Render data dashboards as pure ASCII art in monospace text -- the cheapest, most portable delivery method. No rendering engine, no SVG, no browser.
Generate assisted PRs to correct Security Group ownership for first-party apps flagged by S360 tenant-isolation policy (SFI-TI3.2.2)
Perform a local brain audit for ACT Edition using deterministic QA plus targeted file review, then produce severity-ranked fixes.
Ingestion patterns for CSV, JSON, REST API, SQL, Excel, and Parquet -- guides an LLM through loading data from any common source
Detect, classify, and prune stale entries in Alex_Skill_Mall — define what stale means and how to remove gracefully
Maintain the source registry in sources/supported-stores.json — add a new third-party plugin store, retire one, refresh metadata, validate the schema.
Handling personally identifiable information under European and Australian privacy regulations.
Comprehensive brain file review — external freshness, internal consistency, semantic accuracy — stamp only after full assessment
GROW model, active listening, developmental feedback, and team growth approaches
Context-dependent editorial style rules for academic writing — APA7, Chicago, MLA judgment calls
Help writers produce content that sounds genuinely human by avoiding telltale AI-generated text patterns
Cognitive load reduction strategies for clearer, simpler user experiences. 認知負荷削減策略：選擇精簡、漸進披露、一致模式、智能默認。 Use when: reviewing information architecture, simplifying complex flows,…
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.
Render data dashboards as static SVG panels embeddable in Markdown. Uses D3.js v7 mental model for scales, shapes, and axes.
Build knowledge bases that build software — research before code, teach before execute
Fetch plugin store updates, inventory contents, match against fleet profile, and generate adoption candidates report
Markdown sanitization order matters — marked.js then DOMPurify then Mermaid to prevent XSS
This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring,…
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…
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.
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,…
Recognize and prevent confabulation — when you don't know, say so.
Pre-checks, version consistency, and deployment discipline.
Reusable patterns for VS Code extension development.
Date comparisons at thresholds fail due to fractional days:
Mixing structure and content makes both hard to maintain:
Code-scanning regex that looks for literal strings misses real usage:
Pre-process Markdown into a Gamma-import-ready version.
Two READMEs covering overlapping scope will diverge:
Convert Markdown to PowerPoint presentations via Pandoc.
Create stakeholder-friendly project status updates and progress reports
Validate VS Code extension manifest against runtime code usage
Visual output that passes static checks can still fail to render:
Inline Python in shell scripts has quoting issues:
Template-driven layouts require code changes for structural updates:
Multi-factor decisions become arbitrary without explicit weights:
Universal deployment patterns for any project type.
Time Saved: 1+ hour debugging silent auth failures
Version numbers in 5+ files WILL drift with manual edits:
Convert HTML documents to clean Markdown via pandoc
VitePress intercepts all navigation clicks for SPA routing:
Storing images at embed size loses the original:
Translate research vision into funded reality.
When extracting hardcoded data to JSON, field values silently drift:
Convert PowerPoint (.pptx) to Markdown via Pandoc.
Recognize scope creep, suggest MVP cuts, and manage project boundaries
AI/LLM features default to verbose responses, causing:
Extensions/tools that auto-write to user workspaces without consent:
Monolithic transformations are hard to test and debug:
Plans without measurable success criteria drift into wishful thinking:
Be a thinking partner. The answer often emerges when explaining the problem.
Python mock.patch must target the import location, not the definition location
Raw error messages leak internal information to users:
Older action versions trigger deprecation warnings and will eventually break:
With `cleanUrls: true`, nav links must NOT have `.html` extensions:
Time Saved: 30 minutes - 1 hour debugging
Convert Markdown to LaTeX source via Pandoc.
Strip Markdown formatting and produce clean plain text via pandoc
VitePress iframe embedding gotchas — CSP headers, sandboxing, responsive sizing