second coordinator. Use when defining a tool, a skill, a hook, or a worktree lane.
Worker Benchmarks
48frankxai/claude-skills-library
Run comprehensive worker-system benchmarks and performance analysis. Use when benchmarking worker throughput/latency, comparing worker configurations, or diagnosing worker performance.
Greek Philosopher
48frankxai/claude-skills-library
Channel ancient wisdom through Socratic questioning, Stoic principles, and philosophical inquiry to examine life's deepest questions with poetic eloquence and timeless insight. Use when examining a life decision, seeking Stoic perspective on adversity, or wanting Socratic questioning of an assumption.
Adaptic
45pjt222/agent-almanac
Master skill composing the 5-step synoptic cycle for panoramic synthesis across multiple domains. Orchestrates meditate, expand-awareness, observe, awareness, integrate-gestalt, and express-insight into a coherent process that produces unified understanding rather than sequential compromise. Use when a problem genuinely spans 3+ domains and the interactions between domains matter more than depth in any one, when sequential analysis feels like compromise rather than integration, or before major architectural decisions affecting multiple stakeholders.
Browse the most popular Claude skills, all other skills, or write your own with the skills generator.