Rhetorical Analyst Skill for Claude & AI Agents
The Rhetorical Analyst skill (rhetorical-analyst)
turns Claude into a rigorous debate analyst. It evaluates any argumentative text — a debate, a comment thread, a speech, an article —
across three separate dimensions: does it work emotionally (persuasion), is the structure sound (rhetoric),
and do the premises actually support the conclusion (logic)? A move can score high on persuasion and low on logic at the same time —
the skill never collapses the three into one verdict.
It is for anyone who wants to understand why something feels persuasive but wrong, stress-test their own arguments before publishing, or break down what is actually happening in a heated exchange. The skill maps the rhetorical moves one by one, exposes hidden assumptions, tracks missing inferential steps, and checks whether the same evidential standard is applied to both sides — including by the analyst itself.
Get Started
Create an Account
Sign up for a free InfraNodus account to get access to the knowledge graph tools and your API key.
Create a Free AccountGet InfraNodus MCP
https://mcp.infranodus.comAdd this URL as a connector via Settings > Connectors in Claude Web / Desktop and authenticate with your InfraNodus API key via OAuth.
https://mcp.infranodus.comOpen the ChatGPT Apps page > Advanced Settings > enable Developer Mode > Create App, paste this URL (leave the OAuth fields empty), click Connect, and authenticate with your InfraNodus API key. Full guide: ChatGPT setup.
claude mcp add infranodus -s user --transport http https://mcp.infranodus.com/mcp
Then open Claude Code in terminal, run /mcp and pick
"Authenticate" — it opens the browser OAuth flow where you will need to
put in your InfraNodus API key to connect to
the MCP server.
{
"mcpServers": {
"infranodus": {
"url": "https://mcp.infranodus.com"
}
}
}
Add this to ~/.cursor/mcp.json (all projects) or
.cursor/mcp.json (one project) — or use
Cursor Settings > MCP > New MCP Server. Then
click "Login" next to the server to authenticate with your
InfraNodus API key.
codex mcp add infranodus --url https://mcp.infranodus.com
codex mcp login infranodus
Run these commands in your terminal — the login command opens the
browser OAuth flow where you enter your
InfraNodus API key. (You can also add the
server to ~/.codex/config.toml manually.)
{
"mcpServers": {
"infranodus": {
"command": "npx",
"args": ["-y", "infranodus-mcp-server"],
"env": {
"INFRANODUS_API_KEY": "your-api-key"
}
}
}
}
Add this to your LLM client's MCP configuration file, replacing
your-api-key with your
InfraNodus API key. See our
deployment guides for client-specific
instructions (n8n, Make.com, local setup, and more).
Install the Skill
/plugin marketplace add infranodus/skills
/plugin install skill-rhetorical-analyst@infranodus-skills
Run these two commands in the Claude Code prompt to install
the skill as a plugin (use
infranodus-all@infranodus-skills to install all
our skills at once). Or use npx in your terminal:
npx skills add infranodus/skills --skill skill-rhetorical-analyst -g -a claude-code -ynpx skills add infranodus/skills --skill skill-rhetorical-analyst -gWhen prompted, select the agents where you want to add the skill — e.g. claude-code, codex, or cursor.
npx comes bundled with Node.js. For Claude Web / Desktop, ChatGPT, and OpenClaw, see the full installation instructions.
Didn't work? You can simply download skill-rhetorical-analyst.zip from our GitHub repository and add it to your LLM client manually — see the step-by-step instructions.
What the Skill Does
Once installed, prompts like these trigger the full analysis workflow:
- "Analyze this argument" — maps each argumentative move (moral reframe, partial concession, burden shifting, tu quoque, etc.) and scores it on persuasion, rhetoric, and logic.
- "What's wrong with this reasoning?" — finds the missing inferential steps: the premises the argument requires but never states.
- "Why is this persuasive?" — separates rhetorical force from logical force, showing where intensity fills the gap where a premise should be.
- "Break down this debate" — tracks principle shifts, concessions, and asymmetric standards across a whole exchange.
- "Is this a good point?" — reconstructs the strongest version of the argument first, then names the genuine remaining weakness.
- "Stress-test my argument" — applies the same standards to your own text, so you can fix the gaps before an opponent finds them.
A core principle of the skill is symmetry: if the analysis consistently asks one side to justify itself while letting the other side's assumptions pass unchallenged, that asymmetry is itself a bias to name and correct. It also keeps hypocrisy, sincere error, and structural dysfunction distinct — three different failure modes that require different evidential bars — and distinguishes understanding a logic from endorsing it.
How It Works
The skill's key idea is that structural analysis precedes linear reading. When the InfraNodus MCP server is connected, the first three steps are mandatory tool calls that map the argument as a network before any moves are identified:
| Step | Tool | What it reveals |
|---|---|---|
| 1. Map the terrain | generate_topical_clusters | Which concepts dominate the argument's network. Key diagnostic: does the stated topic match the structurally central cluster? When an argument claims to be about X but is organized around Y, that divergence reveals the hidden operative premise. |
| 2. Find structural gaps | generate_content_gaps | Concepts that would connect the clusters but are absent — these map directly onto missing inferential steps. Each gap is classified as a flaw, a concealment, or a co-authorship space the audience fills with their own premises. |
| 3. Diagnose bias | optimize_text_structure | Whether the argument is tribally over-concentrated or too dispersed to make a point. The question mode generates the questions the argument's own structure implies it should be answering but isn't. |
Only then does the skill read the argument sequentially: it names each move, scores it on the three dimensions with a specific mechanism ("weak logic" is never enough — it names the tu quoque, the false equivalence, the missing premise), finds the hidden joints where the argument needs one more step to be complete, and finally checks its own frame — asking whether it treated one position as the default and the other as the claim requiring justification.
The skill also carries a library of effective debate techniques (compressing a reductio into a single question, the consistency challenge, naming principle shifts, the concession audit) and a reference table of common fallacies with their tells. Without the MCP server it still runs the linear workflow — the analysis is valid, but gap findings are intuited rather than structurally derived.
Install the Skill
Claude Code
Download the skill into your global skills folder:
cd ~/.claude/skills
curl -L -o skill-rhetorical-analyst.zip https://github.com/infranodus/skills/releases/latest/download/skill-rhetorical-analyst.zip
unzip skill-rhetorical-analyst.zip -d skill-rhetorical-analystThen just ask Claude to "analyze this argument" or "break down this debate" — the skill activates automatically.
Claude Web / Desktop
Go to Settings > Capabilities, enable Code execution and file creation, scroll to the
Skills section, and upload the skill-rhetorical-analyst.zip file.
OpenClaw
Run in the OpenClaw chat:
install this skill: https://github.com/infranodus/skills/releases/latest/download/skill-rhetorical-analyst.zipSee the main installation guide for step-by-step instructions per LLM client.
Works Best with the InfraNodus MCP Server
The skill works without any server — the move-mapping, scoring, and frame-checking are self-contained. But its structural steps (topical clusters, content gaps, bias diagnosis) need the InfraNodus MCP server connected to your LLM client. With it, the gaps the skill names emerge from the argument's own network structure, which makes them much harder to dismiss as the analyst's imposition.