# Manifesto Writing

> Trigger when users request manifestos or manifesto tone. Name the enemy, strip hedging, compress to sharp distinctions, end with stark choice.

- Skill: `ryzhakar/manifesto-writing` (Agent Skill)
- Install (CLI): `npx skillmds@latest add ryzhakar/manifesto-writing`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ryzhakar/manifesto-writing/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: ryzhakar (https://skillmd.com/u/ryzhakar)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/ryzhakar/manifesto-writing

---




# Manifesto Writing

Transform source material into manifestos: concentrated declarations of principle that command rather than explain.

## Transformation

It declares. It commands. It names enemies. It assumes the reader is ready to be changed.

**Source material** (talks, essays, documentation) explains, hedges, builds, accommodates objections.

**Manifestos** state positions as facts, strip hedging, build urgency, demand action.

The transformation: cut words, state positions as facts.

## What to Preserve

- **Core distinctions** — the conceptual hinges the argument turns on
- **Sharp vocabulary** — terms the author coined or defined precisely
- **Memorable aphorisms** — lines under 15 words that capture a core distinction
- **The moral core** — why this matters, what's at stake
- **Actionable principles** — what the reader should do

## What to Cut

- Audience asides
- Extended examples
- Hedging language ("I think," "perhaps," "it seems," "sort of")
- Repetition for emphasis (works in speech, bloats on page)
- Explanatory scaffolding (definitions already given, objections pre-answered)
- Qualifications and caveats (unless they are the point)

## What to Transform

| Source Pattern | Manifesto Pattern |
|----------------|-------------------|
| "I believe that X" | "X." |
| "You might consider Y" | "Y." (imperative) |
| "It's possible that Z" | "Z." or cut entirely |
| "Let me explain why..." | State the conclusion directly |
| Extended analogy | One sharp image, then move on |
| Gradual buildup | Lead with the blade |

## Structural Principles

### Name the Enemy Early

Every manifesto opposes something. Name it in the first section. Make the stakes clear.

### Declarations, Not Arguments

State positions. Do not justify them at length. The manifesto assumes the reader is ready to hear. If they need convincing, choose another form.

### Commands, Not Suggestions

Use imperative mood. "Do X." Not "You should consider doing X." Not "It might be helpful to do X."

### Short Sentences, Short Sections

Short sentences (under 20 words). Short sections (under 150 words). Punchy rhythm. White space between sections. Each section should hit once and move on.

### Tables Over Prose for Mappings

When showing "bad → good" or "complex → simple" mappings, use tables. Faster to scan, easier to reference.

### End with a Choice

Manifestos call readers to decide. The closing should make the choice stark.

## Process

1. **Read source** — understand the argument's architecture before cutting
2. **Identify the core** — what are the 3-5 ideas that everything else supports?
3. **Extract vocabulary** — what terms does the author define or use precisely?
4. **Find the enemy** — what does this oppose?
5. **Draft sections** — one per core idea, plus opening (enemy + stakes) and closing (the choice)
6. **Strip hedging** — remove "I think," "perhaps," etc. in a separate pass
7. **Convert to commands** — change suggestions to imperatives
8. **Tighten** — cut words, cut sentences, cut sections until it hurts
9. **Add attribution** — credit the source author

## Tone Markers

**Include:**
- Moral urgency
- Direct address ("you")
- Present tense
- Active voice
- Concrete nouns

**Exclude:**
- Academic hedging
- Passive constructions (unless for emphasis)
- Future tense promises
- Abstract nouns where concrete ones work
- Weasel words ("very," "really," "somewhat," "quite")

## Attribution

When transforming someone else's work, attribute clearly. Use "After [Author]" to signal this is an editorial transformation, not a transcript or original composition.

## Example Transformations

**Source (spoken):**
> "I think that collectively we are infatuated with these two notions of easy. We are just so self-involved in these two aspects, it's hurting us tremendously. All we care about is, can I get this instantly and start running it in five seconds?"

**Manifesto:**
> We are infatuated with easy. We want tools we can install in five seconds. We want syntax that looks like what we already know. We mistake familiarity for quality.
>
> This infatuation is destroying us.

---

**Source (spoken):**
> "And I like to ask this question: What's true of every bug found in the field? It got written, yes. What's a more interesting fact about it? It passed a type checker. What else did it do? It passed all the tests. Okay. So now what do you do?"

**Manifesto:**
> The tests will not save you. Every bug found in the field passed the type checker. Every bug found in the field passed all the tests. When the guardrails fail — and they will fail — you will need to *think*.

---

**Source (spoken):**
> "I didn't put the definition in here, but incidental is Latin for your fault."

**Manifesto:**
> *Incidental* is Latin for *your fault*.

(Some lines need no transformation — only extraction.)

## Length

A manifesto should be readable in one sitting. For transformation of a 45-minute talk, aim for 1500-2500 words. Shorter is usually better.

## Prerequisites

Manifestos require conviction. Manifestos flatten nuance. Manifestos assume sympathetic readers. Manifestos sacrifice precision for force.

A manifesto is a tool for crystallization and transmission, not for discovery or persuasion.

