Claude Skills by fabioc-aloha

Date comparisons at thresholds fail due to fractional days:

Adversarial code review with three parallel perspectives — Advocate, Skeptic, Architect — that create productive tension. Use for high-stakes PRs, architectural changes, or when single-pass review would miss issues. Surfaces findings through disagreement, not consensus.

Systematic 5-dimension audit framework for VS Code extensions — debug hygiene, dead code, performance, menu validation, dependency cleanup

Plans without measurable success criteria drift into wishful thinking:

One-time audits don't track improvement:

When checking that all callers of a contract implement it correctly, you get false positives from wrapper delegators:

CPU, memory, network bottleneck analysis — systematic performance investigation

Python mock.patch must target the import location, not the definition location

Systematic code refactoring to improve maintainability without changing behavior. Use when asked to \"refactor this\", \"clean up this code\", \"improve code quality\", \"simplify this\", \"reduce complexity\", or \"eliminate code smells\". Always preserves existing behavior.

Safe transformations — same behavior, better structure.

Evaluate a repository's readiness for AI-assisted development across 4 axes: code understanding, dependency restore, build success, and test execution. Use when onboarding to a new repo, assessing CI readiness, or validating that an AI agent can work effectively in a codebase.

Pattern-aware code scaffolding that detects existing conventions and generates new components matching the codebase style. Use when asked to \"scaffold a component\", \"generate boilerplate\", \"create a new module\", \"bootstrap a service\", \"add a new endpoint\", \"create a new controller\", or \"add a new feature module\". Discovers patterns first, then replicates them.

Deep structural analysis of a codebase—dependency mapping, architecture boundary detection, coupling/cohesion scoring, and dead code discovery. Use when asked to \"analyze codebase structure\", \"map dependencies\", \"find dead code\", \"architecture analysis\", \"coupling analysis\", \"trace dependencies\", or \"understand this system\". Produces a Context Map with actionable insights.

Systematic technical debt inventory and prioritization. Use when asked to \"find tech debt\", \"show me the TODOs\", \"how healthy is this codebase\", \"what should we fix first\", \"find code smells\", \"audit code quality\", or \"identify hotspots\". Scans code markers, analyzes git history, checks dependencies, and produces a prioritized debt report.

Safe terminal command patterns — backtick escaping, output capture, and hang prevention

Analyze test code quality to detect coverage-only tests, test smells, and low-value assertions. Use when asked to \"analyze test quality\", \"find coverage-only tests\", \"audit our tests\", \"are these tests valuable\", \"find test smells\", or \"which tests should we delete\". Scores tests 1-5 on real value and produces prioritized improvement reports.

When renaming a function, test files have references that survive find-and-replace:

Systematic testing for confidence without over-testing — the right test at the right level

Systematic project audit pattern — version consistency, terminology, fact inventory, cross-references

Visual output that passes static checks can still fail to render:

GROW model, active listening, developmental feedback, and team growth approaches

Don't overwhelm — chunk, scaffold, summarize first.

Therapeutic frameworks, assessment, ethical practice, and client documentation for counselors and psychologists.

Canonical phrasing for respectful disagreement without capitulation — structural resistance to sycophancy

Data-driven narrative construction, stakeholder management, and influencing senior leadership decisions

Help humans learn through partnership, not instruction.

Agenda design, time boxing, decision capture, async alternatives, and productive facilitation

Generate an executive organization brief (leadership chain, direct reports, extended teams, and vendor partners) for a target person. Produces a Word + PDF report from a directory MCP source (WorkIQ is the reference implementation) and displays it in a Copilot canvas. Triggers on "generate org report for X", "build org brief for X", "make an org report for X", "org profile document for X".

Influence mapping, communication strategies, and expectation management for complex organizations

Create stakeholder-friendly project status updates and progress reports

Test harness for validating converter outputs with 284 assertions across all converter muscles

Convert a Markdown file to a styled Word (.docx) document using docpilot — syntax-highlighted code blocks, blue-header tables, no Pandoc required.

Convert Word documents (.docx) to clean Markdown with image extraction and pandoc cleanup

Convert Word documents (.docx) to PDF. Preserves headings, paragraphs, lists, tables, and inline images with best-effort layout fidelity.

Convert Markdown to RFC 5322 email (.eml) with inline CSS and CID images

Convert Markdown to EPUB 3 e-books via Pandoc.

Pre-process Markdown into a Gamma-import-ready version.

Convert Markdown to standalone HTML pages with embedded CSS, images, and Mermaid diagrams

Convert Markdown to LaTeX source via Pandoc.

Convert Markdown to PDF via Pandoc with two rendering engines.

Convert Markdown to PowerPoint presentations via Pandoc.

Convert Markdown with Mermaid diagrams and SVG illustrations to professional Word documents

Convert PowerPoint (.pptx) to Markdown via Pandoc.

Execute read-only KQL queries against Kusto / Azure Data Explorer clusters via the Kusto MCP server. Read-only -- does not create, alter, or drop objects.

Execute read-only DAX queries against Power BI semantic models via the Power BI MCP server -- metadata discovery with INFO.VIEW functions and data retrieval with EVALUATE.

Read any chart (image, HTML, screenshot) and extract insights, patterns, anomalies, bias, and narrative -- the reverse of visualization

Dashboard layout patterns, KPI card design, filter architecture, narrative flow through panels, and self-contained HTML generation

Exploratory data analysis patterns -- profiling, distributions, correlations, segmentation, anomaly detection, and translating statistics into narrative insights

Data pipeline quality assurance — anomaly detection, schema drift, null ratio monitoring, freshness checks, and safe-write protection for reliable data engineering

End-to-end data narrative construction -- three-act structure, Knaflic/Duarte methodology, audience-first framing, and orchestration across analysis, visualization, and dashboard skills