发现 Skills

A skill that provides detailed explanations of code behavior in Japanese. Used in the following situations: (1) When a user asks "Explain this code" or "Tell me what this does" (2) When a user explicitly invokes "/code-explainer" (3) When a question requests understanding of code

Use this skill when an agent needs web scraping or browser automation through Gologin infrastructure, including Web Unlocker scraping, Cloud Browser sessions, interactive browsing, login flows, snapshots, ref-based clicks, typing, screenshots, and batch page extraction.

Use when developing ALTO itself — editing devenv.nix, hooks/*.py, agents/*.md, or checking Claude Code hook/agent syntax. Reference guide with documentation URLs and patterns.

Fastest route to a deployed live evaluation using a pre-built Truesight template. Use when the user wants a quick start without building judgment configs from scratch.

Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern

miglite is an Lite database schema migration tool by Go

Decompose genetic effects into direct and indirect paths through mediating variables using the mediation R package. Tests whether gene expression, methylation, or other molecular phenotypes mediate the effect of genetic variants on disease. Use when testing whether a molecular phenotype mediates the genotype-to-phenotype relationship.

Shared GPT + classifier inference gateway for persona monitoring tasks. Routes validation and classification through a 4-tier cascade: heuristic → classifier → local GPT → scillm.

Repo-specific Python best practices for agentic coding: Loguru + Typer + uv + pyproject.toml, httpx over requests, functions-first, module docstrings, max 800 LOC per file, and non-mocked sanity tests.

Deterministic coded self-improvement loops for *-lab skills. The agent will NOT do this reliably — loops MUST be in code. Proven pattern from Classifier Lab: data_enrichment.py + training_loop.py.

Create and update architecture diagrams programmatically in UX Lab's Architecture Editor. Agents define pipeline components, connections, and file attachments — the skill generates proper Excalidraw elements and saves via the Express API. Diagrams are visible at localhost:3002/#architecture and stored in ArangoDB for recall.

Create icons for Stream Deck or other uses. Fetches from web, resizes to 72x72, creates white/active states.

Deliberate persona creation for client modeling, expert profiles, and stakeholder mapping. Integrates with /interview for collaborative creation and /ask for knowledge enrichment. Supports Theory of Mind (BDI), voice training, and simulacrum validation.

Generate scene-specific music using ACE-Step 1.5 via a Dockerized FastAPI service. Supports reference audio to maintain thematic continuity across scenes. Integrates with the Federated Taxonomy (HMT) for multi-hop graph traversal in /memory.

Create, iterate, and deploy dynamic Stream Deck button pages. Design context-aware layouts that auto-switch based on active window, voice mode, or running skills. Evaluate layouts against ground truth, self-correct, and store winners as memory-backed templates with taxonomy tags. Triggers: create streamdeck page, design page layout, optimize deck layout.

Dual-backend embedding service for semantic search. Text-only (MiniLM-L6-v2, 384d) and multimodal (Qwen3-VL-Embedding-2B via vLLM, 2048d). Persistent Docker containers with automatic routing by modality.

Episodic Memory Archiver. Stores full conversation transcripts with embeddings and analysis into ArangoDB. Tracks UNRESOLVED sessions for reflection with structured failure episodes (trigger/diagnosis/action/outcome), K≈4 similar-failure retrieval, user behavioral profiling, and federated taxonomy classification.

Self-improving evidence case convergence loop. Runs question banks against /create-evidence-case, diagnoses mismatches, and tracks convergence across cycles.

Live evidence case pipeline viewer with NVIS sentence markup and agent chat well. Shows gates firing, entity grounding, QRA evidence, and verdicts in real-time. Chat well connects to /subagent-service for human-agent course correction.

Benchmark and compare small GPTs for task-specific inference. Tests base, fine-tuned, and prompted models against shared eval datasets. Finds minimum viable model, compares fine-tuned vs prompted, and generates reports.

Ingest codebases into /memory for knowledge extraction and CWE scanning. Phase 1 extracts functional knowledge (module docstrings, function signatures, class hierarchies, markdown docs) via Python AST. Phase 2 scans for CWE mappings via /taxonomy. Designed to run nightly via /monitor-codebase.

Train RVC voice models from artist names. Full pipeline: YouTube search, download, stem separation, preprocessing, training, and model indexing. Builds a library of singing voices organized by category (voice/instrument).

Thin CLI wrapper for memory service /match/* endpoints. All domain logic lives in the memory project.

Manage the Embry Agent D-Bus daemon (embry-agent.service) for system-level Pi access