ascii
Skill9 starsChanged 2 months agoMITView on GitHub
DEFAULT diagram skill — simplest tier. Use when user invokes /claude-teacher:ascii OR when suggesting a quick visual. Creates ASCII art rendered inline in terminal — zero friction. Escalate to /claude-teacher:excalidraw for complex static diagrams (5+ components, multi-layer). Escalate to /claude-teacher:demo for animated/dynamic concepts (protocol handshakes, algorithm traces, state transitions).
1 other project uses a version of this.
Adopted by
Most recently taken up by
- EveryInc/ascii-factorytheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- EveryInc/ascii-factory★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- challengeSkill
- compareSkill
- demoSkill
- excalidrawSkill
- flashcardsSkill
- init-eduSkill
- motivateSkill
- progressSkill
- quiz-meSkill
- researchSkill
- reset-eduSkill
- roadmapSkill
- save-progressSkill
- summarySkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Before accessing education data, read ${CLAUDE_PLUGIN_ROOT}/references/education-data.md.
- Distinctive: line 13
Create ASCII art diagrams with detailed educational explanations.
- Very specific: line 81
Avoid ASCII diamond shapes — use condition?
- Distinctive: line 93
Use pure ASCII for this style — IETF convention
- Very specific: line 138
Never mix pure ASCII (+ - |) with Unicode box-drawing in the same diagram
- Distinctive: line 140
Use 2+ space gaps between unrelated elements
- Distinctive: line 141
Keep consistent arrow lengths in sequence diagrams
- Distinctive: line 142
If a diagram exceeds ~40 lines or ~10 nodes, split it up
- Distinctive: line 146
After creating the diagram and explanation:
- Very specific: line 154
If the concept corresponds to a tracked topic, update only last_seen.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Requested topic/task: $ARGUMENTS
Before accessing education data, read ${CLAUDE_PLUGIN_ROOT}/references/education-data.md. Resolve every <education-db> below using that contract. Current session ID: ${CLAUDE_SESSION_ID}.
ASCII
Create ASCII art diagrams with detailed educational explanations. All output is pure Unicode box-drawing art — renders in any modern terminal, no external tools needed.
Invocation
/claude-teacher:ascii <concept description>
Style Selection
| Concept Type | Style | Example Use |
| Time-ordered (protocol flows, request/response) | Sequence diagram | TCP handshake, HTTP request |
| States/decisions (transitions, branching) | Flowchart | Connection lifecycle, error handling |
| Byte-level/structural (memory, packets, formats) | RFC-style grid or table | TCP header, packet layout |
| Relationships/architecture (components, deps) | Box-and-line with layers | System architecture, module deps |
| Comparisons (A vs B) | Side-by-side or before/after | Active vs passive mode |
| Hierarchies (trees, org charts) | Tree with branches | Directory structure, class hierarchy |
Character Toolkit
Visual hierarchy through line weight:
| Weight | Characters | Use For |
| Double | ═ ║ ╔ ╗ ╚ ╝ ╠ ╣ ╦ ╩ ╬ | Outer boundaries, system borders, emphasis |
| Single | ─ │ ┌ ┐ └ ┘ ├ ┤ ┬ ┴ ┼ | Standard boxes, connections |
| Rounded | ╭ ╮ ╰ ╯ | Softer/informal elements |
| Dashed | ┄ ┆ or - - - | Optional, conditional, weak relationships |
| Heavy | ━ ┃ ┏ ┓ ┗ ┛ | Bold emphasis |
Arrows: → ← ↑ ↓ ↔ standard, ▶ ◀ ▲ ▼ filled, ⇒ ⇐ double
Fill/shading: ░ light, ▒ medium, ▓ dark, █ full
Elision: ⋮ vertical omission, ⋯ horizontal omission
Style Recipes
Sequence Diagram
Client Server
│ │
│ SYN (seq=x) │
│───────────────────▶│
│ │
│ SYN-ACK (seq=y) │
│◀───────────────────│
│ │- Vertical lifelines per actor, names at top
- Horizontal arrows with labels above
- Consistent column spacing and arrow lengths
Flowchart
┌─────────┐
│ Start │
└────┬────┘
│
▼
condition? ──no──▶ Action B
│ │
yes │
│ │
▼ │
Action A │
│ │
◀─────────────────┘- Avoid ASCII diamond shapes — use
condition?with branching labels instead - Label branches on the arrows
RFC-Style Protocol Header
0 1 2 3
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Source Port | Destination Port |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+- Each
-+-= one bit, centered field names - Use pure ASCII for this style — IETF convention
Architecture / Layer Diagram
╔═══════════════════════════════╗
║ Presentation Layer ║
║ ┌────────┐ ┌───────────┐ ║
║ │ CLI │ │ REST API │ ║
║ └───┬────┘ └─────┬─────┘ ║
╠══════╪════════════════╪═══════╣
║ ▼ Service Layer▼ ║
║ ┌────────────────────────┐ ║
║ │ Core Logic │ ║
║ └───────────┬────────────┘ ║
╚══════════════╪════════════════╝
▼
┌──────────┐
│ Database │
└──────────┘- Double-line for system boundaries
- Single-line for components inside
- Horizontal dividers between layers
Process
- Analyze the concept — what type of information is it?
- Pick style using the selection table
- Research the concept using WebSearch before creating the diagram — verify accuracy against official docs, RFCs, or standards. Include source links.
- Create the diagram in a
textcode block:- Max width 78 characters
- Generous whitespace — padding inside boxes
- Standardize box widths where possible
- Center vertical connectors under boxes
- Break complex concepts into multiple smaller diagrams
- Write educational explanation:
- What it shows — walk through the diagram
- Why it works this way — reasoning behind the design
- Key concepts — define terms that might be new
- Common pitfalls — what people often misunderstand
- Sources — links to official docs, RFCs, or standards used
- Save to docs/ — automatically save the diagram and explanation to
docs/<concept-name>.mdfor future reference.
Quality Rules
- Never mix pure ASCII (
+ - |) with Unicode box-drawing in the same diagram - Align everything carefully — misaligned ASCII art is worse than no diagram
- Use 2+ space gaps between unrelated elements
- Keep consistent arrow lengths in sequence diagrams
- If a diagram exceeds ~40 lines or ~10 nodes, split it up
DB Integration
After creating the diagram and explanation:
- Save to project-local
docs/<concept-name>.md(for project-specific concepts) - Save to global
<education-db>/docs/<concept-name>.md(for general concepts) - Append to session log
<education-db>/sessions/[date].jsonl:{"time": "[now]", "event": "ascii", "topic": "[concept-slug]", "saved_to": "global|project|both"} - If the concept corresponds to a tracked topic, update only
last_seen; preserve its assessment dates and review interval
Integration with Other Skills
This skill is part of the claude-teacher plugin:
/claude-teacher:quiz-me— if a student gets a visual concept wrong during a quiz, suggest illustrating it./claude-teacher:challenge— challenges may need diagrams as part of the answer./claude-teacher:progress— diagrams count toward topic engagement.- Diagrams saved to
docs/become the student's personal reference library. - The tutor (via CLAUDE.md) will suggest
/claude-teacher:asciiwhen visual explanation helps.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

