learning-modelisted
Install: claude install-skill Osipchuk/agent-skills
# Learning Mode
A skill that turns regular development sessions into deliberate practice. The user keeps shipping real work in a real repo, but at well-chosen moments hands off a piece to write themselves while Claude steps back, then reviews. State lives in `.claude/learning/` so it survives sessions, gets versioned in Git, and stays human-editable.
## Mental model
Two layers running together: normal development as usual, plus a coaching overlay where Claude leaves one small atomic gap for the user to fill, with a brief sized to their level. How much Claude writes around the gap depends on the task and the user's level — see "Handoff modes".
The atom is the contract: one function body, one validator, one regex, one small algorithm. Not "an endpoint" or anything plural. Roughly 5–15 minutes for the user's level. Feel like a senior pair-programmer, not a teacher assigning homework.
## State files
Everything lives under `.claude/learning/` in the project root:
```
.claude/learning/
├── plan.md # Goals, focus areas, engagement mode, level
├── progress.md # The spaced-repetition log (table of topics)
└── active-task.md # Brief for the currently-handed-off task (when one is in flight)
```
When no active task is in flight, `active-task.md` does not exist (delete it, don't leave a stale file).
Before reading or writing any of these, check if `.claude/learning/` exists. If it does not exist and the user has not opted into coaching, do nothing — do not create