rhetorical-orchestrator

rhetorical-orchestrator is a skill for Claude Code from Biolytics-AI/rhetoric-engine. It costs 61 tokens per session (1,877 once invoked), scanned A, original, MIT.

A routing skill for a presentation workflow that determines which planning or review stage should happen next. It keeps the audience, purpose, constraints, and approval points in view before slide production begins.

In plain words
What is it for?
Use it to start, improve, critique, rehearse, or compile a presentation, especially when the request needs help choosing the right preparation stage.
Why use it?
It prevents an agent from jumping straight from a vague request to a finished deck. It also makes clear which decisions belong to the user and which stage is still incomplete.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the rhetoric-engine plugin — 12 skills shipped together

Good fit Use it to start, improve, critique, rehearse, or compile a presentation, especially when the request needs help choosing the right preparation stage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/biolytics-ai/rhetoric-engine/rhetorical-orchestrator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Biolytics-AI/rhetoric-engine --skill rhetorical-orchestrator
Clone the repo
git clone --depth 1 https://github.com/Biolytics-AI/rhetoric-engine

Made for: Claude Code.

Or install rhetoric-engine, the plugin that ships this one along with the rest of its 12 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for rhetorical-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/biolytics-ai/rhetoric-engine/rhetorical-orchestrator/github.svg)](https://agentmods.dev/skills/biolytics-ai/rhetoric-engine/rhetorical-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/biolytics-ai/rhetoric-engine/rhetorical-orchestrator"><img src="https://agentmods.dev/badge/skills/biolytics-ai/rhetoric-engine/rhetorical-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for rhetorical-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/biolytics-ai/rhetoric-engine/rhetorical-orchestrator"><img src="https://agentmods.dev/badge/skills/biolytics-ai/rhetoric-engine/rhetorical-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,877 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.01877
Opus 5 $0.00030 $0.00938
Sonnet 5 $0.00012 $0.00375
Haiku 4.5 $0.00006 $0.00188

Measured 10d ago against content hash 23c9afd76a51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rhetorical-orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/rhetorical-orchestrator/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rhetorical Orchestrator

Use this as the entry gate for the Rhetoric Engine. Keep the user's view primary: optimize for their intent, audience, constraints, and decision needs before optimizing for slide count, visual polish, or production speed.

Operating Model

Run one plugin with many stage skills. You are the orchestrator, not the whole pipeline. Diagnose the user's current rhetorical state, route to the smallest applicable phase, update the artifact ledger, and stop at the next required approval gate. If a named stage skill is unavailable in the current install, execute the phase instructions yourself and record that the route was handled by rhetorical-orchestrator.

Do not compile, draft, or render a deck just because the user mentions slides. First make sure the rhetorical artifacts exist and are approved.

Approval gates are user-owned. Do not treat model-generated assumptions as approved artifacts. When the user's view is still forming, route to exploratory elicitation before drafting polished artifacts.

Phase Order

| Phase | Intended stage skill ID | Purpose | Route when | | --- | --- | --- | | 1. Intent | intent-framer when available; otherwise this skill. | Define objective, audience, stakes, constraints, and success criteria. | The ask is broad, ambiguous, new, or missing audience/outcome. | | 2. Insight | insight-externalizer when available; otherwise this skill. | Find the core audience-relevant idea, tension, or useful shift in perspective. | The user has facts but no clear point of view or audience insight. | | 3. Argument spine | argument-spine-builder when available; otherwise this skill. | Build the persuasive sequence: claim, reasons, evidence, objections, and resolution. | The thesis exists but the logic, sequence, or persuasion path is weak. | | 4. Slide thesis map | slide-thesis-mapper when available; otherwise this skill. | Assign one controlling thesis to each slide or section before layout. | The argument exists but slide-level jobs are not mapped. | | 5. Cognitive design | cognitive-designer when available; otherwise this skill. | Resolve attention, hierarchy, accessibility, reading order, slide grammar, and cognitive risk before production. | Slide theses are approved and the deck needs design decisions, cognitive load reduction, accessibility checks, or slide grammar guidance. | | 6. Visual reasoning | visual-reasoner when available; otherwise this skill. | Create the visual plan, chart or diagram recommendations, and annotation plan. | Slide theses are approved and the deck needs visual strategy, data display choices, diagrams, visual hierarchy, or annotation decisions; run after or alongside cognitive design. | | 7. Evidence curation | evidence-curator when available; otherwise this skill. | Build the claim-evidence matrix, choose evidence, track provenance, identify backup evidence, and flag evidence gaps. | Claims, source materials, or proof burden matter before compilation; run before deck compilation whenever evidence/design/visual reasoning is relevant. | | 8. Content distillation | content-distiller when available; otherwise this skill. | Tighten, cut, compress, fit to time or attention budget, move overflow to notes, recommend splits, and preserve argument integrity before or during production. | Slide theses are known and content needs signal improvement, compression, moved-to-notes decisions, split recommendations, or risk checks before compilation. | | 9. Deck compilation | deck-compiler when available; otherwise this skill only after gates pass. | Produce or revise slides from approved slide theses plus Phase 2 artifacts and any existing content distillation outputs when available or needed. | Intent, insight, spine, and thesis map are approved, and relevant evidence, cognitive design, visual reasoning, and content distillation work has not been bypassed. | | 10. Critique/rehearsal | critique-iterator for feedback, rubric review, severity-ranked revision backlog, root causes, fixes, retest plan, and delta report; delivery-coach for timing, transitions, pacing, written/visual/verbal delivery, Q&A, and rehearsal guidance; otherwise this skill. | Stress-test clarity, pacing, delivery, objections, and audience reception. | A draft, outline, or talk track exists and the user asks to improve or practice. |

Read the full file on GitHub · 86 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 86 lines · 61 tokens per session scan A 23c9afd76a51

Subscribe to this mod's changes

rhetorical-orchestrator is a skill published in the GitHub repository Biolytics-AI/rhetoric-engine (1 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 1,877 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

2slides-ppt-generator

AI-powered presentation generation via the 2slides API — create slides from text, match a reference image style, summarize documents into decks, add AI voice narration, and export pages/audio. Use for any "make slides", "create a deck", or "slides from this document" request.

sickn33/agentic-awesome-skills · 64 tokens

slides

Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding…

fcakyon/claude-codex-settings · 83 tokens

design_creator

Structured workflow for creating professional designs — slide decks, documents, landing pages, app mockups, and motion storyboards.

siddsachar/row-bot · 27 tokens

presentations

Use when building, theming, or exporting a presentation deck — pitch, sales, keynote, board/QBR, leave-behind one-pager — from slide structure to a token-based theme to PDF or editable PPTX (Marp, Slidev, python-pptx). NOT the words (that is marketing), NOT the visual tokens (that is design), NOT the investor story…

ericrisco/rsc-harness · 93 tokens

lov-media-publisher

A video publishing workflow for the WeChat Channels and Bilibili creator dashboards. It checks media and post fields, handles platform-specific limits and layouts, and reads the submitted details back from the platform.

lovstudio/skills · 88 tokens

lov-article-creator

A skill that turns source material or a draft into a complete, branded WeChat public-account article package.

lovstudio/skills · 75 tokens