The official public registry of cognitives — reusable AI instructions for skills, agents, prompts, workflows, and tools. Works across Claude, OpenAI, Cursor, Windsurf, Copilot, and Gemini. Install via npx skills add.
This repository also configures its own agents. See what skills-registry tells them →
Skill Claude Code
Multi-domain codebase audit: security, contracts, patterns, observability, and ops. Invoke as /audit [domain?] where domain is one of: security | contracts | patterns | observability | ops | all (default). Use whenever the user asks to audit or review a codebase for issues, wants a security review, asks what's wrong…
Skill Claude Code
Analyzes code modules and generates structured technical reports with architecture diagrams. Trigger: When the user asks to analyze, explain, or document a module, file, or codebase section.
Skill Claude Code
Rigorous dead code audit for any module, folder, or file in any programming language. Detects orphan files never imported anywhere, classes/functions/ methods declared but never called, constructor parameters received but never consumed, unused imports/requires, private fields with no references, and commented-out…
Skill Claude Code
Investment decision engine that fetches real-time market data and produces actionable stock analysis with probability-weighted scenarios, expected value calculations, and capital allocation guidance. ALWAYS use this skill when the user's message involves ANY of these — even if they don't explicitly ask for "analysis"…
Skill Claude Code
Analyze and improve prompts using Claude's official prompting best practices. Use this skill whenever the user wants to improve, refine, review, or optimize a prompt — whether it's a system prompt, a user prompt, an API prompt, or instructions for an AI agent. Also trigger when the user shares a raw prompt and asks…
Skill Claude Code
Creates new AI agent skills following the SynapSync spec with enhanced templates and guidelines. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.
Skill Claude Code
Unified Obsidian vault operations: sync documents to vault, read notes for context, search knowledge, and validate markdown standards. Filesystem-based, no MCP required. Trigger: When user wants to read from or write to Obsidian vault.
Skill Claude Code
Elite tech CEO strategist that thinks like Musk, Bezos, Altman, Huang, and Thiel combined. Generates billion-dollar-scale strategic initiatives, product visions, and growth plays using first principles, 7 Powers, flywheels, and exponential thinking. Use this skill whenever the user discusses product strategy, business…
Skill Claude Code
Per-task implementation micro-cycle: Analyze -- Develop -- Certify -- Correct -- Close. Use when executing individual tasks within a sprint, feature, or any code change.
Skill Claude Code
Session memory for AI agents — load context at the start, save sessions at the end, evolve knowledge across sessions. Like a professional's notebook: open before work, write a summary when done, persist between sessions. Trigger: When starting a session and need to recover context, or ending a session and want to save…
Skill Claude Code
Registers new cognitives (skills, agents, prompts, workflows, tools) into the SynapSync Registry with proper structure, manifest, and registry index. Trigger: When the user says "GUARDA", "REGISTRA", "AGREGA" followed by a cognitive type and name, or asks to save/register/add a cognitive to the registry.
Skill Claude Code
Orchestrates the Kyro sprint flow on Pi by directing specialized workers. The orchestrator never executes the sprint or runs QA itself. Trigger: When the user asks to run the active Kyro sprint, execute the Kyro flow, launch Kyro workers, continue a Kyro sprint, or start Kyro QA after execution. Spanish: ejecutar el…
Skill Claude Code
Read-only conversational copilot for manual QA testers. Investigates git history, source code, and Kyro artifacts (scopes, sprints, specs, debt, plans) to explain what changed, what could break, and how to test it — with every claim labeled by its evidence. The QA keeps full authority; this skill never certifies…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: