Investigate a codebase question using an isolated subagent. Use when you need to read many files without bloating the main context.

Find, install, and configure an MCP server for a specific service. Handles discovery, installation, and verification.

name: memorylane

Start the multi-AI pipeline with a given request. Guides through plan -> review -> implement -> review workflow.

Generate mobile app icons using OpenAI or Gemini image generation. Use when creating iOS icons, Android icons, app icons, or generating icon assets.

Plan experiments or development tasks using past knowledge. Adapts behavior based on project domain (research, unsloth, cuda) by reading registry.json. Triggers on <advise> or questions like "What should we try next?"

Ask whether to proceed with refactoring after architecture mapping.

Pflege die Extraktion von ATS-Kriterien aus CVs; verwenden bei Anpassungen an Kontakt-, Erfahrung- oder Bildungsextraktion.

Query the hosted Taiga API at taiga.ant.dev for job results, passrates, transcripts, and run evaluations. Use when user asks about Taiga jobs, problem scores, eval results, or needs to submit/check jobs.

Audit and improve CLAUDE.md files. Use when rules aren't working, context is bloated, or after learning a lesson that should become a rule.

Discover and install useful Claude Code plugins for your project. Recommends based on your tech stack.

Plan a new feature before writing code. Explores the codebase, creates a structured plan with verification criteria, and only implements after approval.

Use when you need a detailed execution trace of a Python script using sys.monitoring, including logging every operation with include/exclude event controls.

This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency.

Update Nix flake inputs in persops. Use when asked to update flake.lock/inputs, update AI inputs (codex-cli-nix, claude-code-nix, llm-agents), or run full `nix flake update`, then verify with `nix flake check` and commit the update-only changes.

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

AI thinking partner for strategy and planning. Reads the current work state, analyzes progress, and helps you plan the next phase while the worker instance builds. Triggered by "think ahead".

The Block Collection and Block Party are repositories for existing AEM blocks, build tools, code snippets, integration patterns, plugins, and more. Use this skill anytime you are developing something and want to find a reference to use as a starting point.

Track and evaluate AI predictions over time to assess accuracy. Use when reviewing past predictions to determine if they came true, failed, or remain uncertain.

**Version:** 0.1.0