Claude Skills

Use at development completion - guides branch integration with Shannon 3-tier validation (0.00-1.00 readiness score), MCP merge pattern analysis, and Serena risk assessment

Automatically detects Datadog resource mentions (URLs, service queries, natural language) and intelligently fetches condensed context via datadog-analyzer subagent when needed for the conversation (plugin:schovi@schovi-workflows)

This skill should be used when creating distinctive, production-grade frontend interfaces with high design quality. It applies when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.

Context-aware task execution with Serena MCP backend. First time: Explores project, saves to Serena, runs spec if complex, executes waves. Returning: Loads from Serena (<1s), detects changes, executes with cached context. Intelligently decides when to research, when to spec, when to prime. One catch-all intelligent execution command. Use when: User wants task executed in any project (new or existing).

Use when you want to validate changes before committing, or when you need to check all React contribution requirements.

Load when retrofitting framework documentation to existing code. Supports creating specs and decisions from implementations, enabling gradual framework adoption for existing projects.

Commits code changes with appropriate git commit strategy. Adopts Squash (default), new commit, or Interactive Rebase based on context, and creates messages following Conventional Commits format. Use when implementation is complete or user requests a commit.

Draft sales or investor emails: cold outreach, follow-up, intro request, update. Use when drafting outreach to investors or sales prospects.

Restore previous session state from Serena MCP checkpoints. Retrieves checkpoint by ID or auto-selects most recent, deserializes context, restores command/skill/phase/wave state. Use when: resuming after context loss, continuing previous session, recovering from interruption.

Stakeholder briefs for board, investors, or exec team: status, decisions, asks. Use when creating a brief for board, investors, or exec team.

PocketFlow framework for building LLM applications with graph-based abstractions, design patterns, and agentic coding workflows

Split large changes into logical commits by semantic meaning. Use when handling large features or refactors that should be split into focused commits.

Use when interacting with Google Chat - send messages, list messages, or get message details. Requires agentio CLI with a configured Google Chat profile (webhook or OAuth).

Use PROACTIVELY when creating research reports, experiment writeups, technical whitepapers, or empirical study documentation. Orchestrates the complete benchmark report pipeline with structure, diagrams, hi-res PNG capture, and PDF export. Provides working scripts, CSS templates, and complete command sequences for publication-quality AI/ML benchmark reports. Not for slides, blog posts, or simple README files.

Use PROACTIVELY when creating Model Context Protocol servers for connecting AI applications to external data sources, tools, and workflows. Generates production-ready MCP servers with TypeScript/Python SDKs, configuration templates, and Claude Desktop integration. Includes testing workflow with MCP Inspector. Not for modifying existing MCP servers or non-MCP integrations.

Comprehensive Next.js v16 development with Cache Components, feature-based architecture, and best practices. Use for ANY Next.js 16 task to know - (1) Project structure with features folder pattern, (2) Where to fetch data with use cache, (3) Server vs Client component decisions, (4) One file per query/type/schema/hook pattern, (5) Cache invalidation with updateTag/revalidateTag, (6) Proper component organization within features. Apply to all Next.js 16 development tasks.

Analyzes git commits and changes within a timeframe or commit range, providing structured summaries for code review, retrospectives, work logs, or session documentation.