viktorbezdek
- 116 skills
- 0 followers
- 14 hours ago last updated
- ▌
- ▌ Security Hardening Audit · viktorbezdek bundleSystematic security audit workflow for hardening a codebase through structured multi-pass analysis. Composes four skills across five phases — threat surface mapping with attack vector identification (risk-management), security-focused code review targeting OWASP and language-specific vulnerabilities (code-review), boundary condition and validation gap analysis (edge-case-coverage), and security test suite construction with fuzzing and property-based tests (testing-framework). Use when hardening an existing codebase before launch, after a security incident, during compliance preparation, or for periodic security reviews. Use when you want a structured audit rather than ad-hoc scanning. NOT for real-time intrusion detection or incident response — use your SIEM. NOT for infrastructure/network security — this covers application code only.
- ▌ User Research To Insight · viktorbezdek bundleFunnel workflow for turning user interviews into actionable product direction that the team actually acts on. Designs the research conversations using elicitation frameworks (OARS, narrative identity, values elicitation, schema detection), synthesizes findings into grounded personas (persona-definition), places them in the organizational landscape (persona-mapping), maps their journeys with touchpoints and friction (user-journey-design), audits for what the research missed (critical-intuition), and presents insights as narrative rather than report (storytelling). Use when you're running a research project and want the outputs to change product direction, not just sit in a Notion page. NOT for quantitative research — different methodology.
- ▌ Typescript Development · viktorbezdek bundleTypeScript development — use when the user works with TypeScript, type system patterns, generics, Zod, tsconfig, NestJS, branded types, or runtime validation. Covers type system mastery, framework integration, architecture patterns, security, and testing strategies. NOT for Python development (use python-development), NOT for React component patterns or hooks (use react-development), NOT for Next.js framework specifics (use nextjs-development).
- ▌ Docker Containerization · viktorbezdek bundleDocker and container development — use when the user mentions Dockerfiles, multi-stage builds, Docker Compose, container optimization, image size reduction, DDEV, containerization, or dev environment setup with containers. NOT for CI/CD pipeline YAML or pipeline configuration (use cicd-pipelines), NOT for workflow orchestration or release automation (use workflow-automation), NOT for Kubernetes or container orchestration platforms (use cloud-native tooling).
- ▌ Documentation Generator · viktorbezdek bundleGenerate comprehensive documentation for a codebase by reading the repository and producing READMEs, API docs, architecture docs, and technical references. Use when the user asks to "document this repo", "generate docs", "write a README", "create API documentation", "document this codebase", "write architecture docs", or "produce technical references" for an existing project. NOT for UX copy, button labels, or interface microcopy (use ux-writing). NOT for pedagogical code examples or tutorials (use example-design). NOT for inline code comments. NOT for navigation or sitemap design (use navigation-design).
- ▌ Evaluate And Improve Agent · viktorbezdek bundleDiagnostic-loop workflow for improving an underperforming AI agent. Starts with baseline measurement using rubrics and LLM-as-judge scoring (agent-evaluation), then diagnoses architectural problems like task-model mismatch and pipeline bottlenecks (agent-project-development), redesigns the agent topology — supervisor, swarm, or specialized agents (multi-agent-patterns), adds the right memory framework when persistence is the gap (memory-systems), and re-evaluates against the original baseline to prove improvement. Use when an existing agent is underperforming, producing inconsistent results, failing on edge cases, or costing too much per interaction. NOT for building a new agent from scratch — use the build-ai-agent workflow instead. NOT for prompt-only fixes — use prompt-engineering directly.
- ▌ Test Driven Development · viktorbezdek bundleGuides the Test-Driven Development methodology: the Red-Green-Refactor cycle of writing failing tests before implementation code, then making them pass with minimal code, then refactoring. Use when the user asks to do TDD, practice test-driven development, follow red-green-refactor, write tests first, apply test-first methodology, or implement a feature using TDD workflow with pytest, Vitest, ERT, or Zod. NOT for choosing or setting up test frameworks (use testing-framework), NOT for finding and fixing bugs or analyzing stack traces (use debugging), NOT for reviewing existing code or PRs (use code-review).
