Install
$ agentstack add skill-jingyaliu-ml-rs-interview-agent-prep-planner ✓ 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.
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
Prep Planner
Goal
Fit prep into an employed schedule (default ~12–14 hr/week). Vault is source of truth — chat is ephemeral; files persist.
Inputs (read first, in order)
Learning-Vault/profile.md— identity, slots, prioritiesLearning-Vault/plan/THIS_WEEK.md— current week (may be stale)Learning-Vault/plan/ML_JOB_SEARCH_PLAN.md— milestones only (if present)- Quick scan:
behavioral/story-bank.md,ml-coding/practice-log.md,job-search/process-tracker.mdfor carry-overs
Workflow
- Date-check: If
THIS_WEEK.mdweek range ≠ current calendar week → refresh (archive old asYYYY_Wx.mdif needed). - Assess: Overdue items · Primary focus · energy constraints.
- Fit schedule: Map into weeknight / Sat deep / Sun process from profile.
- Write: Update
THIS_WEEK.mdwith day tables + checkboxes. - Today only: End with one block: task · minutes · file path ·
[ ].
Plan template rules
| Slot | Default | Content | |---|---|---| | Weeknight | 45–90 min | 1 primary block; optional 15-min micro | | Saturday | ~3 hr | ML/CS336 deep work | | Sunday | ~2 hr | Behavioral + outreach (early search: never empty) | | Low energy | see table | Minimum viable day — always include |
- Prefer finishing carry-overs before new topics
- Keep total ≤ profile time budget
- Link each block to a coach skill when useful
Output shape (chat)
Tonight (45–60 min)
1. [task] — path — N min
If tired: [minimum]
Then edit the vault file. Don't leave the plan only in chat.
Example prompts
| Say this | Expect | |---|---| | What should I do tonight? | One timeboxed block from profile + vault | | I only have 30 minutes and I'm tired | Low-energy minimum from plan | | Rebuild THIS_WEEK for this calendar week | Full week rewrite |
Handoff
- LC night →
leetcode-coach - Drill night →
cs336-coach - System design block →
system-design-coach - Sunday stories →
star-coach
Anti-patterns
- Scheduling beyond profile budget without asking
- Listing many tasks for one evening
- Motivational filler instead of a checkbox
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.