메뉴
Check Mermaid CLI, Vega CLI, matplotlib, cairosvg availability and report readiness.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | verify |
| description | Check Mermaid CLI, Vega CLI, matplotlib, cairosvg availability and report readiness. |
| allowed-tools | Bash(python *), Bash(npx *), Bash(which *) |
Check whether this plugin's prerequisites are met and report readiness.
python3 -c "
import json
deps = {}
try:
import matplotlib; deps['matplotlib'] = matplotlib.__version__
except Exception: deps['matplotlib'] = None
try:
import seaborn; deps['seaborn'] = seaborn.__version__
except Exception: deps['seaborn'] = None
try:
from PIL import Image; import PIL; deps['Pillow'] = PIL.__version__
except Exception: deps['Pillow'] = None
try:
import cairosvg; deps['cairosvg'] = 'installed'
except Exception: deps['cairosvg'] = None
print(json.dumps(deps))
"
npx mmdc --version 2>/dev/null || echo "NOT_FOUND"
npx vl2svg --version 2>/dev/null || echo "NOT_FOUND"
PLUGIN: jack-tar-custom-smartart
VERSION: 1.0.0
DEPENDENCIES:
matplotlib: READY (3.9.1)
seaborn: READY (0.13.2)
Pillow: READY (10.2.0)
cairosvg: READY (rasteriser: cairosvg)
Mermaid CLI: READY (11.12.0)
Vega CLI: READY (6.2.0)
Vega-Lite: READY (6.4.2)
ENGINES:
custom_svg: READY (9 layouts: flowchart, decision_tree, timeline, venn, swot, feature_matrix, pipeline_funnel, radar_chart, gantt)
mermaid: READY
vega_lite: READY
matplotlib: READY (chart types: bar, line, area, pie, donut, scatter, radar)
STATUS: FULLY_AVAILABLE
REASON: All rendering engines available
Status rules:
STATUS: FULLY_AVAILABLE — all engines present (matplotlib, Mermaid CLI, Vega CLI)STATUS: PARTIALLY_AVAILABLE — Mermaid or Vega CLIs missing (custom SVG and matplotlib still work)STATUS: NOT_AVAILABLE — matplotlib missing (core engine unavailable)Produce a labeled figure with PERFECT text — render a label-free image locally (or take an external image) then overlay leader lines and typeset labels programmatically from vision-derived anchor coordinates. Text is correct by construction; only pointer placement is reviewed.
Ask which image models fit a set of tasks — get evidence-based recommendations with per-image costs, which external services to pay for, and which local models to install (with disk/RAM/licence guidance). Reads the live model catalog and probes what is actually available on this machine.
Check mflux (MLX) availability, per-family runtime presence, cached weights, and report readiness status.
Top-level image orchestrator. Routes all slide image generation to the appropriate skill (jack-tar-ollama:image, jack-tar-ollama:icon, jack-tar-ollama:pattern, jack-tar-ollama:diagram, jack-tar-cloud:image, jack-tar-cloud:icon, render_chart). Produces ImageManifest and ChartManifest. Also reads strategy-map.json to determine per-slide rendering approach (full_render, backdrop_render, composed).
Meta-verify — discover all jack-tar engine plugins, call each verify, report aggregate pipeline capability and discipline-hook readiness.
Generate an image locally on Apple Silicon via the mflux CLI (MLX). Flag-compatible with jack-tar-ollama's /image — a $0 local tier, no API keys needed.