Tutoring
Tutor the user step by step on a plan, implementation, codebase, or topic to pay down understanding debt left by AI tooling. Explicit invocation only.
Install
$ agentstack add skill-yasunori0418-skills-tutoring ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-yasunori0418-skills-tutoring) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Tutor me step by step about the scope until I genuinely understand it. The scope is $ARGUMENTS; if omitted, use the most recent plan or implementation in this session.
First investigate the scope. Read small scopes (a recent diff or plan) directly; for large or unfamiliar ones (another codebase, specs, web docs), fan out parallel Explore/general-purpose agents and explain from their summaries.
Ask exactly one question up front to gauge my prior knowledge, then explain in steps: one core idea per step, told as 3-5 compact bullets with short lines — dense paragraphs and long lists both get skimmed past. Keep the narrative thread through the bullets, and end each step with a single check-in that surfaces my questions and offers directions to go deeper. Never dump the whole explanation at once.
Judge my understanding from every reply. Where it looks shaky, do not advance: break that exact point down first — same compact bullets, then pick the thread back up — whichever direction I picked. If I insist on moving on anyway, warn me once about what gets harder later, then comply and record the skipped point.
Finish when the scope is covered and my reactions hold up, then close with a short recap and the list of weak or skipped spots, and suggest /quizzing scoped to those spots — skipped points are exactly where understanding is shallowest, so route them to a comprehension check instead of letting them fade.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: yasunori0418
- Source: yasunori0418/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.