Skip to content
Development
Skill

/ork-glyph

Render an answer inline as compact ASCII or box-drawing art with semantic status icons. Use for status, inventories, budgets, comparisons, rankings, pipelines, or requests to show something visually. Do not use for definitions, conceptual explanations, one-sentence answers, or

From plugin
orchestkit
301122 skills36 agents

Claude Code

$ npx -y skills add yonatangross/orchestkit --skill ork-glyph --agent claude-code

SKILL.md

ork-glyph.SKILL.md
name: ork-glyph
description: Render an answer inline as compact ASCII or box-drawing art with semantic status icons. Use for status, inventories, budgets, comparisons, rankings, pipelines, or requests to show something visually. Do not use for definitions, conceptual explanations, one-sentence answers, or requests for a saved page or file.

Ork Glyph

Render immediately from the user's topic. With no topic, use the current conversation. Choose the form yourself without setup questions, task creation, or subagents. The inline rendering itself needs no external tools.

Encode information in structure. State the verdict in one prose line, then draw one render in a monospace code block. Follow it with two or three short observations when the diagram reveals something worth explaining.

Choose the form

| Data shape | Render | |---|---| | Inventory, audit, budget | Header meter, sections, rows, totals, caveats | | Status, progress, health | Status box and bar meters | | Options, trade-offs | Comparison table | | Steps, pipeline, handoffs | Flow with arrows | | Containment, layers | Nested boxes or tree | | Ranking, scores, counts | Table and bars | | Change over time | Sparkline or milestone track |

Rendering contract

  • One render per reply, at most about 50 lines. In a terminal, keep each line

within 76 display cells. In chat, web transcripts, and other non-TTY surfaces, use at most 72 cells and one narrow table or a vertical list, never side-by-side boards. Default to the non-TTY layout when the surface is uncertain.

  • Use one box style per render: `┌─┐│└─┘` normally, `╭─╮│╰─╯` for soft status

cards, or `+-|` for ASCII-only surfaces. Keep nesting to three levels. Use arrows `→`, `↓`, or `->` and meters `▓▓▓░░` with the numeric value beside them.

  • Pair every status icon with a word: ✅ done, ❌ failed, ⚠️ warning,

🔄 in progress, ⏸ waiting, 💡 idea, 🚨 hard block, 🎯 goal, 🔥 top priority, 📜 doc, 🤖 agent, ⚡ hook, ℹ️ caveat. Risk uses 🟢 low, 🟡 medium, 🔴 high; ranking uses 🥇 1st, 🥈 2nd, 🥉 3rd.

  • For domain rows, use at most one leading icon: 🐳 docker, 🌐 browser,

📦 package, 🐍 python, 🧠 model, 📱 device, 💾 volume, 🗑️ trash, 🗂️ files, 📥 downloads, 🔑 secret, 🧪 test, 🖥️ host, ☁️ cloud, 📧 mail, 💬 chat. Keep icons out of prose sentences and avoid emoji chains.

  • Align labels and numbers by display width, accounting for wide characters.

Avoid full-width decorative rules, em or en dashes, and Mermaid in this inline mode.

  • Use only supplied or verified data. Print `?` for unknown values. Show units,

denominators, and arithmetic for totals; call out overlaps or estimates.

  • An inventory proceeds from subject and headline meter to labeled sections,

then rows containing label, bar, value, and action when relevant. Finish with section totals, the overall arithmetic, and caveats. Omit unsupported fields.

Example with supplied counts:

Checks        3 / 4 passed
┌──────────┬─────────────┐
│ Unit     │ ✅ done     │
│ Security │ ✅ done     │
│ Build    │ ✅ done     │
│ Browser  │ ⏸ waiting  │
└──────────┴─────────────┘

Keep output inline unless the user requested a file. If the full data exceeds the budget, render a labeled summary and state what was omitted. For an explicit file or page request, use the host's available artifact workflow and link the resulting artifact; do not assume another plugin's commands exist.

Read more
@yonatangross
Ships withorchestkit

The Complete AI Development Toolkit for Claude Code. 115 skills, 36 agents, 163 hooks. Install `ork` for stable (v10.x).

301122 skills36 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
301
Star history of yonatangross/orchestkit on GitHub, a chart by star-history.com

Other skills on orchestkit.

ork-assess

ork-assess

Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a…

ork-brainstorm

ork-brainstorm

Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when a request…

ork-explore

ork-explore

Map an unfamiliar codebase, feature, architecture, data flow, or operational path with file-backed evidence. Use when a request…

ork-implement

ork-implement

Make an approved, scoped change and prove the affected behavior. Use when a request asks to implement, build, add, or land a…

ork-review-pr

ork-review-pr

Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a…

ork-verify

ork-verify

Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to…

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills12d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc13d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react3d252k
@facebook@facebookInstall Skill

Questions about ork-glyph.

Which coding agents can use ork-glyph?
ork-glyph installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.