Agent skills for Claude Code

Guide the user through a structured specification process: define the goal, specify exactly what to build (and what NOT to build), and…

AI & LLM Systems Architect - Design RAG pipelines, vector search, semantic caching, evals, and tool-calling guardrails.

Software Architect - Make evidence-based system design decisions, document trade-offs and ADRs, and define modular, reliable…

Ambiguity Resolver - Detect, prioritize, and close specification ambiguity without inventing requirements.

Content Architect - Heading Structure, Readability, Multimodal, Fact-density.

Systematic Debugger - Reproduce, isolate, prove root causes, and produce a scoped fix plan.

Technical Planner - Convert approved specifications into an evidence-backed implementation plan.

Logic Challenger (Red Team) - Ask critical questions, find edge cases.

Roadmap Strategist - Maintain evidence-backed milestones, dependencies, risks, and phase transitions.

Security Auditor - Perform evidence-backed application, dependency, secret, and threat-model audits without silently modifying code.

Technical SEO Lead - Optimize Meta Tags, Sitemap, Core Web Vitals, Schema.org.

UI/UX Architect - Definition of Design System Anti-Slop, UI Components, Spacing, Typography, Responsive Patterns.

Implementation Validator - Decide whether implementation satisfies spec, governance, build, runtime, and evidence gates.

Track all URLs fetched during SpecStory AI coding sessions.

Organize SpecStory AI coding sessions in .specstory/history into year/month folders.

Analyze your SpecStory AI coding sessions in .specstory/history for yak shaving - when your initial goal got derailed into rabbit holes.

Bidirectional conversion between SpecWeave increments and Azure DevOps work items.

Expert speech-language pathologist specializing in AI-powered speech therapy, phoneme analysis, articulation visualization, voice…

Generates realistic talking head videos from text scripts using brand characters and Higgsfield AI models.

Bring declared user journeys within pre-declared performance budgets, proven by measurement.

Use when drafting, revising, or diagnosing an LLM system prompt, message layout, tool description, tool schema, or structured-output…