DeepTutor CLI
HKUDS/DeepTutor
Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.
KB-grounded Socratic interview. An agent skill from Abilityai/cornelius.
Install Insight Interview
$ npx skills add Abilityai/cornelius --skill insight-interview -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Abilityai/cornelius insight-interview --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/insight-interview .claude/skills/insight-interview && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "insight-interview" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/insight-interview into .claude/skills/insight-interview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "insight-interview", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Abilityai/cornelius/tree/main/.claude/skills/insight-interviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Abilityai/cornelius --skill insight-interview -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Abilityai/cornelius insight-interview --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/insight-interview .agents/skills/insight-interview && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "insight-interview" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/insight-interview into .agents/skills/insight-interview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "insight-interview", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Abilityai/cornelius --skill insight-interview -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Abilityai/cornelius insight-interview --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/insight-interview .cursor/skills/insight-interview && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "insight-interview" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/insight-interview into .cursor/skills/insight-interview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "insight-interview", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Abilityai/cornelius.git --path .claude/skills/insight-interview--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Abilityai/cornelius --skill insight-interview -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Abilityai/cornelius insight-interview --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/insight-interview .gemini/skills/insight-interview && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "insight-interview" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/insight-interview into .gemini/skills/insight-interview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "insight-interview", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Abilityai/cornelius insight-interviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Abilityai/cornelius --skill insight-interview -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/insight-interview .github/skills/insight-interview && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "insight-interview" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/insight-interview into .github/skills/insight-interview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "insight-interview", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Abilityai/cornelius --skill insight-interview -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Abilityai/cornelius insight-interview --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abilityai/cornelius.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/insight-interview .opencode/skills/insight-interview && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "insight-interview" agent skill from https://github.com/Abilityai/cornelius/tree/main/.claude/skills/insight-interview into .opencode/skills/insight-interview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "insight-interview", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
insight-interview- GitHub stars
- 109
- Token cost
- ~1.6k tokens
- SKILL.md length
- 769 words
- Files
- 1
- Skills in repo
- 51
- Repo updated
- First seen
- Licence
- MIT
At a glance
KB-grounded Socratic interview. An agent skill from Abilityai/cornelius.
- Works in 7 steps: Search the KB → Map the Frontier → Open the Dialogue → …
- Tasks that involve Tutoring and explanations
- SKILL.md covers Purpose, State Dependencies, Process and Dialogue Principles, plus 2 more sections
- Calls python
What it does
Insight Interview is an agent skill from Abilityai/cornelius. KB-grounded Socratic interview. Searches existing notes on a topic, then runs a one-question-at-a-time dialogue to surface, sharpen, and extract your own thinking. Ends by running extract-insights on the full conversation transcript.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Education, covering Tutoring and explanations. The repository describes itself as: AI-powered second brain template for Claude Code + Obsidian. The licence is MIT.
When your agent uses it
- Tasks that involve Tutoring and explanations
Example prompts
- “/insight-interview”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Bash, Read, Write, Glob, Grep, Task
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit fd5e9a4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashReadWriteGlobGrepTask
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Insight Interview loads about 1.6k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 769 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Read, Write, Glob, Grep, Task
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Abilityai/cornelius at commit fd5e9a4, republished under its MIT licence (© Abilityai). 769 words, ~1,650 tokens.
Download SKILL.mdSave it as
.claude/skills/insight-interview/SKILL.md (or your agent's skills folder).- name
- insight-interview
- description
- KB-grounded Socratic interview. Searches existing notes on a topic, then runs a one-question-at-a-time dialogue to surface, sharpen, and extract your own thinking. Ends by running extract-insights on the full conversation transcript.
- allowed-tools
- Bash, Read, Write, Glob, Grep, Task
- automation
- manual
- user-invocable
- true
- argument-hint
- <topic>
Insight Interview
A Socratic dialogue grounded in your own knowledge base. It finds what you already think, then probes the edges - gaps, underdeveloped claims, contradictions, missing connections - one question at a time. Your responses feed directly into the vault at the end.
Purpose
Not to summarize a topic. Not to explain research. To find out what you actually think - and make that thinking precise enough to live in the knowledge base.
The KB is the context, not the content. Every question is anchored in a note you already wrote.
