Skill Claude Code needs its repo
Performance profiling principles. Measurement, analysis, and optimization techniques.
AI-Tadpole-OS a local-first "development platform" a Lily Pad to jump from for running autonomous AI agent teams on your own hardware. Coordinate parallel workflows, maintain full data privacy, and oversee every decision — no cloud required.
This repository also configures its own agents. See what AI-TadPole-OS tells them →
Skill Claude Code needs its repo
Performance profiling principles. Measurement, analysis, and optimization techniques.
Skill Claude Code
Zero-Trust PII sanitizer that redacts customer credit cards, phone numbers, SSNs, and addresses before data is sent to cloud LLM providers.
Skill Claude Code needs its repo
Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.
Skill Claude Code
PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling.
Skill Claude Code
Builds minimal, low-fidelity executable spikes or stub components to resolve "how should it look/behave" questions before production coding.
Skill Claude Code
Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying.
Skill Claude Code needs its repo
Red team tactics principles based on MITRE ATT&CK v19.2 and MITRE ATLAS v2026.07. Stealth, defense impairment, and agentic swarm attack phases.
Skill Claude Code
Executes isolated research and investigation subagents on throwaway git branches to prevent cluttering main working state.
Skill Claude Code
Master Rust 1.75+ with modern async patterns, advanced type system features, and production-ready systems programming. Expert in Tokio, Axum, and zero-cost abstractions.
Skill Claude Code
SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles.
Skill Claude Code
Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands.
Skill Claude Code
Reduce complexity of over-engineered code. Identify unnecessary abstractions, remove dead code, flatten deep nesting, and simplify logic while preserving behavior.
Skill Claude Code
Auto-create new skills from repetitive workflows. When you notice yourself doing the same multi-step process repeatedly, extract it into a reusable SKILL.md that any agent can use.
Skill Claude Code
Parses and validates messy SMB data exports (CSV, Excel, Quickbooks PDFs, legacy SQL) into clean JSON-Schema & SQLite state for AI Digital Twins.
Skill Claude Code
4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.
Skill Claude Code
Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture.
Skill Claude Code needs its repo
Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.
Skill Claude Code needs its repo
Testing patterns and principles. Unit, integration, mocking strategies.
Skill Claude Code
Converts informal conversation context or brainstorms into formal, published specification files under docs/specs/.
Skill Claude Code
Prove code works by running it, not just checking it exists. Verification through execution rather than inspection. Use after writing or modifying code to ensure it actually functions correctly.
Skill Claude Code needs its repo
Advanced vulnerability analysis principles. OWASP Agentic Top 10 (2026), MITRE ATLAS, Supply Chain Security, attack surface mapping, risk prioritization.
Skill Claude Code
Plan large multi-session initiatives wrapped in fog as a map of linked decision tickets, resolving them sequentially without context degradation.
Skill Claude Code
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Skill Claude Code needs its repo
Web application testing principles. E2E, Playwright, deep audit strategies.
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: