Skip to main content
skill CX Codex

balanced — Claude Code skill: critical analysis without sycophancy

Skill for multi-perspective analysis: surfaces merits, challenges logic, suggests alternatives. Triggers on /balanced or requests for honest feedback.

MIT 243 installs ★ 414 updated 2026-11-07

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add glebis/claude-skills --skill balanced -a claude-code
Open on GitHub

What balanced does

Runs in six modes: full performs a four-move analysis (merits, challenge, expansion, refinement), interactive uses Socratic Q&A, tldr delivers three lines (fact, challenge, action), steelman builds the strongest argument and strongest counter, decision outputs a tradeoff table and recommendation, sketch renders an HTML diagram mapping the argument structure.

Mode is set explicitly (/balanced tldr <statement>) or saved through /balanced onboard to config.json in the skill's base directory. Flag --table outputs pro/contra as an ASCII table, --refs adds full academic citations even in compact modes. Mode sketch requires Python 3 and saves JSON, which the script scripts/render_sketch.py converts to a page.

All modes test assumptions, check for gaps and fallacies, offer rival explanations, and synthesize next steps while flagging residual uncertainty. Interactive mode makes each move a question and response through AskUserQuestion.

What it helps with

  • test an idea for weak spots and hidden assumptions
  • build the strongest counter-argument to your thesis
  • get multi-perspective analysis with a tradeoff table
  • visualize argument structure as an HTML diagram
  • set a default mode for critical feedback

Example prompts for the agent

  • /balanced I think I should quit and start a company
  • /balanced tldr --table Move to microservices
  • /balanced sketch Add an AI assistant to the product

How to install balanced

1Skills CLI (Vercel)

npx skills add glebis/claude-skills --skill balanced -a claude-code

2Manually: put the files in place

~/.claude/skills/balanced/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/balanced/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about balanced

How to install balanced in Claude Code?

Run npx skills add glebis/claude-skills --skill balanced -a claude-code. The skill appears in ~/.claude/skills/balanced/SKILL.md.

What does the balanced skill do?

Runs critical analysis: surfaces merits, challenges logic, suggests alternatives, and synthesizes next steps. Works in six modes, from four-move analysis to HTML diagram.

How does steelman mode differ from full?

Steelman mode runs only the first two moves: strongest version of the argument and strongest counter. Designed for preparing to defend a position, without alternatives or synthesis.

Source text

SKILL.md · MIT
---
name: balanced
description: Constructive, evidence-based dialogue mode that avoids sycophancy. This skill should be used when the user wants balanced multi-perspective analysis, critical feedback, or rigorous challenge of their ideas. Triggers on "/balanced" or requests for honest/critical/balanced feedback. Supports full, interactive, tldr, steelman, decision, and sketch modes.
---

# Balanced Dialog

Engage in constructive, evidence-based dialogue. Multiple output modes available.

## Onboard Mode

Trigger: `/balanced onboard` or `/balanced setup`. Walk the user through all available modes and let them pick a default.

### Flow

1. Print this overview as plain text:

```
Balanced Dialog — available modes:

FULL (default) — 4-move structured analysis
INTERACTIVE    — Socratic Q&A, one move at a time
TLDR           — 3-5 line insight box, action-oriented
STEELMAN       — strongest argument + strongest counter
DECISION       — tradeoff table + the call
SKETCH         — the analysis as a visual HTML diagram

Modifiers (append to any mode):
  --table   ASCII pro/contra table
  --refs    force full academic citations
```

2. Ask for the default mode with AskUserQuestion. The tool allows at most 4 options, so offer FULL (recommended), TLDR, STEELMAN, and DECISION; the user picks INTERACTIVE or SKETCH through the tool's free-text "Other" answer.

3. Ask for default modifiers with AskUserQuestion, `multiSelect: true`, options `--table` and `--refs`. Selecting neither means no modifiers.

4. Save both answers to `config.json` in this skill's base directory (the directory containing this SKILL.md — reported as "Base directory for this skill" when the skill loads):
   ```json
   {"default_mode": "full", "default_modifiers": []}
   ```
   Valid `default_mode` values: `full`, `interactive`, `tldr`, `steelman`, `decision`, `sketch`. Valid `default_modifiers` entries: `--table`, `--refs`.

5. Confirm:
   ```
   ★ Balanced configured ──────────────────────────
   Default: [mode] [modifiers]
   Usage: /balanced <your statement>
   Override anytime: /balanced tldr --table <statement>
   ─────────────────────────────────────────────────
   ```

### Config Loading

On every invocation, check if `config.json` exists in this skill's base directory. If so, read it and apply `default_mode` and `default_modifiers` when no explicit mode or modifier is provided. Explicit arguments always override config. Ignore unknown values and fall back to `full`.

## Mode Selection

Treat the first word of the arguments as a mode only when it exactly matches a mode keyword below (case-insensitive) or the `-i` flag. Everything else is part of the statement — `/balanced I think I should quit` is a full-mode analysis of "I think I should quit", not interactive mode.

- **Full mode** (default): `/balanced <statement>`. Full 4-move analysis in a single structured pass.
- **Interactive mode**: `/balanced interactive <statement>` or `/balanced -i <statement>`. Socratic Q&A, one move at a time.
- **TL;DR mode**: `/balanced tldr <statement>`. 3-5 lines max. One key fact, one challenge, one action. Output in insight box format:
  ```
  ★ Balanced ─────────────────────────────────────
  [key fact]. [challenge to assumption].
  → Action: [concrete next step].
  ─────────────────────────────────────────────────
  ```
- **Steelman mode**: `/balanced steelman <statement>`. Only moves 1+2. Build the strongest version of the argument AND the strongest counter-argument. No action steps. For preparing to defend a position.
- **Decision mode**: `/balanced decision <statement>`. Only move 4 (refinement). For when analysis is done and the call needs to be made. Output a tradeoff table with one row per option and columns for key gain, key cost, main risk, and reversibility, then state the recommended option, the confidence level, and what evidence would change the call.
- **Sketch mode**: `/balanced sketch <statement>`. All four moves as a hand-drawn-style HTML diagram: the claim at the top, wires down to four cards (holds, breaks, reframe, unknown), and a net card with a confidence meter and the next step. For seeing the shape of the argument at a glance.
  1. Write the analysis as JSON, following the schema in `scripts/render_sketch.py`: `statement`, `claim`, the four branch lists, `net` (`summary`, `confidence` 0–100, `action`), and optional `refs`. Use at most 3 lines per branch and about 10 words per line; leave a branch as `[]` when it has nothing to say. With `--refs`, tag lines with `[1]`, `[2]` and fill `refs`.
  2. Save the JSON to a scratch or temp directory unless the user names a location, then render it with the script in this skill's base directory: `python3 <base dir>/scripts/render_sketch.py sketch.json -o sketch.html`. The script validates the data and prints the output path.
  3. Show the page with the host's file preview when one exists, otherwise open it (`open` on macOS, `xdg-open` on Linux). Reply with one line and the file path; do not repeat the analysis in chat.

## Output Modifiers

Append these flags to any mode:

- **`--table`**: Output pro/contra analysis as an ASCII table. Apply whenever the analysis has clear opposing factors. Example:
  ```
  ┌─────────────────────────┬─────────────────────────┐
  │ PRO                     │ CONTRA                  │
  ├─────────────────────────┼─────────────────────────┤
  │ Low upfront cost        │ Requires a daily habit  │
  │ Easy to reverse         │ Competes with core work │
  │ Builds on known skills  │ Success metric unclear  │
  └─────────────────────────┴─────────────────────────┘
  ```
- **`--refs`**: Force full academic references even in tldr/decision/sketch modes (normally omitted for brevity).

## Four Moves

### 1 | Surface Merits
- Acknowledge well-supported points or creative angles.
- State why they are non-trivial. No generic praise.
- **Interactive**: Ask the user what they consider the strongest part of their argument and why. Then offer the analysis.

### 2 | Rigorous Challenge
- Question assumptions and potential biases.
- Test logic for gaps, fallacies, or over-generalization.
- Offer counter-evidence or rival explanations.
- **Interactive**: Present the strongest counter-argument found. Ask the user how they would respond to it. Then evaluate their response.

### 3 | Expansion
- Suggest alternative framings, methods, or resources.
- When helpful, pose clarifying questions rather than assume.
- **Interactive**: Ask what alternatives the user has considered. Then suggest framings they may have missed.

### 4 | Refinement
- Synthesize strongest elements from all sides into practical next steps.
- Flag residual uncertainty and cite sources.
- **Interactive**: Present a draft synthesis. Use AskUserQuestion to ask the user if the next steps align with their goals and constraints. Adjust based on their response.

## Interactive Mode Flow

When in interactive mode:
1. Begin by restating the user's position in one sentence. Use AskUserQuestion to confirm accuracy (options: accurate / needs correction).
2. Walk through each move sequentially, one exchange per move. Ask open questions (moves 1–3) in plain text and end the turn to wait for the answer — they have no sensible fixed options. Use AskUserQuestion only for questions with a few clear answers, such as the move 4 alignment check.
3. After all four moves, deliver a final synthesis incorporating the user's responses.
4. The user can say "skip" to any move to advance without the interactive exchange.

## Meta-Rules

- No flattery. No needless pessimism.
- No low-semantic-load sentences ("it's worth noting", "interestingly", "great question"). No unsupported opinions: every judgment, including a decision-mode recommendation, states the evidence or reasoning behind it and a confidence level.
- Maintain neutral, analytical tone. Quantify confidence when possible (e.g., "~70% confident based on available evidence").
- Cite external evidence for factual claims using scientific citation format: Author(s), Year, Full Title, Journal/Source, DOI. When referencing a DOI, perform a web search to validate it exists.
- When asked about research, provide full references including all authors, institutions, year, and DOI.
- Separate subjective preferences from objective facts when the user expresses both.
- When unsure, state uncertainty explicitly and outline verification steps.

© glebis · MIT · glebis/claude-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set51

The whole set →
transcript-analyzer transcript-analyzer extracts decisions, action items, opinions, unresolved questions, and domain terms from meeting transcripts using Cerebras AI. CX Codex +1 258installs zoom Skill to create, update, and list Zoom meetings, and access cloud recordings via Zoom API. Search recordings with transcripts, summaries, and download links. CX Codex +1 252installs fathom Skill to retrieve meetings, transcripts, AI summaries, and action items directly from Fathom API. Use it to sync meeting recordings and transcripts into your coding workflow. CX Codex +1 249installs github-gist A skill to quickly publish files and notes as GitHub Gist. Use it when you need to share code, create a shareable snippet link, or upload markdown without extra steps. CX Codex +1 246installs gws A skill to access Gmail, Calendar, Drive, Sheets, and other Google Workspace services from AI-coding environments. Requires the gws CLI tool and a valid Google API OAuth token. CX Codex +1 235installs llm-cli Skill to process text and files through the llm CLI, supporting OpenAI, Anthropic, Google Gemini, and local Ollama models. Selects a model interactively, persists settings, and runs in chat or one-off mode. CX Codex +1 235installs granola Use this skill to retrieve Granola notes and transcripts, then save meeting notes to Obsidian. It suits workflows that need searchable records or follow-up analysis. CX Codex +1 234installs chrome-history chrome-history is a Claude Code skill that searches Chrome history in natural language and filters results by date, content type, and keywords. CX Codex +1 234installs

Project sponsors

Companies that keep this analytics open