Claude Skills

Coordinates Serena MCP knowledge graph operations for Shannon Framework. Enforces standardized entity naming (shannon/* namespace), relation creation patterns, search protocols, and observation management. Prevents orphaned entities, naming chaos, and broken context lineage. Use when: storing specs/waves/goals/checkpoints, querying Shannon history, managing knowledge graph structure, ensuring cross-wave context preservation.

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).

Builds high-impact landing page narratives that turn visitors into customers. Use this skill to construct a complete messaging framework that connects with your audience on an emotional level and logically guides them toward a single, desired action.

Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically with Shannon quantitative analysis, executes tasks in complexity-based batches, runs validation gates, reports for review between batches

Autonomous task execution with library discovery, 3-tier validation, and atomic git commits. Integrates with Shannon CLI Python modules for platform-specific execution. Invokes /shannon:wave for code generation, validates outputs functionally, commits only validated changes. Use when: user requests autonomous execution, wants library-first development, needs validated commits.

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests with quantitative reliability tracking

Use when creating or developing ideas before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning with Shannon quantitative validation, alternative exploration, and incremental validation. Don't use during clear mechanical processes

Provides best practices and guidelines for creating Claude Code skills. Use when you need help with skill structure, naming conventions, writing effective descriptions, progressive disclosure patterns, and evaluation methods.

Create GitHub pull requests with standardized title format and draft status. Use when the user requests to create a PR. This skill uses gh command to create PRs with specific title format '[base-branch] type: description' and generates concise bullet-point descriptions from git changes.

Creates isolated git worktree environments for parallel development. Fetches latest from default branch, creates worktree in .git-worktrees/, copies .env and .serena files. Branch '/' is converted to '-'. Use when starting new features or switching context.

Get the current Neovim context as JSON (cursor position, current file, visual selection and diagnostics) to help answer questions about code at the current cursor position, visual selections and diagnostics. Use when users ask about "this line", "current file", "selection" or need context about their Neovim editor state.

Agentic workflow for cloning websites with pixel-perfect fidelity using specialized sub-agents. Use when the user wants to clone/copy/replicate a website, create a landing page based on an existing site, or needs to extract and recreate a website's design. Includes orchestration via slash command, four specialized sub-agents (screenshotter, extractor, cloner, qa-reviewer), and outputs React components with Tailwind CSS and motion animations.

Use when implementing features with test-driven development, writing tests before code, building domain-rich business logic, or following hexagonal architecture

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.

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.

Inter-agent communication for tmux sessions. Send and receive messages between AI agents.

Extract and persist learnings from the current session. This skill should be used when the user wants Claude to analyze the conversation and capture insights, patterns, preferences, or knowledge discovered during work. Triggers on requests like "learn from this session", "what did we learn", or "capture insights".