PranitMohnot/repo-learner-suite / repo-learner
repo-learner
VerifiedOrchestrator for the repo-learner skill suite. Routes /learn commands to specialized sub-skills for analyzing codebases, generating exercises, tutoring, and quizzing. Trigger on any /learn command, "help me learn this repo", "teach me this codebase", "I want to understand this project", or any request to systematically learn a codebase. Also trigger when the user references an existing learn/ directory.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 16.0 KB |
| commands/learn.md | markdown | 1.1 KB |
| gemini.skill-meta.yaml | config | 171 B |
| scripts/reconcile.py | script | 11.7 KB |
commands/learn.md
View on GitHub# /learn
Entry point for the repo-learner skill suite.
## Routing
Parse the first word of $ARGUMENTS as the subcommand. If empty, check state and
recommend ONE action (see orchestrator SKILL.md for the logic — never dump a menu).
| Subcommand | Sub-skill |
|---|---|
| `analyze [path] [--focus topic]` | repo-analyzer |
| `exercises [section]` | exercise-gen |
| `tutor [section-id]` | code-tutor |
| `quiz [section-id\|--full]` | code-quiz |
| `status` | Parse `learn/README.md` checkboxes, summarize progress |
## Fresh run (no learn/ directory)
1. Auto-detect: primary language, framework, lockfile/package manager.
2. **MANDATORY: Ask 3-4 questions in one call** (see orchestrator SKILL.md
"Front-Loaded Questions"). Do NOT skip this and assume defaults — the user
has preferences (especially env manager) that you cannot infer.
3. Save answers to `learn/internals/.config.json`.
4. Hand off to repo-analyzer, then exercise-gen. No stops between.
## Status
Parse checkbox state from `learn/README.md` table rows. Count checked vs unchecked
per phase. Suggest the next unchecked section.
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: 471k | 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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |