Mark West
Community@MWest2020 · Amsterdam
Linux | Python (automation) | k8 | Argo | Dabbles in whatever
Agent Skills by Mark West
Showing 46 vetted skills indexed across 1 GitHub repositories.
MWest2020defuddle
Extract clean markdown content from web pages using the Defuddle CLI.
MWest2020cost-estimation
Predicts token usage, agent-compute time, and grounded dollar cost ranges for tasks before execution.
MWest2020constraint-design
Designs verifiable harness constraints with enforcement types, scopes, and promotion lifecycle guidance.
MWest2020choice-cartographer
Surfaces implicit decisions in specs as structured choice stories for human disposition.
MWest2020thinking-steel-manning
Constructs the strongest opposing case before accepting or rejecting a proposal.
MWest2020doc-coauthoring
Guides collaborative document drafting through context gathering, iterative refinement, and reader testing.
MWest2020thinking-theory-of-constraints
Identifies and resolves the single binding constraint limiting system throughput or latency.
MWest2020web-quality-audit
Audit websites for performance, accessibility, SEO, and best practices using live browser evidence.
MWest2020obsidian-markdown
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, and properties.
MWest2020owasp-security
Review code against OWASP Top 10, ASVS 5.0, LLM, and agentic AI security standards.
MWest2020claude-api
Build, debug, and migrate applications using the Claude API and Anthropic SDKs.
MWest2020core-web-vitals
Diagnose and optimize LCP, INP, and CLS using field data and browser traces.
MWest2020no-ai-slop
Edit drafts to remove AI writing patterns while preserving the writer's voice.
MWest2020ponytail
Enforces minimal code solutions by prioritizing stdlib, native features, and shortest diffs.
MWest2020xlsx
Create, edit, and recalculate Excel spreadsheets with formulas using openpyxl and LibreOffice.
MWest2020Extract, merge, split, create, and fill PDF documents using Python libraries and command-line tools.
MWest2020context-engineering
Write enforceable codebase conventions for the Context section of HARNESS.md.
MWest2020algorithmic-art
Generate seeded p5.js generative art with interactive HTML viewers and parameter controls.
MWest2020ponytail-audit
Audits an entire codebase for over-engineering and ranks deletable code, dependencies, and abstractions.
MWest2020ponytail-help
Displays a quick-reference card for ponytail modes, skills, and commands.
MWest2020internal-comms
Write internal communications using company-specific formats and guideline files.
MWest2020skill-creator
Create, evaluate, and iteratively improve SKILL.md skills with benchmarked test runs.
MWest2020canvas-design
Create original visual artwork as PNG or PDF files from a written design philosophy.
MWest2020pptx
Create, edit, and validate PowerPoint .pptx presentations via OOXML manipulation and rendering.
Frequently Asked Questions About Mark West
FAQPage SchemaWhat tasks can I accomplish with MWest2020's skill collection?▼
The 46 skills cover document processing (PDF, DOCX, XLSX, PPTX), web quality audits (performance, accessibility, SEO, Core Web Vitals), code review for maintainability and over-engineering, adversarial spec analysis, decision reasoning frameworks, Obsidian markdown editing, and frontend design with React, Tailwind, and p5.js generative art.
Who is the target audience for these skills?▼
Software engineers, web developers, and technical writers benefit most. Frontend engineers use the web-quality and design skills; maintainers use ponytail-review and maintainability-review for refactoring; architects use archify for system diagrams; and spec authors use advocatus-diaboli and choice-cartographer for decision review.
How do the web quality audit skills work in practice?▼
The web-quality-audit, performance, accessibility, seo, and core-web-vitals skills run evidence-led audits using Lighthouse-style lab and field data. They diagnose LCP, INP, and CLS regressions, check WCAG 2.2 compliance, validate meta tags and structured data, and produce prioritized optimization recommendations.
What do the ponytail and caveman skills do?▼
Ponytail enforces minimal solutions: standard library over dependencies, YAGNI checks, and deletion-focused code review via ponytail-review, ponytail-audit, and ponytail-debt ledger tracking. Caveman compresses communication output by roughly 75% while preserving technical accuracy, with lite, full, and ultra intensity levels.
What security review capabilities are included?▼
The owasp-security skill covers OWASP Top 10:2025, ASVS 5.0, LLM Top 10, and agentic security guidance for code review and authentication design. The thinking-red-team skill models attackers, maps attack surfaces, and reports only findings with reproducible exploit paths and verified mitigations.