Render data dashboards as self-contained HTML files using Apache ECharts v6. Single file, zero build step, interactive charts with tooltips and data zoom.
Previews and configures repository-level defaults for optional Alex ACT plugins while keeping Manager and Core enabled.
Audit and eliminate token waste from cognitive architecture memory files -- instructions, prompts, skills, and agents
Analyze documentation gaps, create Architecture Decision Records (ADRs), and build knowledge indexes.
Query S360 Kusto for SFI-TI3.2.2 tenant isolation violations, classify by ViolationTitle, flag autofix-eligible items for downstream remediation
Best practice decision matrix for choosing between Marp, Gamma, and PptxGenJS based on use case requirements.
Design and optimize production-grade multi-agent systems with LangGraph, LangChain, and DeepAgents for complex AI workflows.
Dark-slate SVG banner family — 1200×320 hero + 1200×60 section dividers — for governance, curation, and audit-style documentation
Execute an approved model task plan through Microsoft Foundry, Hugging Face, or ElevenLabs and record provider evidence.
Distill the central claim before authoring any summary-shaped output: hero copy, commit-message subject, PR title, ADR title, slide title, executive summary, skill description,…
Configure optional Microsoft Foundry, Hugging Face, and ElevenLabs provider access for AI Operations.
Help writers produce content that sounds genuinely human by avoiding telltale AI-generated text patterns
Context-dependent editorial style rules for academic writing — APA7, Chicago, MLA judgment calls
Communication patterns for feedback, cross-audience content, and eliciting needs. SBI feedback model (Situation → Behavior → Impact), stakes-calibrated review voice,…
Complex multi-step remediation scenarios for S360 Tenant Isolation violations that require code changes, Federated Identity Credential (FIC) setup, and bilateral coordination…
Cleanly uninstalls the four Alex ACT constellation plugins (alex-act-core, alex-act-illustrator-plugin, alex-act-enterprise, alex-act-msft), the fifteen user-scope discipline…
General Copilot CLI plugin operations: install / list / update / remove / marketplace add + remove, scope precedence (user vs repo), the enabledPlugins + extraKnownMarketplaces…
Maintain the source registry in sources/supported-stores.json — add a new third-party plugin store, retire one, refresh metadata, validate the schema.
Domain: Multicultural team communication, cultural intelligence, global collaboration
Evaluate a proposed store for inclusion in Alex_Skill_Mall using a quality scorecard
Route AI image generation and editing requests to Replicate (FLUX, Ideogram, Recraft, SDXL, imagen) via the bundled `replicate` MCP server.
Build professional, themed PowerPoint decks from Markdown via LLM-generated pptxgenjs JavaScript. Uses modular per-slide architecture for all decks.
Render data dashboards as pure ASCII art in monospace text -- the cheapest, most portable delivery method. No rendering engine, no SVG, no browser.
Ship deterministic hand-authored SVG generators for print-quality figures backed by real published datasets.
Author print-quality SVG figures for books, reports, and exec-facing documents. Ships the canvas + typography grammar (viewBoxes, print-legibility floor with math, type hierarchy,…
Distill the one-sentence Big Idea, story arc, audience, and style stance for a chart BEFORE picking a chart type.
Evaluate plugin quality. Use when user says "evaluate plugin", "review plugin quality", "score my plugin", "check plugin", "rate plugin".
Error recovery and failure handling patterns for distributed systems including rollback strategies, circuit breakers, retry logic with exponential backoff, graceful degradation,…
Systematic documentation audit, drift detection, preflight validation, and multi-pass quality pipelines
Meta-skill for maintaining and evolving Alex's cognitive architecture through deliberate documentation and pattern extraction.
VS Code Copilot platform changes affecting how tools are used: deferred-tool categories with example search queries (GitHub, Azure MCP, Fabric, Microsoft docs, browser, notebook,…
Data cleaning, profiling, transformation, and quality gates -- prepares raw data for visualization and analysis
Comprehensive preparation for doctoral dissertation defense including timeline management, presentation design, Q&A practice, mock sessions, and committee dynamics.
Documentation hygiene — anti-drift rules, count elimination, and living document maintenance
Generate branded SVG banners for documents (READMEs, plans, changelogs, release artifacts) using a configurable Node.js muscle.
Safely update Copilot CLI plugins by wrapping `copilot plugin update` with per-plugin change summaries and breaking-change warnings.
Bootstrap repository-scoped VS Code workspace files for a plugin-native Alex ACT workspace. Use when a new repository lacks Markdown Preview CSS, the current workspace needs the…
Calibrated human-AI collaboration with creative latitude — trust calibrated to reliability, creativity preserved with validation. — from fabioc-aloha/Alex_Skill_Mall
Orchestrate end-to-end SFI-TI3.2.2 workflow — fetch violations, classify, dispatch to remediation skills, generate report
Patterns for fiction, narrative structure, character development, dialogue, and storytelling craft.
Add a new project to the planning suite. Creates a project-specific configuration directory and walks through project settings.
Step-back protocol — restate, generalise, specialise, invert, ask why, pre-mortem, check stakeholders, and audit framings before solving
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.
Annotate screenshots, diagrams, and images with callout rectangles, arrows, labels, and color-coded highlights using PIL.
End-to-end process of rehoming (moving or reissuing) certificates so every production Entra app credential lives in the same tenant and cloud as the app itself.
Build knowledge bases that build software — research before code, teach before execute
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory…
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).
This skill should be used for the tool-interface layer of an agent system specifically: writing tool descriptions agents can route on, designing tool schemas and response formats,…
This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring,…
How the Plugin Mall scans, scores, and prunes itself. The Mall is a self-curating repo; this skill is its operational playbook for the weekly catalog refresh and trust scoring.
Privacy by design, data protection, and responsible AI principles.
With `cleanUrls: true`, nav links must NOT have `.html` extensions:
Convert Markdown to RFC 5322 email (.eml) with inline CSS and CID images
Convert Markdown to LaTeX source via Pandoc.
Date comparisons at thresholds fail due to fractional days:
Older action versions trigger deprecation warnings and will eventually break:
Hardcoded paths in build scripts break when directory structure changes:
Choosing the right model for the task — power vs. cost vs. speed.
Extensions/tools that auto-write to user workspaces without consent: