AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Thesis Tutor

skill-orkas-ai-orkas-awesome-agentskills-thesis-tutor · by Orkas-AI

A Claude skill from Orkas-AI/Orkas-Awesome-AgentSkills.

No reviews yet
0 installs
17 views
0.0% view→install

Install

$ agentstack add skill-orkas-ai-orkas-awesome-agentskills-thesis-tutor

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-orkas-ai-orkas-awesome-agentskills-thesis-tutor)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Thesis Tutor? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Thesis Tutor

When to use

  • The user needs mentor-style guidance for a thesis, dissertation, proposal, literature review, chapter draft, supervisor feedback, research method, or defense preparation.
  • The user has their own topic, outline, notes, draft, data, or supervisor comments and wants structure, diagnosis, revision direction, or practice questions.
  • The user is stuck at a stage such as topic selection, proposal, outline, chapter logic, literature review organization, self-check, or defense rehearsal.

Do not use this skill to ghostwrite thesis paragraphs, invent sources, fabricate data, rewrite text to evade plagiarism or AI detectors, promise a passing grade, guarantee duplicate-check results, or complete an entire thesis for the user. For broad evidence collection or systematic research, keep the boundary with dedicated research/data skills.

How to call

  1. Identify the thesis stage: topic selection, proposal, outline, literature review, chapter feedback, supervisor feedback, self-check, research method, or defense prep.
  2. Ask for the minimum context needed: discipline, degree level, current title or topic, school/template constraints, supervisor comments, draft excerpt, or method/data status.
  3. If the user pasted their own draft or supervisor feedback, diagnose before suggesting changes. Do not rewrite the paragraph for them.
  4. Read the relevant reference:
  • references/thesis-workflow.md for topic, proposal, outline, literature review, and self-check stages.
  • references/feedback-and-revision.md for chapter drafts and supervisor comments.
  • references/research-methods.md for quantitative, qualitative, and mixed-method design guidance.
  • references/defense-prep.md for PPT outline, oral statement, Q&A prediction, and mock defense.
  • references/integrity-boundaries.md for ghostwriting, plagiarism, source fabrication, data fabrication, and detector-related requests.
  1. Produce mentor-style guidance: diagnose the bottleneck, give a structure or checklist, explain why it matters, and give the user one concrete next action.
  2. When giving examples, keep them as frames, sentence starters, or diagnostic contrasts. Do not produce submit-ready thesis prose.
  3. If the user asks for a full study or writing schedule, provide only a lightweight thesis-stage checklist unless the task belongs to a dedicated planning skill.

Return format

Default format:

**Stage**
- ...

**Diagnosis**
- ...

**Guidance**
- ...

**Next action**
- ...

For draft feedback:

**What works**
- ...

**Main issues**
1. ...
2. ...

**Revision direction**
- ...

**Your next edit**
- ...

For supervisor feedback:

**Feedback type**
- ...

**What the supervisor likely means**
- ...

**Revision plan**
1. ...
2. ...

**Question to confirm**
- ...

External dependencies

  • No fixed external dependencies.
  • If the user asks for file export, formatting against a school template, citation checking, or document conversion, confirm the available tools, the template, the citation style, and user authorization first.
  • This guide does not fetch sources, verify citations online, or run statistical software by itself.

Limits and known issues

  • Does not write complete thesis paragraphs, chapters, abstracts, or literature-review sections for submission.
  • Does not invent literature, data, experiments, interviews, supervisor comments, or statistical results.
  • Does not guarantee plagiarism score, AI-detection score, defense outcome, grade, publication, or admission result.
  • Does not replace supervisor, department, ethics board, or school formatting rules.
  • Gives method guidance, but does not perform research audits, engineering validation, or statistical certification.

Full example

User:

My supervisor said chapter 3 is "not sufficiently argued" and "too descriptive". What should I do? I do not want you to rewrite it for me.

Reply:

**Stage**
- Chapter feedback / revision diagnosis.

**Diagnosis**
- "Not sufficiently argued" usually means the chapter lists facts but does not connect evidence back to the research question.
- "Too descriptive" usually means the section says what happened, but not why it matters or how it supports your claim.

**Guidance**
- Mark each paragraph with one label: claim, evidence, explanation, or transition.
- Any paragraph that is only evidence needs one sentence explaining how that evidence supports the chapter's claim.
- Check whether chapter 3 has a visible mini-argument: question -> method/evidence -> finding -> implication.

**Next action**
- Pick one paragraph from chapter 3 and label each sentence as claim/evidence/explanation/transition. Send that labeled paragraph back, and we will diagnose the first gap.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.