
Founder @wevoteproject - https://teapawt.org/t.co/hviEvtAzDQ - all rights reserved
Joined January 2022
- Tweets2.1K
- Following2.1K
- Followers185
- Likes23.5K
Andy Curran retweeted
Being a founder is weird because you’re good at a lot of things and can probably easily get a job in Product, Marketing, Engineering, Sales/GTM, VC, etc. but the combination mixed with your god-given temperament means you are unemployable and must build your own thing
Andy Curran retweeted
🚨Mike Johnson cancels another day of Congress this week, and I’m here in half a cubicle trying to stop a war and bring Epstein’s coconspirators to justice.
Andy Curran retweeted
If you're designing with AI, these 18 websites deserve a spot in your bookmarks.
A curated toolkit for better designs, faster workflows, and serious inspiration:
AI & Website Building
1. "Modulify.ai" (modulify.ai) — Build websites with AI
2. "Motionin.design" (motionin.design) — Turn one prompt into a website
3. "Modulify Templates" (modulify.ai/templates) — Free website templates
Design Inspiration
4. "Landdding" (landdding.com) — High-quality landing pages
5. "Godly" (godly.website) — Award-worthy websites
6. "Recent" (recent.design) — Fresh design inspiration
7. "On.Design" (on.design) — Design community
8. "Wonderlist" (wonderlist.design) — Figma design resources
UI, Icons & Components
9. "Iconly" (iconly.design) — Beautiful icon collections
10. "BeUI" (beui.dev) — Animated UI components
11. "Mobbin" (mobbin.com) — Real-world app UI references
12. "60fps" (60fps.design) — Mobile UI animations
13. "Footer.design" (footer.design) — Footer design inspiration
Branding & Visual Assets
14. "Font in Logo" (fontinlogo.com) — Discover fonts used by famous brands
15. "Backgrounds Supply" (backgrounds.supply) — Unique backgrounds
16. "Posts.design" (posts.design) — Social posts from big brands
17. "Logotouse" (logotouse.com) — Premium logo inspiration
18. "Paper Animation" (paperanimation.ai) — Paper-style animations
Bonus
19. "Sent.dm" (sent.dm) — Affordable SMS infrastructure
Save this list. Your next design project will thank you.
Bookmark it. You'll need it. 🔖
I send around PDFs and markdown files to my coworkers so much and they use their agents to make sense of the world too, so I started using this skill methodology-appendix to make sure their agents could replicate what my agents found.
---
name: methodology-appendix
description: "Every data-backed report or memo ends with a Methodology / Replication Appendix: the signal choice and its sensitivity, verbatim queries, derivation pseudocode over named constants, the rebuild command, and drift/limits. Appended by default, without asking."
---
# Methodology / Replication Appendix
## Rule
Any report, PDF or page whose conclusions rest on data queries ends with a
**Replication Appendix**. It is a working recipe, not a citation list. The test:
> A reader with an agent and equivalent data access can regenerate the document
> end to end from the appendix alone, without contacting the author.
If a reader would have to ask "which column did you use?", "what date was this
pulled?" or "how do I rebuild the PDF?", the appendix failed.
## Body voice
The body states conclusions plainly. No process narration ("I was asked...",
"on the first pass..."), no self-grading. The first sentence after the title
contains a finding. Everything about how you got there goes in the appendix at
the end, written for forensic recreation.
## When this fires
Always, automatically, for:
- analysis memos backed by database or API queries
- any PDF sent to partners, executives or external stakeholders
- pages presenting quantitative findings
- anything with tables of counts, rates or percentiles
Skip for narrative or qualitative writing, meeting notes, personal memos,
short ephemera, and documents with no data spine. Do not ask permission.
## The six sections
### 1. Header
```markdown
## Replication Appendix
A reader with an agent and equivalent data access can regenerate every number
and rebuild this document from this appendix alone.
**Access required:** <tool/CLI + auth, internal APIs>
**Snapshot date:** <ISO date>. Live-data documents won't reproduce exactly after this date; see Drift.
```
### 2. Signal definitions and the choice that mattered
The most important section. Analyses usually turn on one column or threshold
choice. Name it, name the alternatives, state the impact.
