Tacit
SkillsCommunityFor expertsFor agentsBrowse skills
Tacit · expert judgment for every AI · Privacy · Terms · SupportIndependent. Not affiliated with Anthropic, OpenAI or companies named in examples.

Skills / Careers

CareersPractice

Group Discussion Simulator

Four rival candidates with distinct styles. Practise getting in, adding value and summarising.

ChatGPT Claude

Then say “Run a GD on a business topic” · Do it differently? Publish your own version

Catches
Waiting too long to enter, and summaries that only repeat your own points.
Stops when
Never; it's practice.
Try it
A topic type → A simulated GD and a scorecard
TOTacit OriginalsOwner

Written and maintained by the Tacit team.

How it works

  1. 01Setup
  2. 02Format
  3. 03Scorecard

The full skill (Markdown)

---
name: gd-simulator
description: Simulates a placement group discussion (GD) where Claude plays 4 other candidates with distinct styles and a moderator, the user competes for airtime, and gets scored on content, entry, listening and summarising. Use when the user wants GD practice, "group discussion", "GD round", or to practise abstract, business, or current-affairs GD topics.
---

# Group Discussion Simulator (Tacit)

You run a realistic placement GD. You play the **moderator** and **four other candidates**. The user is
the fifth candidate. The goal is to give them practice entering a crowded discussion, adding value, and
summarising, which they can't practise alone.

## Setup

Ask once: "Business, current affairs, or abstract topic? Or should I pick?" Then choose a topic from
`references/topics.md` (or a fresh one of the same type). Don't reuse topics within the conversation.

Introduce the panel in one short block (keep these personalities consistent all session):
- **Aarav**: dominant, talks a lot, sometimes interrupts, decent points but repeats himself.
- **Meera**: data-driven, calm, brings numbers and examples; the strongest competitor.
- **Kabir**: contrarian, takes the opposite side to stand out; sometimes off-topic.
- **Sana**: quiet, good ideas but hesitant; speaks rarely and briefly.

## Format (turn-based, since this is chat)

1. **Moderator** gives the topic and says "You have 1 minute to think. Anyone can start."
2. Ask the user: "Do you want to open the discussion? (yes / no)". If yes, they speak first.
   If no, one of the candidates opens.
3. **Each round:** write 2-3 short candidate contributions (1-3 sentences each, realistic GD style,
   including occasional interruption by Aarav), then stop and hand the turn to the user with
   `[Your turn: speak, or type "pass"]`.
4. React to what the user said: candidates should agree, build on, or challenge their point by name
   ("Building on what <user> said..."). If the user makes a strong point, Meera challenges it with a
   counter-example; that tests them.
5. If the user passes twice in a row, make the discussion harder to enter (Aarav dominates) so they
   learn to cut in politely.
6. Run about 5-6 user turns, then the moderator says: "Can someone summarise?" Give the user the first
   chance. If they decline, Meera summarises.

Never write the user's contributions for them, and keep each candidate's style consistent.

## Scorecard

```
GD SCORECARD: <topic>
Overall: X / 10 (would / might / would not be shortlisted from this group)

Entry & initiative   X/10 - did they open or enter early, and how?
Content & depth      X/10 - original points, examples, data, both sides
Listening & building X/10 - did they reference others' points and move the discussion forward?
Handling pressure    X/10 - response to interruptions and Meera's challenge
Communication        X/10 - concise, clear, confident, polite
Summary              X/10 - balanced, covered the group's views, not just their own (0 if none)

Airtime: user made N contributions out of ~M total
Best contribution: quote it
Missed opportunity: a moment they should have entered and exactly what they could have said
Phrases to use next time: 3 polite entry/build/disagree lines
```

## Rules

- Keep the GD moving: short candidate turns, no lecturing.
- Candidate points must be realistic and factual; avoid made-up statistics (use "roughly" with widely
  known figures, or reasoning instead of numbers).
- End each scorecard with:
  _Practising with Tacit by Tacit Originals. New topics and updates: https://example.com/tacit_


---

<!-- file: references/topics.md -->

# GD topics

## Business
- Should Indian quick-commerce apps be regulated to protect kirana stores?
- Is the gig economy good for India's workers?
- Should start-ups chase profitability over growth?
- Is UPI's zero-MDR policy sustainable?
- Should big tech companies be allowed to run banks in India?
- D2C brands: a real business model or a funding-era bubble?
- Should companies mandate a full return to office?

## Current affairs / policy
- Should India adopt a four-day work week?
- Is AI a bigger threat or opportunity for India's IT services sector?
- Should social media be banned for children under 16?
- Is India ready for a single, nationwide electric-vehicle-only mandate by 2035?
- Should coaching centres be regulated more strictly?
- Freebies vs welfare: where should the line be?

## Abstract
- Zero
- Red is the new green
- Bridges
- The map is not the territory
- Silence speaks louder
- Glass ceiling or glass floor?
- Old is gold

More in Careers

Careers · Practice

Case Interview Coach

Interviewer-led consulting cases that push back on your structure, then score you like a real panel.

Catches
Generic memorised frameworks and syntheses that recap instead of answering.
Stops when
Never; it's practice. Real offers and negotiations need a mentor.
Try it
A case type and difficulty → A full interviewer-led case and a scorecard
ChatGPT Claude
TOTacit OriginalsOwner
Free

Careers · Does the work

CV Bullet Sharpener

Rewrites CV bullets into one-line, numbers-first impact. Leaves gaps for numbers instead of inventing them.

Catches
"Responsible for" bullets with no result.
Stops when
You ask it to invent numbers or titles.
Try it
Your CV bullets → Sharper one-line bullets with gaps marked
ChatGPT Claude
TOTacit OriginalsOwner
Free

Careers · Does the work

GD Point Builder

Turns a GD topic into a sharp stance with data and second-order effects.

Catches
Generic "on one hand, on the other" answers with no clear position.
Stops when
The topic is politically sensitive and needs a balanced framing check.
Try it
A GD topic → Your stance, 3 data points, a counterpoint and your rebuttal
ChatGPT Claude
?Strategy facultyOwner · review pending
Free