tobihagemann/turbo / claude/skills/route-lessons
route-lessons
VerifiedRoute lessons to instructions, auto memory, skills, the backlog, or a Turbo handoff after approval. Use when asked to "route lessons" or "where should this lesson go".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.7 KB |
| references/package-managed-skills.md | markdown | 1.3 KB |
| references/turbo-skill-lessons.md | markdown | 1.1 KB |
references/turbo-skill-lessons.md
View on GitHub# Turbo Skill Lessons
**When `checkout` is set:** write every lesson routed to a turbo skill into one handoff file with the Write tool, at `<checkout>/.turbo/handoff/<YYYY-MM-DD>-turbo-lessons-<slug>.md`, where `<slug>` names the lessons' common subject. When that path already exists, append `-2`, `-3`, and so on to the slug until it is free. State the resolved path before writing. Record for each lesson:
- Which turbo skill it targets, as a path under `claude/skills/<name>/` in the checkout
- The change to make and where in the file it belongs
- The evidence that motivated it, and its origin
**When `checkout` is unset:** use `AskUserQuestion` to ask whether to propose each turbo skill lesson upstream. Ask one question per lesson, at most four per call. Write each lesson the user leaves out to **Auto memory** as Step 6 item 2 writes it, recording the turbo skill it applies to, except a lesson whose origin already sits in Auto memory, which needs no write and is reported as kept where it is. Then, when any lesson remains to propose, run the `/contribute` skill once for all of them, passing each lesson's target skill, change, and evidence.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |