发现 Skills

Design and review CLI commands following clig.dev and 12-Factor CLI principles. Use when adding commands, designing flags/arguments, writing help text, handling errors, formatting output, or reviewing CLI code for UX issues.

Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.

Expert on GigLedger's database schema, collections, data models, DTOs, caching strategy, and cost control. Use when designing database schemas, creating DTOs, understanding data flow from database, or optimizing queries. References docs/05_data_model_and_schema.md.

Use when creating a new MCP (Model Context Protocol) server, extending an existing one, or debugging tool discoverability/performance. Guides through research → implementation → test → eval phases with TypeScript-first guidance matching our stack. Trigger on phrases like "build an MCP server", "expose X as an MCP tool", "write MCP tools for Y", "integrate Z via MCP".

Use this skill when executing the agreed session plan in waves with role-based execution and parallel subagents. Handles inter-wave quality checks, plan adaptation, and progress tracking. Core orchestration engine for feature and deep sessions. Triggered by /go command.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Specialized in system architecture, API contracts, and modular black-box design. Use when creating technical specifications, designing system primitives, defining module boundaries and contracts, reviewing architecture for replaceability, or mapping system dependencies.

根据论文或汇报内容生成多页 Draw.io 格式 PPT，支持论文答辩与通用汇报两种模式，自动导出为 .pptx。当用户提到论文答辩 PPT、答辩幻灯片、通用 PPT、汇报 PPT、根据模板生成 PPT、drawio2pptx 时使用。

Create professional diagrams and visualizations using the Excalidraw JSON format. Specialized for IT architecture diagrams, flowcharts, network topology, system design, microservices, ER diagrams, and state machines. Includes curated color palettes and visual styles. Use when working with .excalidraw files, or when the user mentions diagrams, flowcharts, architecture visualization, or drawing. Delegates to subagents to prevent context exhaustion from verbose JSON.

Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological data including genes, drugs, diseases, phenotypes, and more.

RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.

This skill applies the first-principles engineering and capital allocation frameworks of Elon Musk (CEO of Tesla and SpaceX, founder of X.com / PayPal). Reach for this skill whenever the user is facing complex manufacturing bottlenecks, evaluating existential risks, debating free speech vs. censorship, dealing with bureaucratic overregulation, or trying to accelerate ambitious technical timelines. It is highly effective for situations involving hardware production, AI symbiosis, radical innovation, and aggressive execution. Use this skill proactively when discussing multi-planetary expansion, government efficiency, or scaling prototypes to mass production, even if the user doesn't explicitly name him.

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API, opentrons-integration may be simpler.

Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.

Write fiction scenes following Stephen King principles and the McDonald opening rule. Use when drafting new scenes, editing existing prose, or writing chapters. Triggers include "write scene", "draft scene", "edit scene", "new chapter", "prose writing", "scene draft". Ensures POV discipline, character voice consistency, and craft quality.

Disciplined development workflow that prevents incomplete implementations, silent fallbacks, and hallucinated code. Use this skill for ANY coding task, feature implementation, bug fix, or technical work. Enforces mandatory decomposition of specs into tasks, elicits clarification for ambiguities, prohibits fallbacks without explicit approval, requires research for uncertain APIs/libraries, and maintains grounding checkpoints to prevent rework. Triggers on requests like "implement", "build", "create", "fix", "add feature", "develop", or any programming task.

Generate comprehensive equity research snapshots combining analyst consensus estimates, company fundamentals, historical prices, and macroeconomic context. Use when researching stocks, comparing estimates to actuals, analyzing company financials, assessing equity valuations, or building investment cases.

Anthropic's open-source financial analysis framework, adapted for the Hermes environment. It includes 10 financial agent templates covering investment banking, equity research, wealth management, financial analysis, and private equity. Locally deployed at ~/financial-services/.

Reconcile general ledger to subledger for a trade date or period — match at the position or transaction level, surface breaks, and classify each break by likely cause. Use for daily or month-end recon runs across asset classes.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Delegate coding to Claude Code CLI (features, PRs).