Chalk Labs
Need help deploying show-me?
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.
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/fmflurry-show-me-3f8418
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.
About
Use cases: presentations, frontend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
show-me- Description
- Help the user understand the current topic visually. Produces a self-contained HTML file by default (diagrams, infographics, short slide decks) and opens it, because terminal-rendered diagrams read poorly. Use when the user says "show me", "visualize", "diagram this", "draw it", "explain visually", or when a topic is too dense for prose.
- License
- MIT
- Instructions
- 124 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Help the user understand the current topic of conversation visually. Skip the preamble and keep prose brief.
**v2 change:** when the topic is states, flows, lifecycles, workflows or protocols, prefer the **Statechart** form below. Its visual vocabulary (reader-facing labels, phase colors, `breaks` / `mayBreak` / `bugPath` marks, numbered bug paths) is adapted from [@poteto](https://x.com/poteto)'s `/statechart` skill in [backnotprop/pstack](https://github.com/backnotprop/pstack) (MIT License · Copyright 2026 Lauren Tan). Keep the MIT notice in any substantial copy of that vocabulary or CSS. This skill does **not** run TLC or Pele; it only borrows the chart language so show-me stays offline.
**Look (v2.1):** default to a warm, creamy, chill page — pleasant to read, never neon-dark unless the user asks for a dark theme.
## Default: write an HTML file, screenshot it, open it
Terminal-rendered diagrams read poorly. So unless an exception below applies, produce **one self-contained HTML file**, run the "Before opening the file" checklist, then follow "Then screenshot and show it" below.
- Path: `/tmp/show-me-{slug}.html`, where `{slug}` is 2-4 kebab-case words naming the topic.
- `/tmp` is the default so the repo working tree stays clean. Write inside the repo only when the user asks to keep the artifact; then `docs/` or the path they name.
- When the host has an attach-files tool (e.g. `openbot.attach_files_to_response`), the app may not read `/tmp`. Write `~/OpenBot/Shared/show-me/show-me-{slug}.html` instead, running `mkdir -p` on that directory when it is missing. Detect the tool by its presence in your tool list.
### Hard constraints on the HTML
- **Zero network dependencies.** No CDN, no Mermaid script, no Pele, no Google Fonts, no external CSS or JS. The file must render fully offline. A CDN-loaded diagram library renders as a blank box on a flaky network — build diagrams from plain HTML + CSS instead (flexbox/grid boxes, CSS borders, unicode arrows `▶ ▼ └ ├ ──`) or inline SVG. A tiny inline `<script>` is fine for hover or highlight of a bug path.
- Single file. Inline `<style>` in `<head>`; inline `<script>` only if interaction genuinely helps.
- Match the product's colors only when the topic is that product; otherwise use the cream look below. Real labels and real data — never `foo`/`bar` placeholders.
- Responsive: at least one `@media` breakpoint collapsing multi-column layouts to a single stack; no horizontal scroll on mobile.
- Monospace blocks for code, trees and pseudocode, visually distinct from prose.
- Write in the user's language; keep technical terms in English when they are proper nouns or code.
- Slide decks: stack the slides as sections in normal flow, with no `vh` heights or JS-driven one-slide view, so the full-page screenshot shows every slide.
### Cream look (default visual language)
Aim for a page you could read with coffee — soft paper, earthy accents, room to breathe.
