Skip to content
Agentmart
Submit a tool

30-30-30-technical-note

Turn a PGS research finding into a three-layer technical note bundle: (1) Grade-10 plain prose, (2) embedded SVG infographic with concise figures, (3)…

Skill by zfifteen

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying 30-30-30-technical-note?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/zfifteen-30-30-30-technical-note

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Turn a PGS research finding into a three-layer technical note bundle: (1) Grade-10 plain prose, (2) embedded SVG infographic with concise figures, (3) PhD-level rigorous technical treatment; plus a PNG export of the SVG. Output lives under research/<chapter>/30-30-30-technical-note/. Use when the user asks for a "30/30/30 technical note", "30-30-30 tech note", "/30-30-30-technical-note", or wants the standard finding bundle format for a research chapter.

Use cases: design, research, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/30-30-30-technical-note

What's inside

Skill name
30-30-30-technical-note
Description
Turn a PGS research finding into a three-layer technical note bundle: (1) Grade-10 plain prose, (2) embedded SVG infographic with concise figures, (3) PhD-level rigorous technical treatment; plus a PNG export of the SVG. Output lives under research/<chapter>/30-30-30-technical-note/. Use when the user asks for a "30/30/30 technical note", "30-30-30 tech note", "/30-30-30-technical-note", or wants the standard finding bundle format for a research chapter.
License
MIT
Metadata
version: 1.0.0 · short-description: 30/30/30 finding bundle: plain prose, SVG, PhD note
Instructions
162 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • export_infographic_png.sh · scripts/

SKILL.md (first lines)

# 30/30/30 Technical Note

Produce a **finding bundle** with three reading layers and two image artifacts.

## Output location

```text
research/<chapter>/30-30-30-technical-note/
├── TECHNICAL_NOTE.md      # all three parts in one file
├── infographic.svg        # concise visual summary
└── infographic.png        # raster export of the SVG
```

- `<chapter>` is the existing research folder (e.g. `18-derived-half-coefficient`).
- If the chapter folder does not exist, create it first with a minimal `README.md`
  before writing the bundle.
- Do **not** place the bundle at repo root or under `docs/` unless the user
  explicitly overrides.

## Mandatory workflow

### Step 1 — Gather source material

Read before writing:

1. The finding statement or theorem authority (`PROOF.md`, chapter `docs/`,
   `FINDING_STATEMENT.md`, prior digests).
2. Any measured/audit artifacts cited by the finding.
3. An existing technical note in the repo for tone reference:
   `research/twin-prime-resonance-technical-note-2026-07/TECHNICAL_NOTE.md`.

Use tools. Do not invent proof status or numbers.

### Step 2 — Write `TECHNICAL_NOTE.md`

Use this exact skeleton:

```markdown
# <Finding Title> Technical Note

**Date:** YYYY-MM-DD
**Finding / Theorem:** <ID or name>
**Status:** <proved | measured | hypothesis | corollary>
**Authority:** <paths>

---

## Part I — Plain-Language Summary

<Grade-10 prose — see rules below>

---

## Part II — Visual Summary

![<alt>](infographic.svg)

*PNG export:* [infographic.png](infographic.png)

<3–6 bullet caption of what the diagram shows>

---

## Part III — Technical Treatment

<Rigorous PhD-level exposition — see rules below>
```

### Step 3 — Part I rules (Grade 10)

Follow the **grade-ten** skill discipline:

- Short sentences. Everyday words. Define any unavoidable term immediately.
- **No metaphors, no analogies** ("like a…", "think of it as…").
- State what is proved, what is measured, and what is hypothesis.
- Include one concrete numeric example when the finding allows it.
- Target length: **~250–400 words** unless the user asks for longer.

### Step 4 — Part II rules (SVG infographic)

Create `infographic.svg` in the bundle folder.

**Design contract** (match repo house style from twin-prime note):

- Canvas ~1600px wide; height as needed (typically 1200–1700px).
- Palette: warm off-white background (`#f7f5ef`), dark ink (`#1f2528`),
  muted captions (`#586069`), colored step boxes with distinct stroke colors.
- Font stack: `Inter, ui-sans-serif, system-ui, sans-serif`.
- Structure: **numbered steps** (usually 4–6) with arrows between stages.
- Include: theorem/finding title, one key formula, status badge, boundary line
  ("does not prove RH" when relevant).
- Text in the SVG must stay **concise** — labels and short clauses, not paragraphs.

Embed in markdown as:

```markdown
![<descriptive alt>](infographic.svg)
```

### Step 5 — Part III rules (PhD level)

- Full notation block, formal theorem statement(s), lemma chain or proof architecture.
- Display math with LaTeX (`$...$`, `$$...$$`).
- Cross-reference authority files with paths and section names.
- Explicit **boundary** paragraph: what the finding does **not** establish.
- Cite finite certificates, audit tables, or external validation when present.
- Target length: as long as needed for completeness; do not compress proofs into hand-waving.

### Step 6 — Export PNG

Run the bundled script:

```bash
bash "$HOME/.grok/skills/30-30-30-technical-note/scripts/export_infographic_png.sh" \
  "<path-to-infographic.svg>"
```

Requires `rsvg-convert` (Homebrew `librsvg`). Fallback: `magick convert` at 2× density.

From zfifteen/skills-catalog, MIT.

More from zfifteen/skills-catalog

Signals

Stars
1
Forks
1
Open issues
0
Last commit (this folder)
Jul 19, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0.0
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from zfifteen

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get 30-30-30-technical-note running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying 30-30-30-technical-note?

CallGet help
Cite this page

30-30-30-technical-note skill. Agent Mart. https://agentmart.dev/skills/zfifteen-30-30-30-technical-note (last updated 2026-10-24)