文件

YAML data serialization format. Use when reading/writing configuration files, Kubernetes manifests, or structured data.

Shared foundation for Oracle & Corrector agents. Establishes the source hierarchy for resolving conflicts between documentation, code, and specs. Load this skill first when investigating how the system works.

Apply safe refactoring patterns to improve code structure without changing behavior. Use when cleaning up code, reducing technical debt, or improving maintainability.

Search enterprise context data (Slack, docs, meetings, PRs) from the HERB benchmark to answer questions about products, employees, customers, and organizational activities. Use when answering questions that require searching through enterprise communication and documentation.

Generic web scraper for extracting and organizing Snowflake documentation with intelligent caching and configurable spider depth. Scrapes any section of docs.snowflake.com controlled by --base-path.

Apply XP practices including pair programming, ensemble programming, continuous integration, and sustainable pace. Use when implementing agile development practices, improving team collaboration, or adopting technical excellence practices.

Writing dbt models with proper CTE patterns, SQL structure, and layer-specific templates. Use this skill when writing or refactoring dbt models, implementing CTE patterns, creating staging/intermediate/mart models, or ensuring proper SQL structure and dependencies.

Write clear, engaging technical content from real experience. Use when writing blog posts, documentation, tutorials, or technical articles.

Generate JSON schemas and OpenAPI specs using justfile tasks (just gen, just gen-*-schema). Use when user modifies dataset manifests, API definitions, adds/removes schema fields, or mentions code generation, schemas, OpenAPI specs. Outputs to docs/manifest-schemas/ and docs/openapi-specs/.

Analyze and address technical debt in codebases.

Creates clear, welcoming handbooks and documentation that help team members understand roles, responsibilities, and workflows. Transforms technical documentation into engaging guides. Use when user wants to create a handbook, improve documentation, write team guides, create process documentation, or make existing handbooks more readable and approachable.

First-draft writing assistant for Crucible-planned novels. Use when author has completed planning (crucible-planner) and outlining (crucible-outliner) and wants to write the actual prose. Handles scene-by-scene drafting, style matching, continuity tracking, and hallucination prevention. Triggers on "write my novel," "draft chapter X," "start writing from my outline," "help me write my book," or when user has Crucible outline and wants prose output. Works with any Crucible-planned story.

Use when writing or updating tests (Python, JS/Hoot, integration, or tours).

Creates vision documents through structured 5-phase discovery process. Guides through problem discovery, solution exploration, user needs analysis, future & scope planning, and document generation. Use when user wants to create a vision document for a feature, needs to define strategic context and high-level goals, or is starting feature development and needs to establish the "why" and "what" before technical details. Follows established feature development process with lean, focused documents (100-150 lines max) that flow from general problems to specific scope.

Professional investment analysis skill for stock market analysis. Provides 7 core capabilities: (1) Daily market overview, (2) Stock fundamental analysis, (3) Technical chart analysis, (4) Strategy simulation, (5) Risk management, (6) Stock screening, (7) News impact analysis. Use when users need comprehensive stock analysis, investment research, portfolio management, or market analysis tasks.

Chapter-by-chapter outline generator for stories planned with the Crucible Structure. Use when a user has completed Crucible planning documents (thesis, strand maps, forge points, etc.) and wants to create detailed chapter outlines. Triggers on requests like "outline my book," "create chapter outline," "outline Book 1," "turn my Crucible plan into chapters," or when user has Crucible planning docs and wants to start writing. Works for single books or multi-book series.

Use when integrating with Orama. Links to official docs for search, indexing, answer engine. (project)

Creates concise technical specification documents through 3-4 phase process. Guides through architectural decisions, system contracts, and technical design without getting bogged down in implementation details. Use when user wants to create a technical specification, needs to define how the system will be implemented technically, or is documenting architecture, data contracts, API specifications, and system components. Follows established feature development process with concise (5-10 page) specs focused on WHAT and WHY, not HOW to code. Optionally creates design brief for features with UI/UX complexity.

Automatically detect and fix documentation inconsistencies, outdated examples, and missing @file headers in the u-he-preset-randomizer project. Triggers when documentation appears outdated or when making significant code changes that affect public APIs.

Comprehensive guide for creating REST API endpoints in Bruno. Use when working with Bruno collections, creating .bru files, configuring API endpoints, setting up authentication, writing pre/post-request scripts, organizing Bruno collections, or testing REST APIs with Bruno.