```css
:root {
--bg: #FAF6EE; /* warm cream page */
--bg-soft: #F3EDE0; /* slightly deeper cream for wells */
--card: #FFFcf6; /* near-white card */
--text: #3A342C; /* soft charcoal-brown */
--muted: #7A7164; /* warm gray for secondary text */
--line: #D9CFC0; /* soft borders / arrows */
--accent: #8B6F47; /* muted clay / oak */
--accent-2: #6B8F71; /* sage */
--accent-3: #C4A35A; /* honey */
--accent-4: #9B6B6B; /* dusty rose (sparingly) */
--shadow: 0 8px 28px rgba(58, 52, 44, 0.07);
--radius: 16px;
--serif: "Iowan Old Style", "Palatino Linotype", Palatino, "Book Antiqua",
Georgia, "Times New Roman", serif;
--sans: "Avenir Next", "Segoe UI", system-ui, -apple-system, sans-serif;
--mono: ui-monospace, "SF Mono", Menlo, Consolas, monospace;
}
body {
background: var(--bg);
color: var(--text);
font-family: var(--serif);
line-height: 1.55;
max-width: 42rem; /* comfortable measure for prose */
margin-inline: auto;
padding: 2rem 1.25rem 3.5rem;
}
/* Wide layouts (charts, comparison grids) may open to ~1100px;
keep body prose columns ≤ ~42rem inside cards. */
.card {
background: var(--card);
border: 1px solid var(--line);
border-radius: var(--radius);
box-shadow: var(--shadow);
padding: 1.15rem 1.25rem;
}
```
Rules of thumb:
- **Background** `#FAF6EE` (or nearby cream). Avoid pure white full-bleed and avoid dark navy unless requested.
- **Cards** rounded (`14–18px`), gentle shadow, thin soft border — never hard black outlines.
- **Type**: serif or humanist for titles and body; system stack only (offline). Sans for UI chrome and labels on dense charts. Mono only for code.
- **Measure**: ~60–75 characters for reading blocks; charts can span wider.
- **Whitespace**: generous padding; prefer gap over divider lines.
- **Arrows / edges**: stroke in `--line` or a muted sage/clay, ~1.5–2px, soft arrowheads — not neon.
- **Accents**: earthy clay, sage, honey, dusty rose. One accent family per page.
- **Statechart marks** keep their meaning but soften into the cream palette (see Statechart form).
### Pick the smallest form that makes the point
- **Diagram**: one relationship, flow, or failure chain.
- **Infographic**: several linked facts that need ranking or comparison.
- **Short slide deck**: a sequence that only makes sense in order.
- **Statechart**: the system moves between observable states; see below.
## Statechart form (show-me ∪ poteto /statechart)
Use this when the question is "how does this move?", "what can go wrong on the way?", or the topic is a lifecycle, sync/ingest pipeline, protocol, checkout, or any workflow with named phases.
A worked offline page is [references/statechart-example.html](references/statechart-example.html). Copy its structure, not its labels.
### What to draw
1. **States** labeled with what the *reader* can observe or cares about ("applying snapshot", "ready to retrieve") — not function or variable names (`_pull_and_apply`, `last_sha`).
2. **Arrows** labeled with the event as the reader sees it ("you run sync", "snapshot for HEAD"). Put a condition in brackets when it matters: `9 pm [if quiet]`.
3. **Phase / group colors** — cream-adapted soft fills (still distinct; adapted from pstack `references/render.md`):
- teal `#D7E6DF` · blue `#D9E4F0` · orange `#F0E0D0` · yellow `#F2E8CC` · purple `#E6DDF0` · tan `#E8DFD4` · pink `#F0DDE4`
- Text on phases stays `--text` (`#3A342C`).
4. **Marks** (use CSS classes; `!important` on fill/stroke so they win over phase color) — softened for cream:
- `breaks` — fill `#F7E4E4`, stroke `#B85C5C`, text `#8A3A3A`
- `mayBreak` — fill `#F7ECDD`, stroke `#C4873A`, text `#8A5A20`
- `bugPath` — border `#5B7FA6`, 2.5px (muted steel blue)
- `repeats` — optional; dashed `#8B6FA6` border
5. **Parallel regions** when two things are true at once (dashed soft frame, quiet uppercase mono title).
6. **Aim for ~20 arrows or fewer.** Merge states that act the same; drop resets that every state has. Never merge two states that break *different* rules.
7. **Bug-path hand-off** beside the chart: for each bug, one short block with (a) the rule in the reader's words, (b) the numbered path through state labels, (c) what the model or diagram leaves out.
