viktorbezdek

Author high-quality Claude Code SKILL.md files using philosophy-first design, evidence-based prompting, progressive disclosure, and anti-pattern prevention. Use when the user asks to write a skill file, create a new Claude Code skill, design a SKILL.md, review whether a skill's description will trigger correctly, or convert a workflow into a reusable skill. NOT for optimizing standalone prompts or

Parallel-merge workflow for producing a pitch (investor deck, board proposal, internal funding request, customer sales narrative) in roughly a week. Runs three parallel streams (deep interviews via elicitation, market dynamics via systems-thinking, audience sharpening via persona-definition), merges them into a single storytelling spine, audits via critical-intuition, and polishes every line with

Reframe work around measurable outcomes using OKRs, KPIs, and the outcome-vs-output distinction. Use when the user asks to define success criteria, write OKRs, set KPIs, clarify what "done" means in terms of impact, distinguish outputs from outcomes, or make a goal statement measurable and time-bound. NOT for ranking or scoring features by priority (use prioritization). NOT for systemic feedback-l

Diagnosing context FAILURES — lost-in-middle, poisoning, distraction, confusion, and clash patterns with model-agnostic measurement workflows. Use when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, context clash, or agent performance degradation. NOT for learning context basics or

Combine a parallel persona-swarm's outputs into an actionable artifact — consensus matrix (what every persona agreed on), dissent log (where personas disagreed and why), open questions (what nobody could answer), recommended next move (synthesized decision). Preserves dissent rather than forcing consensus. Use when running a brainstorm-swarm and the swarm-protocol skill has collected the persona o

Presentation creation, editing, and analysis for working with .pptx files including layouts, comments, and speaker notes.

Python development — use when the user works with .py files, pyproject.toml, uv, ruff, mypy, pytest, async/await, MicroPython, CLI tools, or PyPI publishing. Covers modern tooling, best practices, library architecture, functional patterns, and production workflows. NOT for TypeScript or JavaScript development (use typescript-development), NOT for React component patterns (use react-development).

Validates a plugin idea by surveying the marketplace, reading authoritative Anthropic sources, and deciding build-vs-fork-vs-skip before writing any code. Use when you want to research existing Claude Code plugins, check whether there is already a plugin for X, decide whether to build a new plugin or fork an existing one, run a marketplace survey before starting work, find authoritative documentat

This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", "implement LLM-as-judge", "compare model outputs", "mitigate evaluation bias", or mentions multi-dimensional evaluation, agent testing, quality gates, direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated qualit

Align stakeholders in writing using RFCs, design docs, proposals, pre-reads, and decision docs with explicit role assignments (DACI, RAPID). Use when the user asks to write an RFC, design doc, proposal, pre-read, or decision doc, wants to align async stakeholders on a decision, needs to assign deciders vs consulted vs informed, wants to structure a cross-team proposal, or is preparing a pre-read f

Design CMS content models — content types, fields, editorial workflows, governance rules, and COPE (Create Once, Publish Everywhere) patterns — for structured, multi-channel publishing. Use when the user asks to design a content model, define content types in a CMS, structure fields for editorial content, plan a headless CMS architecture, or design content reuse across channels. NOT for formal kno

Build and deploy hosted background coding agents with sandboxed VM execution, multiplayer sessions, and multi-client interfaces. Use when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes, self-spawning agents, or remote coding envi