Documentation

Create new Claude Code skills with proper structure, documentation, and best practices. Use when building custom skills for specific domains, workflows, or organizational needs.

Best practices for writing efficient, clean Stan programs

Write self-documenting code with minimal, evergreen comments that explain WHY rather than WHAT, avoiding temporary change notes or obvious descriptions. Use this skill when adding comments to any code file to ensure comments provide value by explaining complex logic, business rules, or non-obvious decisions rather than describing what the code does. Apply this skill when writing code that needs clarification, when documenting complex algorithms or business logic, or when removing outdated or redundant comments that describe obvious operations. This skill prioritizes writing clear, expressive code through meaningful naming and structure that minimizes the need for comments, ensures any comments added are helpful and explain intent or reasoning, and avoids leaving comments about recent changes, temporary fixes, or information that belongs in commit messages or documentation.

Maintain and update CHANGELOG.md following Keep a Changelog format. Use when: updating changelog, version documentation, release notes, semver versioning, categorizing changes (Added/Changed/Fixed/Security).

Creates or modifies Claude Code skills. Use when user asks to create a new skill, modify an existing skill, or needs help with skill structure. Always checks online documentation first to ensure accuracy and best practices.

Repair malformed markdown code fence closings. Use when markdown files have closing fences with language identifiers (```text instead of ```) or when generating markdown with code blocks to ensure proper fence closure.

Refine rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation. Use before writing code or creating implementation plans.

Parse regulatory document templates (PDF/DOCX) into structured markdown and extract section hierarchies using semtools. Use when tasks involve: analyzing regulatory templates, extracting document structure, parsing ICH/eCTD documents, identifying section hierarchies, preparing documents for content generation,or working with bulk PDF/DOCX processing.Keywords: parse template, extract sections, regulatory document, ICH template, eCTD, document structure,section headings, PDF parsing, DOCX parsing, bulk document processing, semtools

Send text messages via Apple Messages app with automatic contact lookup and attachment support. This skill should be used when sending SMS/iMessage to contacts. Supports name-based recipient lookup via Google Contacts integration, image/file attachments, and handles missing recipient/message prompts. CRITICAL - Messages are ALWAYS sent individually to each recipient, NEVER as group messages. REQUIRES E.164 phone format (+1XXXXXXXXXX) for reliable delivery. Integrates Arlen's writing style guide for authentic messaging.

Principles for writing effective, maintainable tests. Covers naming conventions, assertion best practices, and comprehensive edge case checklists. Based on BugMagnet by Gojko Adzic.

Generate comprehensive {node_name}.example.json files that showcase real-world usage of Workscript workflow nodes. Use when asked to document a node, create node documentation, generate node examples, or produce usage examples for workflow nodes. Also use when a subagent needs to create node documentation as part of node development or review.

Query and manage local Convex documentation mirror (42 docs). Search Convex topics for real-time database, serverless functions, authentication, file storage, and React hooks. Use when implementing Convex backend features or answering Convex-related questions. (user)

This skill should be used when the user wants collaborative, iterative development instead of autonomous implementation. It transforms Claude from "autonomous implementer" to "pair programmer" by enforcing ask-before-assuming, show-before-writing, iterate-in-small-chunks, and get-approval-at-each-step patterns. Trigger when user explicitly requests paired programming or when working on complex/novel features requiring collaboration.

Comprehensive Vitest testing framework guide with strong emphasis on Jest-to-Vitest migration. Covers automated migration using codemods, configuration setup, API differences, best practices, and troubleshooting. Use when migrating from Jest, setting up Vitest, writing tests, configuring test environments, or resolving migration issues. Primary focus is seamless Jest migration with minimal code changes.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Testing strategy, test pyramid (70% unit/25% integration/5% E2E), PGlite patterns, Playwright best practices. Use when writing tests, debugging test failures, or when user mentions testing/test/spec/E2E.

Full context reload. Use after /clear, after compaction, or at session start. Loads conversation history, indexes docs, maps code, scans configs, checks git. Gets you immediately helpful.

On-demand TDD guideline access without loading full documentation into context. Provides targeted guidance for RED-GREEN-REFACTOR phases, refactoring decisions, and test quality patterns.

Generate patent-style technical diagrams (flowcharts, block diagrams, system architectures) with automatic reference numbering.

Standards for API development, documentation, and maintenance using OpenAPI 3.0.