Crypto Whitepaper Writer

Crypto Whitepaper Writer

Guides an AI agent to write or review a crypto whitepaper grounded in problem-first framing, named threat models and per-actor incentive analysis.

Skill files1 file
SKILL.md99 lines
1
---
2
name: crypto-whitepaper-writer
3
description: Write a credible, well-structured whitepaper for any crypto/blockchain project (L1 chain, DeFi protocol, oracle network, stablecoin, token system) — grounded in the structural and rhetorical patterns of Bitcoin, Ethereum, Uniswap, Chainlink, and MakerDAO, not generic ICO-hype templates. Use whenever asked to draft, outline, or review a crypto/Web3 whitepaper.
4
---
5
6
# Crypto Whitepaper Writer
7
8
## Why this skill exists
9
10
Most AI-generated crypto whitepapers read like marketing decks: vague "revolutionary" language,
11
unbacked security claims, a roadmap standing in for proof, tokenomics as decoration. The five
12
most-cited whitepapers in the industry — Bitcoin, Ethereum, Uniswap, Chainlink, MakerDAO — share a
13
different discipline instead: problem-first framing, incremental mechanism-building, named threat
14
models, and per-actor incentive analysis. This skill encodes that discipline so the output reads
15
like engineering, not a pitch.
16
17
See `reference.md` for the full research base: archetype skeletons, craft principles, anti-patterns,
18
and the pre-publish checklist. Read it before drafting.
19
20
## Step 1 — Gather inputs before writing a word
21
22
Do not start drafting until you have, from the user:
23
24
- **The problem** this project solves, in one sentence, with a concrete scenario of what fails
25
without it.
26
- **The project archetype** — the closest match in `reference.md` → Archetypes: base-layer
27
consensus/settlement, DeFi mechanism (AMM/lending/derivatives), oracle/coordination network,
28
stablecoin/collateral system, or application-layer protocol/token system.
29
- **The core mechanism** — what actually happens on-chain/off-chain, in enough detail to describe a
30
state transition or formula, not just a feature list.
31
- **Token existence and role** — if a token exists, what specific mechanical function does it serve
32
(fee payment, collateral, staking/slashing, governance weight)? If the project doesn't need a
33
token, say so explicitly rather than inventing tokenomics to look complete.
34
- **Known limitations / open risks** the team is willing to state honestly.
35
36
If any of these is missing or vague, ask before drafting — never fabricate a problem statement, team
37
background, adoption numbers, or token model to fill a gap.
38
39
## Step 2 — Pick the section skeleton, calibrate length
40
41
Match the archetype to its skeleton in `reference.md`. Don't force every whitepaper through an
42
identical template — Bitcoin has no tokenomics section; MakerDAO has no proof-of-work security proof.
43
Use the shared spine (problem → mechanism → actor/incentive analysis → threat/risk model →
44
architecture → [governance/token, only if applicable] → limitations → conclusion), and cut whatever
45
doesn't apply to this project.
46
47
Length follows mechanism complexity, not a fixed page count — Bitcoin proves its point in 9 pages;
48
MakerDAO needs far more because it coordinates more actors and failure modes. Let each section run as
49
long as the idea needs and no longer (anti-pattern: forced symmetry). If the project has a token or
50
makes any financial/return-implying claim, include a short disclaimer (Uniswap's precedent) stating
51
the document is not investment advice.
52
53
## Step 3 — Draft section by section, applying the craft principles
54
55
Work through `reference.md`'s craft principles as each section gets written. The ones that matter
56
most in practice:
57
58
- Open with a failure scenario, not a mission statement.
59
- Build the mechanism from a minimal model upward — don't state the final design cold.
60
- Every security or performance claim gets a number, threshold, or named proof — never an adjective
61
alone ("highly secure" is not a claim).
62
- Every incentive-driven actor (miner, LP, oracle node, keeper, validator) gets its own paragraph
63
naming exactly what they earn and what punishes defection.
64
- Name specific attack vectors and pair each with its specific countermeasure.
65
- Include at least one worked, traceable example — a transaction walkthrough, a numeric calculation,
66
a step-by-step lifecycle.
67
- If this design revises or extends a known predecessor, write it as an explicit delta (what changed
68
and why), not a from-scratch re-explanation.
69
70
## Step 4 — Run the anti-pattern filter before showing a draft
71
72
Scan against `reference.md`'s anti-pattern list. Any hit is a reason to rewrite the line, not soften
73
it: price predictions or market-cap claims, unverifiable team/advisor credentials used as an
74
argument, roadmap phases presented as proof of viability, a tokenomics table with no stated
75
mechanical purpose, novelty claimed without naming what came before, a security claim with no threat
76
model behind it, a missing limitations section, buzzwords substituting for a mechanism description.
77
78
## Step 5 — Self-check and disclose gaps
79
80
Before finalizing:
81
82
- Confirm every numeric or technical claim traces to something the user provided or a cited external
83
source — flag anything you inferred rather than were told.
84
- Confirm a limitations/risks section exists and isn't hollow.
85
- Run `reference.md`'s pre-publish checklist and state the result (pass/fail per item, or a
86
self-rating) to the user before calling the draft done — don't ship a whitepaper without surfacing
87
what's unresolved.
88
89
## Output format
90
91
Markdown, sections matching the chosen archetype skeleton, an abstract at the top, references/sources
92
at the bottom if external material was used. No emoji, no bolded label scaffolding (`Problem:`,
93
`Solution:`), no forced symmetry between sections — a simple idea gets a short section, a hard one
94
gets a long one, exactly as the five reference papers do.
95
96
Cite every external claim (a cryptographic primitive, a competitor's known limitation, a market fact)
97
inline with a bracketed marker (e.g. `[1]`) resolving to a numbered reference list at the end — never
98
assert an outside fact with no traceable source. See `reference.md` → Calibration examples for what a
99
compliant vs. non-compliant sentence looks like before you draft the real thing.
@OpenSourceBuffGuy

I find openly licensed prompts and post them here.

0 followers · 2,873 prompts

More by @OpenSourceBuffGuy

See all
Ethereum Developer prompt image

Ethereum Developer

Asks the AI to act as an experienced Ethereum developer who writes a Solidity smart contract for an on-chain messenger with public reads and owner-only writes.

act-as, crypto, coding

1 view
Linux Terminal prompt image

Linux Terminal

Makes the AI act as a Linux terminal that replies to each typed command with only its output inside one code block.

simulator, linux, coding

5 views
English Translator and Improver prompt image

English Translator and Improver

Turns the AI into an English translator and editor that detects the input language and returns only an improved, more literary English version.

act-as, translation, rewriting, proofreading

2 views

Reviews

Loading reviews…

Discussion

Loading comments…