momo-land/PHD-management-skills / skills/phd-defense
phd-defense
Verified依据真实论文与结果准备答辩论证、追问和限时回答,适用于开题或毕业答辩演练,明确区分 AI 模拟与真实评委意见。
| File | Kind | Size |
|---|---|---|
| SKILL.en.md | markdown | 3.5 KB |
| SKILL.md | skill md | 3.0 KB |
| agents/openai.yaml | config | 322 B |
SKILL.en.md
View on GitHub---
name: phd-defense
description: Prepare evidence-grounded defense arguments, follow-up questions and timed answers for proposal or thesis defenses, clearly labeling AI simulation.
---
# Defense preparation
## Prepare actual defense material
Identify the defense type, duration, audience and readable thesis or outline. Reuse supplied context and ask only about gaps that change the rehearsal focus.
Without a complete thesis, limit the exercise to accessible chapters or plans rather than claiming full research review.
## Explain the contribution clearly
1. Extract the question, its value, main contributions, strongest evidence and remaining limitations.
2. Give each central claim an evidence location and concise explanation, distinguishing personal contributions, collaborative work and prior work.
3. Fit the narrative of question, method, evidence, contribution and limits to the available time, prioritizing material that supports conclusions.
4. Generate questions from actual material about choices, controls, validity, alternatives, reproducibility and boundaries rather than a generic question list.
5. Structure answers as direct response, reason/evidence and boundary. State unknowns and a validation path instead of inventing existing results.
6. During simulation, ask a manageable set of questions and follow up on the user's actual answers, distinguishing reasoning, evidence and expression issues.
7. Summarize difficult follow-ups, relevant evidence, missing material and the next rehearsal focus.
## Deliver a defense preparation package
Provide the requested narrative outline, key questions and answers, evidence index, timed-length version or rehearsal feedback.
Label feedback AI simulation; do not attribute it to real supervisors or committee members or promise a probability of passing.
Report elapsed presentation time only if measured. A word-count estimate must be labeled and state language/speaking-rate assumptions.
## Capability and follow-up boundaries
- Text capabilities support outlines and questions; without audio or timing, do not claim to assess pronunciation, speaking speed or actual duration.
- Use [research presentations](../phd-slides/SKILL.en.md) and available tools when files are requested. Without them, provide slide-by-slide content without calling it a completed presentation file.
- Without thesis evidence, rehearse the research plan rather than fabricating completed achievements.
- Save requested rehearsal feedback as AI-origin reviews. Preserve the source of real defense feedback without inventing meetings.
- Prepared does not mean passed, and rehearsal does not automatically change papers, projects or tasks.
## Workspace synchronization (only when requested)
Read the [local workflow](../phd-manager/references/local-workflow.en.md), locate the actual repository and project, and preserve the current PHD_DATA_DIR.
Discussion, translation, drafts and suggestions do not automatically change research state. Deliver requested files to the selected directory, or outputs/ when unspecified.
For requested saves, use the CLI to read the target and current version; preserve notes, relations and user-estimated percentages rather than editing the database directly.
Use user for user facts, import for external material and ai for AI plans/assessments, preserving provenance and actual verification scope.
Validate a batch before applying multiple changes and read back successful writes before reporting them as saved. Add no fields outside the contract.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |