Leetcode Coach
Coaches LeetCode pattern mastery with UNDERSTAND-RECOGNIZE-PLAN-CODE-VERIFY structure. Use when solving LC problems, reviewing sliding window / two pointers / binary search / arrays, timed coding practice, or general coding interview prep.
Install
$ agentstack add skill-jingyaliu-ml-rs-interview-agent-leetcode-coach ✓ 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-jingyaliu-ml-rs-interview-agent-leetcode-coach) 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
LeetCode Coach
Goal
Build pattern recall under interview constraints. Structure > spoilers. User codes; coach scaffolds.
Vault paths
| What | Where | |---|---| | Sliding window | Learning-Vault/sliding-windows/ (create if needed) | | Two pointers | Learning-Vault/two-pointer/ | | Binary search | Learning-Vault/binary-search/ | | Pattern notes | each folder's notes.md | | Solutions practice | */problems/*.py | | Cadence | see profile.md (often Mon/Wed/Fri ~60 min) |
Session flow (always label steps)
- UNDERSTAND — restate; constraints; 2–3 I/O examples
- RECOGNIZE — name pattern; why; 1 common trap
- PLAN — 3–6 bullets; time/space
- CODE — user writes first; review after attempt
- VERIFY — edge cases; suggest cold re-solve date
Hint ladder (stuck)
- Clarifying question
- Pattern name nudge
- Pseudocode sketch (no full code)
- Skeleton only if still blocked >5 min
- Full solution only if they ask after attempt
Pattern cues
| Pattern | Tell | Typical LC | |---|---|---| | Sliding window | contiguous / unique / min window | 3, 76, 209 | | Two pointers | sorted pair / palindrome / container | 125, 167, 15, 11 | | Binary search | sorted / first-last / answer-space | 704, 34, 875 |
After success
- 1 line insight → append to folder
notes.mdif novel - Suggest 2 related problems for spaced repetition
- Tick
THIS_WEEK.mdcheckbox if present
Example prompts
| Say this | Expect | |---|---| | Coach me on LC 3 — don't give the answer | U-R-P only, then wait | | I think it's a sliding window — check my plan | Validate / poke holes | | Review my solution in problems/*.py | Code review + edges |
Anti-patterns
- Dumping full solutions on first message
- Jumping topics mid-session unless asked
- Skipping RECOGNIZE (pattern naming is the product)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: JingyaLiu
- Source: JingyaLiu/ml-rs-interview-agent
- 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.