MCP HubMCP Hub
스킬 목록으로 돌아가기

create-glyph

pjt222
업데이트됨 Yesterday
3 조회
17
2
17
GitHub에서 보기
메타aidesign

정보

이 스킬은 ggplot2와 프리미티브 라이브러리를 사용하여 시각화 아이콘을 위한 R 기반 픽토그램 글리프를 생성합니다. 컨셉과 색상 전략부터 등록, 빌드 렌더링, 네온 글로우 출력 검증까지 전체 파이프라인을 처리합니다. 새로운 엔티티에 아이콘이 필요할 때, 기존 글리프를 교체할 때, 또는 새로운 도메인을 위해 일괄 생성할 때 사용하세요.

빠른 설치

Claude Code

추천
기본
npx skills add pjt222/agent-almanac -a claude-code
플러그인 명령대체
/plugin add https://github.com/pjt222/agent-almanac
Git 클론대체
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/create-glyph

Claude Code에서 이 명령을 복사하여 붙여넣어 스킬을 설치하세요

문서

Create Glyph

Create R-based pictogram glyphs for skill, agent, or team icons in the viz/ visualization layer. Each glyph is a pure-ggplot2 function that draws a recognizable shape on a 100x100 canvas, rendered with a neon glow effect to transparent-background WebP.

When to Use

  • A new skill, agent, or team has been added and needs a visual icon
  • An existing glyph needs replacement or redesign
  • Batch-creating glyphs for a new domain of skills
  • Prototyping visual metaphors for entity concepts

Inputs

  • Required: Entity type — skill, agent, or team
  • Required: Entity ID (e.g., create-glyph, mystic, r-package-review) and domain (for skills)
  • Required: Visual concept — what the glyph should depict
  • Optional: Reference glyph to study for complexity level
  • Optional: Custom --glow-sigma value (default: 4)

Procedure

Step 1: Concept — Design the Visual Metaphor

Identify the entity being iconified and choose a visual metaphor.

  1. Read the entity's source file to understand its core concept:
    • Skills: skills/<id>/SKILL.md
    • Agents: agents/<id>.md
    • Teams: teams/<id>.md
  2. Choose a metaphor type:
    • Literal object: a flask for experiments, a shield for security
    • Abstract symbol: arrows for merging, spirals for iteration
    • Composite: combine 2-3 simple shapes (e.g., document + pen)
  3. Reference existing glyphs for complexity calibration:
Complexity Tiers:
+----------+--------+-------------------------------------------+
| Tier     | Layers | Examples                                  |
+----------+--------+-------------------------------------------+
| Simple   | 2      | glyph_flame, glyph_heartbeat              |
| Moderate | 3-5    | glyph_document, glyph_experiment_flask    |
| Complex  | 6+     | glyph_ship_wheel, glyph_bridge_cpp        |
+----------+--------+-------------------------------------------+
  1. Decide on a function name: glyph_<descriptive_name> (snake_case, unique)

Got: A clear mental sketch of the shape with 2-6 planned layers.

If fail: If the concept is too abstract, fall back to a related concrete object. Review existing glyphs in the same domain for inspiration.

Step 2: Compose — Write the Glyph Function

Write the R function that produces ggplot2 layers.

  1. Function signature (immutable contract):

    glyph_<name> <- function(cx, cy, s, col, bright) {
      # cx, cy = center coordinates (50, 50 on 100x100 canvas)
      # s = scale factor (1.0 = fill ~70% of canvas)
      # col = domain color hex (e.g., "#ff88dd" for design)
      # bright = brightened variant of col (auto-computed by renderer)
      # Returns: list() of ggplot2 layers
    }
    
  2. Apply scale factor * s to ALL dimensions for consistent scaling:

    r <- 20 * s        # radius
    hw <- 15 * s       # half-width
    lw <- .lw(s)       # line width (default base 2.5)
    lw_thin <- .lw(s, 1.2)  # thinner line width
    
  3. Build geometry using available primitives:

    GeometryUsage
    ggplot2::geom_polygon(data, .aes(x, y), ...)Filled shapes
    ggplot2::geom_path(data, .aes(x, y), ...)Open lines/curves
    ggplot2::geom_segment(data, .aes(x, xend, y, yend), ...)Line segments, arrows
    ggplot2::geom_rect(data, .aes(xmin, xmax, ymin, ymax), ...)Rectangles
    ggforce::geom_circle(data, .aes(x0, y0, r), ...)Circles
  4. Apply the color strategy:

