architecture
Use when the user asks to improve architecture, find refactoring opportunities, surface deepening opportunities, consolidate…
Explain a topic like I'm a 5 year old — restate my last output, or a named topic, in plain words without dropping a single fact. Use when the user types /eli5 [topic], or says an answer was too technical, too long, or unclear about what he now has to do.
Claude Code
$ npx -y skills add Kanevry/session-orchestrator --skill eli5 --agent claude-code
Codex
$ npx skills add Kanevry/session-orchestrator --skill eli5 -a codex -y
Cursor
$ npx skills add Kanevry/session-orchestrator --skill eli5 -a cursor -y
Gemini CLI
$ npx skills add Kanevry/session-orchestrator --skill eli5 -a gemini-cli -y
GitHub Copilot
$ npx skills add Kanevry/session-orchestrator --skill eli5 -a github-copilot -y
OpenCode
$ npx skills add Kanevry/session-orchestrator --skill eli5 -a opencode -y
Windsurf
$ npx skills add Kanevry/session-orchestrator --skill eli5 -a windsurf -y
name: eli5 description: Explain a topic like I'm a 5 year old — restate my last output, or a named topic, in plain words without dropping a single fact. Use when the user types /eli5 [topic], or says an answer was too technical, too long, or unclear about what he now has to do. user-invocable: true argument-hint: "[topic]" model: inherit tools: Read, Grep, Glob, Bash
Say it again in plain words. Same facts, in the order he needs them.
Invoked as `/eli5 [topic]` with arguments: **$ARGUMENTS**.
The argument is optional and is a topic, in prose. If `$ARGUMENTS` is empty, the target is my own last substantial output in this conversation; if there is none yet, say so rather than picking a topic for him.
**Write for someone who knows this project but has not seen what you just saw.**
He owns this repo. He is not missing knowledge, he is missing observation — he did not watch the command run or read the file it points at. Write across, not down. The two limits below are the core of this register and suffice on their own. When the project defines its own register rule (session-orchestrator: `.claude/rules/ask-via-tool.md` § AUQ-006 and `skills/session-start/soul.md` § Register), that rule is the canonical statement; apply it, do not restate it.
Answer in the operator's language: `owner.language` from the owner config when the harness defines one (session-orchestrator: `~/.config/session-orchestrator/owner.yaml`), falling back to `en` when there is no such file, it is unreadable, or the key is absent — and follow the operator's own language the moment he writes in another one.
**1. Say more simply what actually happens — introduce nothing that does not exist.** Test: delete every noun the system does not contain. Sentence still true and complete → it was no analogy. Sentence collapses → describe what actually happens instead. ✓ "Waiting means the other session finishes first." ✗ "Think of the session as a level crossing."
**2. Simplifying removes words, never facts.** If a path, a number, an error code, an identifier, or an instruction to act disappears, that is data loss, not simplification. The mechanical decider: **could the token you are about to cut ever appear in a `grep`? Then it stays.** Never traded for brevity, and outranking every brevity instruction in this file: input validation and the reporting of invalid input; error messages and failure disclosure; security findings, warnings and destructive-action confirmations; accessibility of the output (no meaning carried by colour or emoji alone, no bare unlabelled numbers, no table without its header); anything he explicitly asked to see. When the project defines its own list (session-orchestrator: `skills/session-start/soul.md` § "Never traded for brevity"), that list wins on any difference.
Line 1 answers the question he actually has: **do I have to do something now, and what happens if I don't?** Then the facts, in the order he needs them — not the order you found them.
The output is text, so there is no picture to draw. When options differ in something literal — a diff, a title, a config block, a file list — show that text itself, so he reads the thing instead of a description of it: in the option's preview field where the harness has a question tool with one (Claude Code: `preview` on an `AskUserQuestion` option), otherwise in a fenced block directly under the option it belongs to.
Your coding agents get an agreed plan, a check after each round of changes and a handover to the next session. A free, MIT-licensed workflow plugin for people running Claude Code, Codex CLI, Cursor IDE or Pi on a git repository.
Use when the user asks to improve architecture, find refactoring opportunities, surface deepening opportunities, consolidate…
Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan → wave-executor →…
Use this skill when scaffolding the minimum repository structure required by session-orchestrator. Invoked automatically by the…
Use when you have a feature idea but the scope or UX is still ambiguous — runs a lightweight Socratic design dialogue (3-5 AUQ…
Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / _meta narrative and live repository state. Ten…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.