BF archviz-skills
Restrained information visualization skill pack for AI agents. Every visualization starts with a brief read and three dials. Supports Mermaid, ASCII/termaid terminal rendering, self-contained HTML, Python (Plotly), Obsidian Canvas, draw.io guidance, and Three.js 3D archviz. Text-first, preview-compatible, anti-slop. Default mode is 2D infoviz; enter 3D only when the brief mentions building, floorplan, structure, or spatial walkthrough. Use when the user asks for diagram, visualization, chart, gantt, sankey, mindmap, flowchart, xychart, 可视化, 架构图, 流程图, 信息图, 甘特图, funnel, state diagram, decision matrix, 封面, 卡片, 信息卡, 分享图, 排版, or 3D building/archviz.
Restrained information visualization skill pack for AI agents.
As a process F 45/100 · Will not run — References files that are not bundled: templates/<mode>/
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 60. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6790 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: templates/<mode>/
Process rating: all ten parameters 45/100
- 0Tools and files. 1 referenced file(s) missing: templates/<mode>/
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 4 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 6790 tokens
- 85Steps. 117 steps, 2 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 27 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +3Description length 652: enough signal without eating the budget
- +4Structure: 37 headings
- +3Step-by-step instructions: 117 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (5 of 8)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.