    Alpha Guide:
    +----------------------+------------+--------------------------+
    | Purpose              | Alpha      | Example                  |
    +----------------------+------------+--------------------------+
    | Large fill (body)    | 0.08-0.15  | hex_with_alpha(col, 0.1) |
    | Medium fill (accent) | 0.15-0.25  | hex_with_alpha(col, 0.2) |
    | Small fill (detail)  | 0.25-0.35  | hex_with_alpha(bright, 0.3) |
    | Outline stroke       | 1.0        | color = bright           |
    | Secondary stroke     | 1.0        | color = col              |
    | No fill              | ---        | fill = NA                |
    +----------------------+------------+--------------------------+
    
  5. Return a flat list() of layers (the renderer iterates and wraps each with glow)

  6. Place the function in the appropriate primitives file based on entity type:

    • Skills: domain-grouped across 19 primitives files:
      • primitives.R — bushcraft, compliance, containerization, data-serialization, defensive
      • primitives_2.R — devops, general, git, mcp-integration
      • primitives_3.R — mlops, observability, PM, r-packages, reporting, review, web-dev, esoteric, design
      • Additional primitives_4.R through primitives_19.R for newer domains
    • Agents: viz/R/agent_primitives.R
    • Teams: viz/R/team_primitives.R

Got: A working R function that returns a list of 2-6 ggplot2 layers.

If fail: If ggforce::geom_circle causes errors, ensure ggforce is installed. If coordinates are off, remember the canvas is 100x100 with (0,0) at bottom-left. Test the function interactively:

source("viz/R/utils.R"); source("viz/R/primitives.R")  # etc.
layers <- glyph_<name>(50, 50, 1.0, "#ff88dd", "#ffa8f0")
p <- ggplot2::ggplot() + ggplot2::coord_fixed(xlim=c(0,100), ylim=c(0,100)) +
     ggplot2::theme_void()
for (l in layers) p <- p + l
print(p)

Step 3: Register — Map Entity to Glyph

Add the entity-to-glyph mapping in the appropriate glyph mapping file.

For skills:

  1. Open viz/R/glyphs.R
  2. Find the comment section for the target domain (e.g., # -- design (3))
  3. Add the entry in alphabetical order within the domain block:
    "skill-id" = "glyph_function_name",
    
  4. Update the domain count in the comment if applicable

For agents:

  1. Open viz/R/agent_glyphs.R
  2. Find the alphabetical position in AGENT_GLYPHS
  3. Add the entry:
    "agent-id" = "glyph_function_name",
    

For teams:

  1. Open viz/R/team_glyphs.R

  2. Find the alphabetical position in TEAM_GLYPHS

  3. Add the entry:

    "team-id" = "glyph_function_name",
    
  4. Verify no duplicate ID exists in the target list

Got: The appropriate *_GLYPHS list contains the new mapping.

If fail: If the build later reports "No glyph mapped", double-check that the entity ID exactly matches the one in the manifest and registry.

Step 4: Manifest — Add Icon Entry

Register the icon in the appropriate manifest file.

For skills: viz/data/icon-manifest.json

{
  "skillId": "skill-id",
  "domain": "domain-name",
  "prompt": "<domain basePrompt>, <descriptors>, dark background, vector art",
  "seed": <next_seed>,
  "path": "public/icons/cyberpunk/<domain>/<skill-id>.webp",
  "status": "pending"
}

For agents: viz/data/agent-icon-manifest.json

{
  "agentId": "agent-id",
  "prompt": "<agent-specific descriptors>, dark background, vector art",
  "seed": <next_seed>,
  "path": "public/icons/cyberpunk/agents/<agent-id>.webp",
  "status": "pending"
}

For teams: viz/data/team-icon-manifest.json

{
  "teamId": "team-id",
  "prompt": "<team-specific descriptors>, dark background, vector art",
  "seed": <next_seed>,
  "path": "public/icons/cyberpunk/teams/<team-id>.webp",
  "status": "pending"
}

Got: Valid JSON with the new entry placed among its type siblings.

If fail: Validate JSON syntax. Common mistakes: trailing comma after last array element, missing quotes.

Step 5: Render — Generate the Icon

Run the icon pipeline to render the new glyph. Always use build.sh as the entry point — it handles platform detection and R binary selection. See render-icon-pipeline for the full flag reference and pipeline architecture.

# From project root — renders all palettes, standard + HD, skips existing icons
bash viz/build.sh --only <domain> --skip-existing          # skills
bash viz/build.sh --type agent --only <id> --skip-existing # agents
bash viz/build.sh --type team --only <id> --skip-existing  # teams

# Dry run first:
bash viz/build.sh --only <domain> --dry-run

build.sh runs the full pipeline (palette → data → manifest → render → terminal glyphs). The non-render steps add ~10 seconds but ensure all data is current.