State Dependencies
| Source | Location | Read | Write |
|---|---|---|---|
| Existing notes | Brain/ via Local Brain Search | ✓ | |
| Permanent notes | Brain/02-Permanent/ | ✓ | |
| Dialogue transcript | resources/insight-interview-[slug]-[date].md | ✓ | |
| Extracted insights | Brain/AI Extracted Notes/ | ✓ (via extract-insights) |
Process
Step 1: Search the KB
Run semantic search on the topic using Local Brain Search:
cd resources/local-brain-search && python search.py "[topic]" --top_k 15 --mode spreadingAlso run a keyword grep across permanent notes:
grep -rl "[topic keywords]" Brain/02-Permanent/ Brain/AI\ Extracted\ Notes/ | head -20Read the top 8-10 results. Understand:
- What the user already believes about this topic
- Which claims are well-developed vs. sketched
- Where tensions or contradictions exist between notes
- What connections are asserted but not fully argued
- What's notably absent (a gap where you'd expect a note)
Step 2: Map the Frontier
Before asking anything, internally map 5-7 candidate question zones:
- Existing claim to probe: A strong assertion in a note that could be sharpened or challenged
- Gap: An angle you'd expect him to have thought about but haven't found
- Contradiction: Two notes that pull in opposite directions
- Connection: A note that seems related to another topic he knows well - does he see it?
- So-what: A well-documented insight with no clear practical implication
- Origin: A belief stated as fact - where did it come from?
- Frontier: The newest or most uncertain note - what's unresolved?
Prioritize. You'll likely cover 5-8 of these in a session.
Step 3: Open the Dialogue
Introduce with one sentence of context showing what you found in the KB, then ask the first question. Keep it grounded - reference the specific note or claim:
"You have a note [[X]] where you say '[direct quote or paraphrase]'. Given [new angle / related note / recent development], do you still hold that? Or has your view shifted?"
OR for a gap:
"You have strong thinking on [A] and [B], but I didn't find anything on [C] - which sits right between them. What's your actual take?"
One question only. Wait for the response.
Show full SKILL.md (383 more words)Show less
Step 4: Dialogue Loop
After each response, decide:
- Deepen this thread: The answer opened something - follow it (ask for evidence, for the counterargument, for the implication)
- Mark and move: Useful answer, but another zone is more promising - transition to the next question
- Capture and close: The response crystallized something - reflect it back precisely, confirm it's right, then move on
Question types to cycle through (from elicitation-techniques):
| Type | When to use | Example |
|---|---|---|
| Clarification | Vague or assumed term | "What exactly do you mean by [X] here?" |
| Assumption excavation | Strong claim stated as fact | "What would have to be false for this not to hold?" |
| Counterargument | One-sided note | "What's the strongest case against this?" |
| Connection probe | Two related notes not linked | "Does this relate to your thinking on [Y]?" |
| Implication | Well-documented insight with no so-what | "If this is true, what changes?" |
| Origin | Belief with no cited source | "Where does this come from? Experience, reading, both?" |
| Precision | Fuzzy claim | "How strong is this? Always? Sometimes? Under what conditions?" |
Aim for 6-10 exchanges. Stop when:
- You've covered the main frontier zones
- The conversation is producing diminishing returns
- The user says "done", "enough", or similar
Step 5: Close
Before ending, ask one final open question:
"Is there anything on this topic that you think is important but we haven't touched?"
Give space for any loose threads.
Step 6: Save Transcript
Create a transcript file combining the full dialogue:
resources/insight-interview-[topic-slug]-[YYYY-MM-DD].mdFormat:
# Insight Interview: [Topic]
**Date**: YYYY-MM-DD
**KB notes consulted**: [list of note titles]
**Questions asked**: [count]
---
**[Question 1]**
[Response]
**[Question 2]**
[Response]
...
---
*Raw transcript for extract-insights processing*Step 7: Run Extract-Insights
Invoke the extract-insights skill on the transcript:
/extract-insights resources/insight-interview-[topic-slug]-[YYYY-MM-DD].mdThis will:
- Deduplicate against existing KB
- Extract new insights in your voice
- Create or update notes in
Brain/AI Extracted Notes/ - Log changes in
Brain/05-Meta/Changelogs/
Report what was created or updated.
Dialogue Principles
- One question at a time. Always. No lists of questions.
- Show your work. Reference the specific note you're drawing from. This makes it feel like a conversation with someone who read your stuff, not a generic interview.
- Don't summarize back every time. Only reflect back when something crystallized - and then be precise.
- Follow energy. If a response is animated or detailed, stay in that thread.
- Don't lead. The question opens space; it doesn't suggest the answer.
- Tolerate "I don't know". That's a real answer. Ask what would need to be true to know.
Outputs
- Dialogue transcript:
resources/insight-interview-[slug]-[date].md - Extracted insight notes:
Brain/AI Extracted Notes/ - Changelog entry:
Brain/05-Meta/Changelogs/
Usage
/insight-interview self-improving agents
/insight-interview dopamine and motivation
/insight-interview the folder paradigm© Abilityai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/insight-interview of Abilityai/cornelius.