```markdown
### Signal definitions
| Field | What it is | Why chosen / rejected |
|---|---|---|
| `score_a` | Ensembled score | **Primary.** More predictive per <source>. |
| `score_b` | Single-model score | Rejected as primary; kept for contrast. |
| final_decision | Human decision object | Not queried. Known gap. |
**Outcome sensitivity:** switching from score_b to score_a moved the headline
count from N1 to N2 and changed claim X. A replication that changes the signal
column will not match these numbers.
```
Always include an **Outcome sensitivity** line. If a different defensible choice
changes the conclusion, the reader must know before quoting it.
### 3. Verbatim queries
Every query that produced a number, copy-pasteable, in document order, labelled
by the finding it supports. Never paraphrase SQL. Never write "similar to the
above." Add schema notes a replicator would otherwise get wrong: enum meanings,
non-obvious joins, columns that seem to exist but don't.
### 4. Derivation pseudocode
Queries give raw counts; the document has derived figures. Show the arithmetic,
with assumptions as named constants a reader can swap.
```
ITEMS_PER_DAY = 8 # observed median, <period>
YIELD_HAIRCUT = 0.10..0.15 # marginal cases convert below observed rate
gap = count(status = REJECTED and score >= threshold)
extra_days = gap / ITEMS_PER_DAY
added_wins = gap * YIELD_HAIRCUT
```
Different constants change the recommendation, not just the number, so they
must be visible.
### 5. Rebuild command
Exact commands from source markdown to verified PDF, plus a visual check
(e.g. `pdfinfo` page count, `pdftoppm` a couple of pages and look at them).
Name the source of record: the PDF is a render, never the original.
### 6. Drift, limits and known gaps
- **Live data moves.** What was mid-flight at snapshot; what is closed and stable.
- **Coverage gaps.** Fields only populated for part of the range, and how tables were restricted rather than shown with misleading denominators.
- **What this cannot see.** Inputs to the real decision that the data lacks.
- **Retractions.** Any claim withdrawn between versions, and why.
## Procedure
1. Log queries verbatim as you run them. Reconstructed SQL is how appendices go wrong.
2. Write the analysis.
3. Append the six sections before rendering.
4. Name the signal choice and its outcome sensitivity.
5. Render, check visually, then send.
6. On revision, update the appendix in the same commit as the finding. An appendix describing a superseded method is worse than none.
## Quality bar
- [ ] Could a reader re-run this without asking me anything?
- [ ] Is every headline number traceable to a pasted query?
- [ ] Is the signal/threshold choice named, with alternatives and impact?
- [ ] Are derived figures arithmetic over named constants?
- [ ] Is the rebuild command present and correct?
- [ ] Are drift, coverage gaps and retractions stated?
## Anti-patterns
- **Citation theater:** table names instead of runnable queries.
- **Reconstructed SQL:** retyped from memory, drifted from what ran.
- **Silent signal choice:** one column presented as "the score" when a defensible alternative changes the answer.
- **Buried assumptions:** constants hard-coded in prose.
- **Stale appendix:** findings revised, appendix untouched.
- **Asking first:** this is a default, not an offer.
Andy Curran retweeted
Don't tell ChatGPT "analyze this."
Don't tell ChatGPT "make me a plan."
Don't tell ChatGPT "give me ideas."
You're using advanced AI like it's an intern.
Here are 10 prompts to copy and paste:
Andy Curran retweeted
"How we store ONE year's worth of Homegrown Food!"
This family of 6 just finished harvesting and shows exactly how they store a full year’s worth of homegrown food in a regular basement.
Potatoes, sweet potatoes (~150–200 lbs), winter squash, carrots, beets, cabbage, corn, beans + meat from animals they raised. Simple racks, bins, curing, free/cheap freezers.
Source youtu.be/Bn5NvhoU_Dk?si=UFXr…
Andy Curran retweeted
Jensens don’t grow on trees.
I don’t think most people have a good theory of mind on how unique and rare a person like Jensen is. Comparable replacements simply do not exist.
Andy Curran retweeted
DocuSign wants $8,100/yr from a 15-person team just to sign PDFs. So I built SignuDoc: open source, one-click deploy to your own @vercel account, $0 per seat.
White-label branding, full audit trails, tamper-evident seals and your documents never leave your cloud.
Andy Curran retweeted
Talking about politics on X is a lot like fentanyl:
It feels good in the moment—but afterwards, you’re still broke and retarded.











































































