Technical Writing

Execute implementation plans step-by-step with quality guardrails (ask when unclear, minimal-change bias, readability checklist, verification). Use when the user asks to execute or follow a plan, run tasks sequentially from a plan file (e.g., docs/plans/*.md), or continue plan steps.

Use when creating or editing blog articles for the homepage - enforces humanized writing style, validates punctuation rules, and ensures content reads naturally without AI-typical patterns

Integration with AppFlowy project management tool for task tracking, database management, and workspace organization. Use when working with AppFlowy, managing project tasks, creating databases, organizing workspaces, syncing agent work with project tracking, syncing documentation or tasks to AppFlowy, setting up automated sync workflows, or when the user mentions AppFlowy, project tracking, task management, or sync automation. Includes generic sync script that works with ANY project. Supports rich text formatting (bold, italic, code, links, strikethrough) and git pushsync workflow for automated syncing.

Programmatic verification of KB state: tickets, phases, tests, integrity.Provides scripts for automated checking at each workflow stage.SCRIPTS:- check_ticket.py: Ticket docs, tests, final status → next step- check_phase.py: Phase progress, all tickets complete?- check_tests.py: Trajectory, RED verification, coverage vs spec- check_integrity.py: Index.md matches dirs, roadmap has all active itemsUse when:- Checking ticket/phase completion- Validating before commit/archive- CI/CD automation- User says "status", "check", "verify"

Analyze code diffs and commit messages between current branch and target branch to generate comprehensive Pull Request descriptions in markdown format. Automatically selects appropriate PR template and creates structured, informative PR descriptions ready for submission.

Format conventions for markdown knowledge vaults. Use when writing notes or when format/syntax questions arise. Covers the dual-reader principle (human + AI), YAML frontmatter, wikilinks, and sources.

Supadata API via curl. Use this skill to extract transcripts from YouTube/TikTok/Instagram videos and scrape web content to markdown.

Create database tables with Prisma ORM, migrations, and RLS policies. Use when user needs "create database table", "add [model] model", "set up RLS", "create migration", "store data in database", or "design schema". Generates Prisma models with proper naming conventions, creates migrations, sets up Row-Level Security policies, and syncs test database. Includes WorldCrafter patterns for relationships, tags, comments, activity logs, versions, world membership, collections, wiki pages, and bookmarks. Typically the FIRST skill for new features. Do NOT use for UI/forms (use worldcrafter-feature-builder), simple routes (use worldcrafter-route-creator), tests only (use worldcrafter-test-generator), or auth logic only (use worldcrafter-auth-guard).

Synchronise task lists with GitHub Projects using the gh CLI. Use this skill when users want to add tasks, to-dos, or action items to a GitHub repository's project board. The skill can extract tasks from markdown files, user messages, or structured data, then create GitHub issues and add them to projects. It intelligently detects the target repository from git remotes when not explicitly specified.

Execute project release workflows by locating and following project-specific RELEASE_GUIDE.md in the repository root or docs/. Use when asked to perform a release, publish a release, cut a tag, run release steps, or when a user references RELEASE_GUIDE.md.

Automatically applies when writing Python functions that call async operations. Ensures proper async/await pattern usage (not asyncio.run) to prevent event loop errors.

Clarify ambiguous or incomplete requirements before drafting an OpenSpec change proposal (typically used by /openspec-proposal before writing proposal files).

Write self-documenting code with minimal, helpful comments that explain large sections of logic without cluttering the codebase. When writing or editing any code files and deciding whether to add comments. When reviewing existing comments to ensure they remain relevant and helpful. When structuring code to be self-explanatory through clear naming and organization. When adding comments to explain complex logic or non-obvious implementation details. This skill applies universally to all code files to maintain clean, well-documented code.

Use this skill when helping write content for tacosdedatos newsletter/blog. Provides complete voice analysis, structural patterns, engagement mechanics, and writing principles for the distinctive bilingual tech-writer voice. Use for brainstorming post ideas, structuring drafts, writing posts, editing for voice authenticity, creating headlines, quality checking drafts, and generating quick outlines. Essential for maintaining the unique tacosdedatos voice that blends Spanish/English, technical depth with accessibility, vulnerability with expertise, and Mexican cultural identity with Bay Area tech culture.

This skill should be used when the user asks to "write an article", "draft a blog post", "edit prose", "review my writing", "check style", "improve clarity", or needs general writing guidance. Provides Strunk & White's Elements of Style for foundational grammar, usage, and composition principles.

Use when analyzing existing codebases to generate architecture documentation - coordinates subagent-driven exploration with mandatory workspace structure, validation gates, and pressure-resistant workflows

Добавляет медицинские записи в Notion. Используй когда пользователь просит добавить запись в карточку Богданы, Андрея или Вани по файлу анализов/обследований.

Offline Claude Code documentation fallback. Use when the user asks about Claude Code features, capabilities, or configuration and the built-in claude-code-guide subagent fails due to network issues or proxy blocking.

Research-driven investigation skill for validating solutions and exploring documentation. Never ask questions you can answer yourself through research. Use WebFetch, WebSearch, and testing to validate ideas before presenting them. Deliver concrete, tested recommendations with evidence.

Enforces company voice, tone, and formatting standards across all outputs. Acts as the semantic constitution for documentation, code comments, and external communications.