Open the folder on GitHubat commit fd5e9a4
Compare with similar skills
Insight Interview next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Insight Interview this skillAbilityai/cornelius | 109 | — | ~1.6k | Automated safety check: Notes | MIT | |
| DeepTutor CLIHKUDS/DeepTutor | 41k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| AI Engineering Project Tutorrohitg00/ai-engineering-from-scratch | 66k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Hung-Yi Lee Teaching Stylevoidful/hung-yi-lee-skill | 1.3k | — | ~13k | Automated safety check: Pass | None | |
| Claude Certification Tutorrohitg00/ai-engineering-from-scratch | 66k | — | ~3k | Automated safety check: Pass | MIT | |
| StudyVault Quiz Tutorbevibing/tutor-skills | 1.3k | — | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
AI Engineering Project Tutor
rohitg00/ai-engineering-from-scratch
Tutors a learner through one stage of a hands-on AI engineering project per session: lesson, prediction, code, grader run and reflection, with hints but never full solutions.
Hung-Yi Lee Teaching Style
voidful/hung-yi-lee-skill
Explains machine learning, LLMs, AI agents and speech modeling in a Hung-Yi Lee-inspired teaching style, drawing on a knowledge base built from his lectures and research references.
Claude Certification Tutor
rohitg00/ai-engineering-from-scratch
Guides a learner through one of four independent Claude certification tracks with onboarding, lessons, practice labs, mock exams and remediation.
StudyVault Quiz Tutor
bevibing/tutor-skills
Quizzes you on the notes in an Obsidian StudyVault, tracks proficiency per concept and drills weak areas in four-question rounds.
Zone of Proximal Development Practice Lessons
THU-MAIC/OpenMAIC
Designs a review-and-practice lesson around an independent first attempt, targeted feedback, supported practice, a fresh independent check and a next step.
More from Abilityai/cornelius
All 51 skills in this repoNano Banana Image Generator
Abilityai/cornelius
Generate images using Google's Nano Banana (Gemini 2.5 Flash Image).
Changelog Protocol
Abilityai/cornelius
Protocol for creating dated changelog files after significant agent sessions.
Create Article
Abilityai/cornelius
Create long-form articles from knowledge base insights. An agent skill from Abilityai/cornelius.
Epistemic Classification
Abilityai/cornelius
Framework for distinguishing research findings from hypotheses and speculative synthesis.
Get Youtube Transcript
Abilityai/cornelius
Extract the transcript from a YouTube video by URL or video ID.
Insight Capture Format
Abilityai/cornelius
Standard format for capturing and documenting insights in the knowledge base.
Related
Categories
Questions about Insight Interview
What does Insight Interview do?
KB-grounded Socratic interview. An agent skill from Abilityai/cornelius. Insight Interview is an agent skill from Abilityai/cornelius. KB-grounded Socratic interview.
When should I use Insight Interview?
Insight Interview fits situations like: tasks that involve Tutoring and explanations.
How do I install Insight Interview in Claude Code?
Run `npx skills add Abilityai/cornelius --skill insight-interview -a claude-code`. Or copy the skill folder (.claude/skills/insight-interview in Abilityai/cornelius) into .claude/skills/insight-interview in your project. Claude Code loads it when a task matches its description.
How do I install Insight Interview in Codex?
Run `npx skills add Abilityai/cornelius --skill insight-interview -a codex`. Or copy the skill folder (.claude/skills/insight-interview in Abilityai/cornelius) into .agents/skills/insight-interview in your project. Codex loads it when a task matches its description.
Can I use Insight Interview in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Abilityai/cornelius --skill insight-interview -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/insight-interview, .gemini/skills/insight-interview, .github/skills/insight-interview and .opencode/skills/insight-interview in your project.
What does Insight Interview need to run?
Going by SKILL.md and its folder, Insight Interview needs the command-line tools its instructions call (python). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Read, Write, Glob, Grep, Task.
Does Insight Interview access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Insight Interview safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Insight Interview use?
Insight Interview is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Insight Interview use?
About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Insight Interview?
Skills that share tags, products or a category with Insight Interview: DeepTutor CLI (HKUDS/DeepTutor, 41k stars), AI Engineering Project Tutor (rohitg00/ai-engineering-from-scratch, 66k stars), Hung-Yi Lee Teaching Style (voidful/hung-yi-lee-skill, 1.3k stars) and Claude Certification Tutor (rohitg00/ai-engineering-from-scratch, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Insight Interview?
Abilityai (a GitHub organization) maintains it in Abilityai/cornelius, which has 109 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on September 22, 2026.
Source: Abilityai/cornelius on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.