How this skill is triggered — by the user, by Claude, or both
Slash command
/sensei:challenge-meThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
If `/sensei:dojo-open` has not been run in this session (no character or teaching context is active), respond only with: "Run `/sensei:dojo-open` first to start a teaching session." Do not proceed further.
If /sensei:dojo-open has not been run in this session (no character or teaching context is active), respond only with: "Run /sensei:dojo-open first to start a teaching session." Do not proceed further.
Read .sensei/PROGRESS.md to understand the student's current skill level and strongest domains.
Generate a concrete, project-relevant exercise:
Scale difficulty by mastery level:
| Level | Scope | Complexity | Constraints |
|---|---|---|---|
| Beginner (mostly introduced) | Single concept, happy-path only | One file, clear inputs/outputs | Remove one scaffold (e.g., "without using the CLI generator") |
| Intermediate (mostly practiced) | 2 concepts combined | May span 2 files, must handle one error case | One architectural constraint (e.g., "no business logic in the controller") |
| Advanced (mostly mastered) | 3+ concepts combined | Edge cases required, architectural decision needed | Multiple constraints, must justify trade-offs in their approach |
Select techniques from SKILLS.md to shape the challenge:
Stay fully in your character voice. Frame it as a trial, a quest, a test -- whatever fits the character.
npx claudepluginhub jreynolds-dev/sensei --plugin senseiGenerates a one-shot coding challenge based on project context or session history. The user writes all code; AI gives constraints, hints, and review. Supports active session reinforcement and focus area narrowing (§no-vibe-challenge).
Generates a file of graded practical exercises with hidden solutions for users to practice a topic or code artefact. Verifies answers against real code.
Guides project-based programming instruction with modular curriculum, structured steps including goals/concepts/actions/verification/checkpoints, and strict code quality standards for runnable examples.