architecting-software
Designs software architecture from a confirmed PRD. Use when a PRD exists and architecture must be designed before implementation, when writing ADRs, choosing…
Re-explains concepts at a "knows the basics" level — strips jargon, uses analogies, and assumes broad general knowledge without domain expertise. Use when the user invokes /eli40 to request a simpler explanation of the previous message, or /eli40 <topic> to get an accessible
$ npx -y skills add isvlasov/rageatc-oss --skill eli40 --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/eli40Context preview
The summary Claude sees to decide when to auto-load this skill.
Re-explains concepts at a "knows the basics" level — strips jargon, uses analogies, and assumes broad general knowledge without domain expertise. Use when the user invokes /eli40 to request a simpler explanation of the previous message, or /eli40 <topic> to get an accessible
name: eli40 description: Re-explains concepts at a "knows the basics" level — strips jargon, uses analogies, and assumes broad general knowledge without domain expertise. Use when the user invokes /eli40 to request a simpler explanation of the previous message, or /eli40 <topic> to get an accessible explanation of a specific topic. Like ELI5 but calibrated for an adult generalist.
Re-explain for an intelligent adult with broad general knowledge but no expert depth in the area being discussed.
**Without argument:** re-explain your most recent message or suggestion, covering the same ground. **With argument** (e.g. `/eli40 HTMX frontend`): explain the given topic from scratch.
1. **Replace jargon** with plain language, or define it inline on first use 2. **Use analogies** to familiar concepts where they genuinely clarify 3. **Explain the "why"** — connect facts to reasons, don't just state them 4. **Keep the structure** — same logical flow, more accessible level 5. **Be honest about simplification** — if glossing over important nuance, say so briefly
Assume they understand variables, APIs, databases, git, basic networking, and how the web works. Assume they do NOT know framework-specific internals, protocol details, academic CS terminology, or niche architectural patterns. Concrete examples over abstract definitions; simpler doesn't mean longer.
Don't patronise ("so basically, a computer is like a brain..."), don't pile on caveats, don't turn it into a lecture — roughly match the length of the original explanation, and never lean on "basically" or "simply put" as crutches.
Rage Against The C - pick your own C to rage against. Two plugins for Claude Code / Cowork, built on the idea that we're using AI wrong: the speed of its output tricks us into rushing the input.
Repo: isvlasov/rageatc-oss
Designs software architecture from a confirmed PRD. Use when a PRD exists and architecture must be designed before implementation, when writing ADRs, choosing…
Writes correct, version-aware Telegram bot code. Use when writing, extending, or debugging a Telegram bot in python-telegram-bot, aiogram, grammY, or Telegraf.…
Converts an approved ARCHITECTURE.md into an implementation roadmap of isolated, dependency-ordered chunks. Use when architecture has been approved and work…
Delegates a task to OpenAI Codex running as an interactive session in a herdr pane - uses the user's ChatGPT subscription, visible in herdr, steerable…
Delegates a task to a local LLM running as a Pi coding-agent session in a herdr pane - the subagent is visible in herdr, can be steered mid-session, and costs…
Creates a design system for software with a UI. Use when a project has a user interface and architecture is confirmed — whether creating from scratch or…