Technical Writing

Critical reference for all Supabase database operations. Use this whenever reading from or writing to the database to ensure correct client usage (supabaseServer vs supabase), schema names, and query patterns. CRITICAL for security.

Implements Anthropic's Evaluator-Optimizer pattern where one LLM generates solutions and another provides evaluative feedback in an iterative loop. Use when quality can be demonstrably improved through articulated feedback cycles. Evaluates across 5 dimensions (functionality, performance, code quality, security, documentation) with up to 5 improvement iterations.

Creating high-quality agent skills following Claude's official best practices. Use when designing, implementing, or improving agent skills, including naming conventions, progressive disclosure patterns, description writing, and appropriate freedom levels. Helps ensure skills are concise, well-structured, and optimized for context efficiency.

Personal blog management with Eleventy and Cloudflare Workers. Use when user mentions blog, publishing posts, blog deployment, tj-zhang.com, or writing articles for the blog. Covers content workflow from Obsidian to published post.

Produce first drafts that match a writer's authentic voice using their Voice DNA Document. Consumes DNA documents from writing-dna-discovery skill. Generates 2 meaningfully different drafts with headlines, confidence assessment, decision notes, and DNA refinement suggestions. Collaborative partner that evaluates, pushes back, and advocates for quality. Handles blog posts, essays, newsletters, and more.

This skill should be used when Claude needs to write a feature specification, create acceptance criteria, document requirements, define user stories, or structure feature documentation. Trigger phrases include "write a spec", "create specification", "document requirements", "define acceptance criteria", "write user stories".

Incident response patterns and runbooks. Use when handling production incidents, creating runbooks, performing root cause analysis, writing postmortems, or designing on-call procedures.

Use when working with database models or migrations. Contains schema documentation and relationship patterns.

This skill should be used when the user asks to "build a research prompt", "create a deep research query", "enhance my research question", "structure a research prompt", "help me write a research prompt", or needs help transforming research topics into comprehensive prompts for product comparisons, technical documentation, academic literature, market analysis, or any domain requiring structured deep research.

Use this skill when you need to write configuration files in `src/config` for the Next.js app

Product Owner assistance for ticket refinement, epic breakdown, dependency analysis, and backlog management across multiple project management systems. Use this skill when working with tickets to create, analyze, propose amendments, or generate discussion questions. Supports Linear, Local Markdown, Jira, GitHub Issues, and other PM systems through extensible connectors.

Publish Claude Code Skills to GitHub with proper structure, privacy checks, and bilingual documentation. Use when user wants to "publish a skill", "share a skill", "release a skill to GitHub", or asks about skill distribution.

Search GitHub for real-world code examples and implementation patterns. Use when user wants to find code examples on GitHub, search GitHub repositories, discover how others implement features, learn library usage patterns, or research architectural approaches. Fetches top results with smart ranking (stars, recency, language), extracts factual data (imports, syntax patterns, metrics), and returns clean markdown for analysis and pattern identification.

Craft LinkedIn posts (text, carousels, documents, video) optimized for the December 2025 algorithm. Use when creating individual LinkedIn posts, writing hooks, designing carousel content, or adapting newsletter content for LinkedIn. Includes algorithm signals, format selection, external link workarounds, and templates for thought leadership content.

Detects and removes AI writing patterns from text. Use when polishing drafts, cleaning AI-generated content, or ensuring writing sounds authentically human. Invoke with "run through slop detector", "clean this up", or "remove AI fingerprints".

Data science and machine learning platform functions for the East language (TypeScript types). Use when writing East programs that need optimization (MADS, Optuna, SimAnneal, Scipy), machine learning (XGBoost, LightGBM, NGBoost, Torch MLP, GP), ML utilities (Sklearn preprocessing, metrics, splits), or model explainability (SHAP). Triggers for: (1) Writing East programs with @elaraai/east-py-datascience, (2) Derivative-free optimization with MADS, (3) Bayesian optimization with Optuna, (4) Discrete/combinatorial optimization with SimAnneal, (5) Gradient boosting with XGBoost or LightGBM, (6) Probabilistic predictions with NGBoost or GP, (7) Neural networks with Torch MLP, (8) Data preprocessing and metrics with Sklearn, (9) Model explainability with Shap.

Expert technical reviewer for implementation plans. Reviews plans in docs/plans/ for correctness, completeness, and technical accuracy. Validates libraries, APIs, and approaches. Outputs feedback as markdown in the final response.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

East programming language - a statically typed, expression-based language embedded in TypeScript. Use when writing East programs with @elaraai/east. Triggers for: (1) Writing East functions with East.function() or East.asyncFunction(), (2) Defining types (IntegerType, StringType, ArrayType, StructType, VariantType, etc.), (3) Using platform functions with East.platform() or East.asyncPlatform(), (4) Compiling East programs with East.compile(), (5) Working with East expressions (arithmetic, collections, control flow), (6) Serializing East IR with .toIR() and EastIR.fromJSON(), (7) Standard library operations (formatting, rounding, generation).

Execute Atlassian operations for both Jira and Confluence, including issue management, page retrieval, search, creation, and updates. Use when the user needs to interact with Jira issues, Confluence pages, or any Atlassian-related tasks.