Output locations:

  • Skills: viz/public/icons/<palette>/<domain>/<skill-id>.webp
  • Agents: viz/public/icons/<palette>/agents/<agent-id>.webp
  • Teams: viz/public/icons/<palette>/teams/<team-id>.webp

Got: The log shows OK: <entity> (seed=XXXXX, XX.XKB) and the WebP file exists.

If fail:

  • "No glyph mapped" — Step 3 mapping is missing or has a typo
  • "Unknown domain" — Domain not in get_palette_colors() in palettes.R
  • R package errors — Run install.packages(c("ggplot2", "ggforce", "ggfx", "ragg", "magick")) first
  • If rendering crashes, test the glyph function interactively (see Step 2 fallback)

Step 6: Verify — Visual Inspection

Check the rendered output meets quality standards.

  1. Verify file exists and has reasonable size:

    ls -la viz/public/icons/cyberpunk/<type-path>/<entity-id>.webp
    # Expected: 15-80 KB typical range
    
  2. Open the WebP in an image viewer to check:

    • Shape reads clearly at full size (1024x1024)
    • Neon glow is present but not overpowering
    • Background is transparent (no black/white rectangle)
    • No clipping at canvas edges
  3. Check at small sizes (the icon renders at ~40-160px in the force graph):

    • Shape remains recognizable
    • Detail doesn't turn to noise
    • Glow doesn't overwhelm the shape

Got: A clear, recognizable pictogram with even neon glow on transparent background.

If fail:

  • Glow too strong: re-render with --glow-sigma 2 (default is 4)
  • Glow too weak: re-render with --glow-sigma 8
  • Shape unreadable at small sizes: simplify the glyph (fewer layers, bolder strokes, increase .lw(s, base) base value)
  • Clipping at edges: reduce shape dimensions or shift center

Step 7: Iterate — Refine if Needed

Make adjustments and re-render.

  1. Common adjustments:

    • Bolder strokes: increase .lw(s, base) — try base = 3.0 or 3.5
    • More visible fill: increase alpha from 0.10 to 0.15-0.20
    • Shape proportions: adjust multipliers on s (e.g., 20 * s -> 24 * s)
    • Add/remove detail layers: keep total layers between 2-6 for best results
  2. To re-render after changes:

    # Delete the existing icon first, then re-render
    rm viz/public/icons/cyberpunk/<type-path>/<entity-id>.webp
    # Use the appropriate build command from Step 5
    
  3. When satisfied, verify the manifest status shows "done" (the build script updates it automatically on success)

Got: The final icon passes all verification checks from Step 6.

If fail: If after 3+ iterations the glyph still doesn't read well, consider using a completely different visual metaphor (return to Step 1).

Reference

Domain and Entity Color Palettes

All 58 domain colors (for skills) are defined in viz/R/palettes.R (the single source of truth). Agent and team colors are also managed in palettes.R. The cyberpunk palette (hand-tuned neon colors) is in get_cyberpunk_colors(). Viridis-family palettes are auto-generated via viridisLite.

To look up a color:

source("viz/R/palettes.R")
get_palette_colors("cyberpunk")$domains[["design"]]   # skill domain
get_palette_colors("cyberpunk")$agents[["mystic"]]     # agent
get_palette_colors("cyberpunk")$teams[["tending"]]     # team

When adding a new domain, add it to three places in palettes.R:

  1. PALETTE_DOMAIN_ORDER (alphabetical)
  2. get_cyberpunk_colors() domains list
  3. Run bash viz/build.sh to regenerate palettes, data, and manifests

Glyph Function Catalog

See the full catalog of available glyph functions in the primitives source files:

  • Skills: viz/R/primitives.R through viz/R/primitives_19.R (domain-grouped)
  • Agents: viz/R/agent_primitives.R
  • Teams: viz/R/team_primitives.R

Helper Functions

FunctionSignaturePurpose
.lw(s, base)(scale, base=2.5)Scale-aware line width
.aes(...)alias for ggplot2::aesShorthand aesthetic mapping
hex_with_alpha(hex, alpha)(string, 0-1)Add alpha to hex color
brighten_hex(hex, factor)(string, factor=1.3)Brighten a hex color
dim_hex(hex, factor)(string, factor=0.4)Dim a hex color