### How to render (stay offline)
- Prefer **inline SVG** (rects + paths + markers) or HTML/CSS boxes with soft arrows.
- Do **not** embed Mermaid, Pele, or any CDN. show-me's offline rule wins.
- Include a small legend for phase colors and marks.
- Credit line in the page footer or subtitle: `Visual vocabulary adapted from @poteto's /statechart in backnotprop/pstack (MIT · Lauren Tan).`
### When *not* to use this form
- Pure ranking / comparison → Infographic.
- One linear failure chain with no phases → Diagram.
- The user wants a **machine-checked** TLA+ model and TLC counterexamples → hand off to pstack `/statechart` (needs network once for TLC/Java via mise; renders with Pele). show-me can still draw the resulting chart offline afterward if they paste the states.From fmflurry/settings-opencode, MIT.
More from fmflurry/settings-opencode
- 0.779score
interfectio-commentarum
poteto
Spawn Haruspex Commentorum, fix accepted findings, and offer encodings for claimed constraints.
SkillAFreshness: A★ 171Claude Code +9 - 0.655score
chimera
poteto
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
SkillAFreshness: A★ 171Claude Code +9 - 0.649score
humanizer
poteto
Cut AI tells from any writing.
SkillAFreshness: A★ 171Claude Code +9 - 0.643score
e2e
fmflurry
Resolve this project's browser end-to-end stack before /e2e or e2e-runner writes tests.
SkillAFreshness: A★ 171Claude Code +9 - 0.643score
show-your-work
fmflurry
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).
SkillAFreshness: A★ 171Claude Code +9 - 0.643score
why
fmflurry
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.
SkillAFreshness: A★ 171Claude Code +9 - 0.641score
verify-this
fmflurry
Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or…
SkillAFreshness: A★ 171Claude Code +9 - 0.640score
create-verification-skill
fmflurry
Use when creating or refreshing a project's verify-this override.
SkillAFreshness: A★ 171Claude Code +9 - 0.639score
angular-ddd
fmflurry
Domain-Driven Design for Angular/TypeScript: functional patterns with `type` aliases, `readonly` fields, pure rule functions, immutable value types, branded…
SkillAFreshness: A★ 171Claude Code +9 - 0.639score
codebase-exploration
fmflurry
Use when searching a repository, looking up symbols, callers, callees, or imports, and when deciding whether CodeMemory is on.
SkillAFreshness: A★ 171Claude Code +9 - 0.639score
patterns
fmflurry
Use when starting a feature from a skeleton project, or when adding a repository interface or a shared API response envelope.
SkillAFreshness: A★ 171Claude Code +9 - 0.639score
socratic-design
fmflurry
Use when a planning, design, architecture, or refactor decision is still open.
SkillAFreshness: A★ 171Claude Code +9
Signals
- Stars
- 171
- Forks
- 9
- Open issues
- 0
- Last commit (this folder)
- Sep 12, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/fmflurry/settings-opencode
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from fmflurry
- 0.643score
why
fmflurry
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.
SkillAFreshness: A★ 171Claude Code +9 - 0.643score
show-your-work
fmflurry
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).
SkillAFreshness: A★ 171Claude Code +9 - 0.643score
e2e
fmflurry
Resolve this project's browser end-to-end stack before /e2e or e2e-runner writes tests.
SkillAFreshness: A★ 171Claude Code +9 - 0.641score
verify-this
fmflurry
Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or…
SkillAFreshness: A★ 171Claude Code +9 - 0.640score
create-verification-skill
fmflurry
Use when creating or refreshing a project's verify-this override.
SkillAFreshness: A★ 171Claude Code +9 - 0.639score
codebase-exploration
fmflurry
Use when searching a repository, looking up symbols, callers, callees, or imports, and when deciding whether CodeMemory is on.
SkillAFreshness: A★ 171Claude Code +9
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 show-me 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.
Cite this page
show-me skill. Agent Mart. https://agentmart.dev/skills/fmflurry-show-me-3f8418 (last updated 2026-10-24)