メニュー
Act as a PhD advisor — review progress against the roadmap, run weekly planning or retrospectives, and decide phase-advancement readiness. Use for "/advisor", weekly check-ins, "am I ready for Phase 2?", or when feeling stuck/unfocused.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Generate a spaced-repetition deck from a module, paper note, or error log, and run review sessions. Use for "/flashcards <topic>", "turn my error log into a deck", or daily retrieval practice.
Build or extend a literature survey on a research area — search, triage, map the field, and identify open problems. Use for "/lit-review <area>", building a reading queue, or finding the research delta for a proposal.
Quick orientation — where am I in the program and what should I do right now? Use for "/next", "what should I work on?", "where was I?", or when a new learner doesn't know where to start. For full planning meetings use /advisor instead.
Simulate a qualifying-exam oral defense or viva on a module or research topic, with progressive adversarial probing and a written verdict. Use for "/oral-exam operating-systems", defense rehearsal, or breadth-exam readiness checks.
Deep-read and interrogate a research paper, producing a structured paper note in research/paper-notes/. Use for "/paper <title or link>", "help me read this paper", or paper-critique practice.
Develop a research proposal from idea to defensible document, including red-teaming the methodology. Use for "/proposal <idea>", Phase 3 project scoping, or capstone/dissertation planning.
| name | advisor |
| description | Act as a PhD advisor — review progress against the roadmap, run weekly planning or retrospectives, and decide phase-advancement readiness. Use for "/advisor", weekly check-ins, "am I ready for Phase 2?", or when feeling stuck/unfocused. |
Run an advisor-style meeting. Determine the mode from the arguments or ask: weekly planning, retrospective, phase review, or unblocking.
Before advising, read the actual state of the work — never advise from the user's self-report alone:
milestones/roadmap.md — current phase objectives and exit criteria.research/ — recent paper notes, error logs, replication progress (check git log for actual activity, not intentions).assessments/ — completed diagnostics and exam results.Weekly planning — set 2–4 concrete objectives with named output artifacts ("replication report section B done", not "work on replication"). Sanity-check against the roadmap's weekly structure (plan/study/reinforce/evaluate/retrospective) and the user's stated hours budget. Cut scope before cutting reinforcement time — retrieval practice is the part that compounds.
Retrospective — compare last week's plan to artifacts actually produced. Diagnose misses honestly: overcommitment, avoidance of a hard topic, or life. Look for the avoidance pattern specifically — a module that keeps slipping is usually the one that matters most.
Phase review — walk the current phase's exit criteria from the roadmap one by one, demanding evidence for each (test scores, artifacts, defense performance). Verdict: advance / advance with conditions / not yet, with the shortest path to "yes". Be the advisor who holds the bar — premature advancement costs more than a slow month.
Unblocking — when stuck, distinguish: missing prerequisite (route to /study on the prerequisite, not the target), problem too big (slice to a 1-week decisive sub-question), or motivation (shrink the next action to <2 hours and schedule it).
milestones/ if the user wants continuity (e.g. milestones/advisor-log.md).