Validation Checklist

  • Glyph function follows glyph_<name>(cx, cy, s, col, bright) -> list() signature
  • All dimensions use * s scaling factor
  • Color strategy uses col for fills, bright for outlines, hex_with_alpha() for transparency
  • Function placed in correct primitives file for entity type and domain
  • Glyph mapping entry added in the appropriate *_glyphs.R file
  • Manifest entry added with correct entity ID, path, and "status": "pending"
  • Build command runs without error (dry-run first)
  • Rendered WebP exists at the expected path
  • File size in expected range (15-80 KB)
  • Icon reads clearly at both 1024px and ~40px display sizes
  • Transparent background (no solid rectangle behind the glyph)
  • Manifest status updated to "done" after successful render

Pitfalls

  • Forgetting * s: Hard-coded pixel values break when scale changes. Always multiply by s.
  • Canvas origin confusion: (0,0) is bottom-left, not top-left. Higher y values move UP.
  • Double glow: The renderer already applies ggfx::with_outer_glow() to every layer. Do NOT add glow inside the glyph function.
  • Too many layers: Each layer gets individual glow wrapping. More than 8 layers makes rendering slow and visually noisy.
  • Mismatched IDs: The entity ID in the glyph mapping, manifest, and registry must all match exactly.
  • JSON trailing commas: The manifest is strict JSON. No trailing comma after the last array element.
  • Missing domain color: If the domain isn't in get_cyberpunk_colors() in palettes.R, rendering will error. Add the color first, then regenerate.
  • Wrong primitives file: Skills go in domain-grouped primitives*.R, agents in agent_primitives.R, teams in team_primitives.R.

Related Skills

  • enhance-glyph — improve an existing glyph's visual quality, fix rendering issues, or add detail layers
  • audit-icon-pipeline — detect missing glyphs and icons to know what needs creating
  • render-icon-pipeline — run the full rendering pipeline end-to-end
  • ornament-style-mono — complementary AI-based image generation (Z-Image vs R-coded glyphs)
  • ornament-style-color — color theory applicable to glyph accent fill decisions
  • create-skill — the parent workflow that triggers glyph creation when adding new skills

GitHub 저장소

pjt222/agent-almanac
경로: i18n/caveman-lite/skills/create-glyph
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

연관 스킬

content-collections

메타

이 스킬은 콘텐츠 콜렉션(Content Collections)을 위한 프로덕션 검증된 설정을 제공합니다. 콘텐츠 콜렉션은 Markdown/MDX 파일을 Zod 검증이 포함된 타입 안전한 데이터 콜렉션으로 변환해주는 TypeScript 최우선 도구입니다. 블로그, 문서 사이트 또는 콘텐츠 중심의 Vite + React 애플리케이션을 구축할 때 타입 안전성과 자동 콘텐츠 검증을 보장하기 위해 사용하세요. Vite 플러그인 구성과 MDX 컴파일부터 배포 최적화 및 스키마 검증에 이르기까지 모든 것을 다룹니다.

스킬 보기

polymarket

메타

이 스킬은 개발자들이 Polymarket 예측 시장 플랫폼을 활용한 애플리케이션을 구축할 수 있도록 지원하며, 거래 및 시장 데이터를 위한 API 통합 기능을 포함합니다. 또한 WebSocket을 통한 실시간 데이터 스트리밍을 제공하여 실시간 거래와 시장 활동을 모니터링할 수 있습니다. 이를 통해 거래 전략을 구현하거나 실시간 시장 업데이트를 처리하는 도구를 생성하는 데 활용할 수 있습니다.

스킬 보기

creating-opencode-plugins

메타

이 스킬은 개발자들이 명령어, 파일, LSP 작업 등 25개 이상의 이벤트 유형에 연결되는 OpenCode 플러그인을 만들 수 있도록 돕습니다. JavaScript/TypeScript 모듈을 위한 플러그인 구조, 이벤트 API 명세, 구현 패턴을 제공합니다. OpenCode AI 어시스턴트의 라이프사이클을 사용자 정의 이벤트 기반 로직으로 가로채거나, 모니터링하거나, 확장해야 할 때 사용하세요.

스킬 보기

sglang

메타

SGLang은 RadixAttention 프리픽스 캐싱을 활용하여 JSON, 정규식, 에이전트 워크플로우를 위한 고속 구조화 생성에 특화된 고성능 LLM 서빙 프레임워크입니다. 특히 반복되는 프리픽스가 있는 작업에서 상당히 빠른 추론 속도를 제공하여 복잡한 구조화 출력 및 다중 턴 대화에 이상적입니다. 제약 디코딩이 필요하거나 광범위한 프리픽스 공유가 있는 애플리케이션을 구축할 때는 vLLM과 같은 대안보다 SGLang을 선택하십시오.

스킬 보기