- ▌ Competitive Intelligence · viktorbezdek bundleCompetitive intelligence and market positioning analysis for product and GTM decisions. Use for competitor landscape mapping, positioning gap identification, win/loss pattern synthesis, battlecard creation, market-sizing estimates (TAM/SAM/SOM), and differentiation analysis. Trigger phrases: "map the competitive landscape", "create a battlecard for", "analyse our win/loss patterns", "how do we differentiate from", "size this market". NOT for primary market research (customer interviews, surveys) — this skill works from existing public and internal data. NOT for financial modelling or investor decks — competitive context informs the story but this skill does not build financial projections. NOT for pricing strategy deep-dives — pricing has its own set of constraints and frameworks beyond competitive positioning.
- ▌ Creative Problem Solving · viktorbezdek bundleGenerate new ideas and breakthrough solutions using brainstorming, lateral thinking, SCAMPER, first principles reasoning, game theory, and strategic reframing. Use when the user asks to brainstorm, ideate, "think outside the box", generate alternatives, explore creative solutions, reframe a problem, or come up with ideas — especially when stuck in conventional thinking. NOT for stress-testing or finding flaws in existing ideas (use critical-intuition), NOT for making a final decision between options (use strategic-decision or prioritization), NOT for detecting bias or evaluating evidence quality (use critical-intuition).
- ▌ Context Engineering Pipeline · viktorbezdek bundleDiagnostic-and-fix pipeline for systematic context engineering — fix agent context, context engineering, context optimization pipeline, diagnose context problems. Chains context-fundamentals (attention, budgeting), context-optimization (KV-cache, partitioning, observation masking), context-compression (summarization, anchored iterative, tokens-per-task), context-degradation (lost-in-middle, poisoning, clash diagnosis), and filesystem-context (scratch pads, plan files, dynamic loading). Use when an agent's context is degrading, token costs are bloated, the agent forgets instructions mid-session, output quality drops in long conversations, or building a new agent and wanting context right from the start. NOT for prompt engineering — use prompt-engineering. NOT for agent architecture — use build-ai-agent.
- ▌ Storytelling For Stakeholders · viktorbezdek bundleNarrative-build workflow for turning data, technical results, or project outcomes into a compelling story for leadership, investors, or customers. Structures the narrative using proven story frameworks — 3-act, SparkLines, situation-complication-resolution (storytelling), finds the surprising angle through lateral thinking and reframing (creative-problem-solving), anchors every claim to measurable business impact using OKRs and outcome vs output framing (outcome-orientation), then iterates through craft and polish. Use when presenting quarterly results to leadership, pitching a technical initiative to non-technical stakeholders, writing a case study, summarizing a project for board review, or defending a budget request with narrative. NOT for fiction writing — use storytelling directly. NOT for investor pitches with full research — use the pitch-sprint workflow instead.
- ▌ Agent Project Development · viktorbezdek bundleThis skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches. NOT for evaluating agent quality or building evaluation rubrics (use agent-evaluation), NOT for multi-agent coordination or agent handoffs (use multi-agent-patterns).
- ▌ Object Object · viktorbezdek bundle[TODO: Write comprehensive description in third-person. Start with "This skill provides..." or "This skill should be used when..."] [TODO: Add "Use when" scenarios - specific situations where Claude should use this skill] [TODO: Add keywords - technologies, use cases, error messages that should trigger this skill]
- ▌ PPTX · viktorbezdek bundlePresentation creation, editing, and analysis for working with .pptx files including layouts, comments, and speaker notes.
- ▌ Clip Aware Embeddings · viktorbezdek bundleSemantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries. Mention CLIP, embeddings, image similarity, or semantic search.