AI Socratic Dialogue Designer — teach students to interrogate AI answers critically (short listing)
Short listing — license not verifiable: design multi-round questioning sequences that probe AI chatbot answers, track how responses drift across rounds, and teach students to distinguish genuine logical updates from sycophantic capitulation
- What
- Short listing — license not verifiable: design multi-round questioning sequences that probe AI chatbot answers, track how responses drift across rounds, and teach students to distinguish genuine logical updates from sycophantic capitulation
- Cost
- Free
- Needs
- a classroom or tutoring context — an AI claim or answer to probe (interrogation topic) and a student level; no software or paid services
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Selected by Skill Harbor — short listing (the repo frontmatter carries no verifiable license and the discovery manifest records NOASSERTION — the manifest makes faith, so no content is reproduced): @garethmanning's ai-socratic-dialogue-designer skill — a serious, research-grounded lesson-design tool for AI literacy. Given an interrogation topic and a student level, it generates a multi-round Socratic questioning sequence for probing an AI chatbot's answers: establishing a baseline position, challenging evidence and assumptions, introducing counter-perspectives, then a deliberate "capitulation test" round (pure social pushback with no logical content) to reveal whether the AI changed its answer from argument or from agreeableness. It ships an answer-drift tracker protocol, a capitulation taxonomy (pure agreement, partial retreat, certainty softening vs genuine logical update), facilitation notes, and a debrief guide — citing Paul & Elder (Socratic question types), Walsh & Sattes, Nystrand et al., and the sycophancy/chain-of-thought literature. Honest caveats: license terms not verifiable — short listing with a link only, nothing copied; the AI-dialogue pedagogy is principled but empirically novel (the Socratic evidence base is for human dialogue); AI sycophancy rates vary by model; the capitulation test can provoke strong student reactions — plan for them; follow the source link and read the terms yourself before use. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
AI Socratic Dialogue Designer is a free Muse skill designing multi-round questioning sequences that probe AI chatbot answers, track how responses drift across rounds, and teach students to distinguish logical updates from capitulation. Given a topic and a student level, it generates a sequence establishing a baseline, challenging it, and testing whether later answers show real reasoning or mere agreement.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 6bbbce4Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a classroom or tutoring context — an AI claim or answer to probe (interrogation topic) and a student level; no software or paid services Install "AI Socratic Dialogue Designer — teach students to interrogate AI answers critically (short listing)" for me. It gives my agent @garethmanning's AI-literacy lesson design workflow: generate a multi-round Socratic questioning sequence for a given interrogation topic and student level, with an answer-drift tracker, a capitulation taxonomy (pure agreement, partial retreat, certainty softening vs genuine logical update), facilitation notes, and a debrief guide grounded in Socratic pedagogy and sycophancy research. IMPORTANT: the license terms were not verifiable (the discovery manifest records NOASSERTION) — fetch from the link only, reproduce nothing beyond the link, and read the terms yourself before use. Repository: https://raw.githubusercontent.com/garethmanning/education-agent-skills/6bbbce418f82e11044009c9f3b7373a354de5bd0/skills/ai-literacy/ai-socratic-dialogue-designer/SKILL.md Pinned version: install the code at commit 6bbbce418f82e11044009c9f3b7373a354de5bd0 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "ai-socratic-dialogue-designer". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. read the license terms before reuse; pick an interrogation topic and student level, then ask the agent to design the sequence). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 6bbbce4 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.