Technical Writing

Foundational knowledge for writing PyMC 5 models including syntax, distributions, sampling, and ArviZ diagnostics. Use when creating or reviewing PyMC models.

Generate or update GitHub Pull Request titles and descriptions based on actual code changes in the final state. Use when the user mentions updating, generating, or writing PR descriptions, PR titles, pull request summaries, or says 'update the PR'. Analyzes git diff to determine what's actually in the code (not just commit history) and creates comprehensive, accurate PR documentation.

Code repository analysis and technical documentation generation skill

Review and provide feedback on blog posts to ensure they match the established writing voice and style guidelines.

Create comprehensive PAI skills from tool/CLI/API documentation. Analyzes docs (markdown or URLs via crawl4ai), deduces workflows, generates helper scripts/templates/guardrails, and builds complete skill packages. USE WHEN user says 'create skill from docs', 'build skill for [tool]', 'turn documentation into skill', or provides documentation to transform into a skill.

Documentation synchronization using Mem0 for tracking relationships between specs, architecture, ADRs, and roadmap

Use when web.run fails to parse a webpage and you need raw Markdown via Crawl4AI.

Use PROACTIVELY when reviewing CLAUDE.md configurations, onboarding new projects, or before committing memory file changes. Validates against official Anthropic documentation, community best practices, and LLM context optimization research. Detects security violations, anti-patterns, and compliance issues. Not for runtime behavior testing or imported file validation.

Reviews code comments for quality issues. Use when checking comments in code files, after writing new code with comments, before commits, or when user asks to review/check comments. Ensures comments explain WHY not WHAT, and eliminates noise.

Code quality standards for writing and reviewing. Use when writing new code, reviewing PRs, refactoring, or making architectural decisions.

Implements new modules, agents, or features using TDD methodology. Used when adding any new functionality to the table2image multi-agent system. Follows six-phase workflow: context loading, test writing, implementation, verification, documentation, and protocol completion.

Creates SEO-optimized blog posts in Sanity CMS with native content in English, Spanish, and Portuguese. Automatically activates for blog writing, content creation, and SEO optimization tasks.

Write OpenStudio ModelMeasures (Ruby scripts that modify .osm files) for building energy models. Use when creating measures, writing measure.rb files, or modifying OpenStudio models programmatically. Targets OpenStudio 3.9 with best practices from NREL documentation.

Enterprise-grade production readiness assessment system for comprehensive codebase evaluation. Use when (1) Evaluating a GitHub repository for production deployment, (2) Conducting pre-launch security and architecture reviews, (3) Assessing technical debt and system reliability, (4) Identifying gaps, vulnerabilities, and incomplete features, (5) Generating actionable remediation plans for engineering teams, (6) Validating scalability, observability, and operational readiness, (7) Reviewing cost optimization and resource efficiency, (8) Auditing compliance with industry standards (SOC2, GDPR, HIPAA, PCI-DSS), (9) Evaluating API contracts and integration stability, (10) Assessing team knowledge transfer and documentation completeness. Performs CTO-level multi-dimensional analysis exceeding top-tier tech company standards.

Review blog content for authentic voice and tone. Checks if content sounds like Fabio's conversational, honest technical writing style. Trigger phrases: "voice", "voice review", "tone", "sounds like me", "authentic", "check voice", "voice check"

Convert AI-written text to more human-like writing through subtle edits. Use when text reads "too AI", when the user mentions "humanize", "sounds robotic", "AI-written", "make it natural", or when editing for a more conversational voice.

This skill should be used when the user asks to "coordinate document writing", "manage doc writers", "create a design document with multiple writers", "orchestrate documentation", "delegate doc sections", "cos for documentation", "chief of staff for docs", or needs to break a large document into sections and delegate writing to multiple agents via VibeKanban.

Convert a markdown file to PDF using pandoc

Mandatory spec folder workflow orchestrating documentation level selection (1-3), template selection, and folder creation for all file modifications through documentation enforcement.

This skill should be used to remove AI-generated artifacts and unnecessary code before committing. It scans changed files for redundant comments, AI TODOs, excessive docstrings, and unnecessary markdown files. Git-only, no GitHub required.