Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jin-bo/agentao --skill flint-chart-authorgit clone --depth 1 https://github.com/jin-bo/agentaoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jin-bo/agentao/flint-chart-author)<a href="https://agentmods.dev/skills/jin-bo/agentao/flint-chart-author"><img src="https://agentmods.dev/badge/skills/jin-bo/agentao/flint-chart-author.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00197 | $0.02061 |
| Opus 5 | $0.00098 | $0.01030 |
| Sonnet 5 | $0.00039 | $0.00412 |
| Haiku 4.5 | $0.00020 | $0.00206 |
Grade A, and why
flint-chart-author scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flint-chart-author — Flint 图表规格作者
你把已经拿到手的结构化数据变成一个合法的 ```flint 围栏块。
Flint 是微软研究院的可视化中间语言:给它
「数据 + 图型 + 编码」,它自己推导刻度、轴、标签、图例、布局——所以你不需要写任何
Vega-Lite / ECharts 的底层配置,写多了反而会被丢弃。
图型清单、通道语义、语义类型表、完整示例与失败模式对照见
references/flint-spec.md,按需载入。
边界
| 输入 | 已有的结构化数据、表格、或查询结果(对象数组形态) |
| 职责 | 选图型与编码 · 必要时先聚合 · 生成 / 修复 / 解释 / 校验 flint 规格 |
| 输出 | 一个 ```flint 围栏块(JSON),块外配一句人话说明它在说什么 |
| 不负责 | 数据库连接与取数权限 · 知识库/wiki 维护 · markdown 存放在哪一页 · 浏览器端渲染 |
数据从哪来、图放到哪儿去,都由调用你的那条工作流决定;你只对**「这段 JSON 合法且画出来是对的」**负责。
工作流
1. 先看数据,再选图
看三件事:行数、每列的类型(数值 / 类别 / 日期)、你想让读者看出什么。 最后一件决定图型——参考的图型表按用途分组(对比 / 趋势 / 分布 / 相关 / 构成层级 / 流向 / 时间安排)。
拿不准就选最朴素的那个:类别比大小用 Bar Chart,随时间变化用 Line Chart,两个数值的关系用
Scatter Plot。朴素的图被读懂的概率远高于花哨的图。
2. 必要时先聚合——这是你的活,不是 flint 的
flint 不做聚合(encodings.*.aggregate 只在部分模板生效,别指望)。原始明细表要先自己算成
结论性的聚合结果再内联:GROUP BY 之后的几行、十几行,而不是几百行明细。
判据:这张图要说的那句话,需要几行数据才够? 只要那几行。 搬原始表进来既撞行数上限,也让读者自己去找结论——那是表格的活,不是图的活。
3. 写块
最小形态(semantic_types 可整段省略,flint 会自行推断):
```flint
{"data":{"values":[{"模型":"model-a","评测得分":72.4},{"模型":"model-b","评测得分":81.9}]},
"chart_spec":{"chartType":"Bar Chart",
"encodings":{"x":{"field":"模型"},"y":{"field":"评测得分"}}}}
```
写清楚一点(推荐):加 semantic_types 让刻度/格式/排序更合理,加 baseSize 定尺寸。
字段名用数据里的原名(中文列名完全可以),不要为了图去改名——要改显示名用 field_display_names。
4. 自校验(每次输出前逐条过,不要跳)
- 整块是合法 JSON(不是 YAML、没有注释、没有尾逗号、没有单引号)
- 顶层只有
data/semantic_types/chart_spec/field_display_names/options五个键之内 -
data.values是对象数组且非空;没有data.url(flint 的类型接受 url,但渲染端一般拒绝取远端数据,图不会出现) - 每个单元格是标量(字符串 / 数字 / 布尔)——不放嵌套对象或数组
- 行数 ≤ 1000(这是宿主渲染端的上限、不是 flint 的规格;换宿主时按那边确认。 不过真要画到接近上限,多半是第 2 步的聚合没做够)
-
chart_spec.chartType与参考里的写法逐字符一致(大小写敏感:Bar Chart对,Bar chart错) - 每个
encodings.*.field都能在数据列里找到(任一行有即可) - 数据形状与图型匹配(
Histogram的x必须是数值列、Calendar Heatmap的x必须是日期串……见参考) - 若写了
baseSize:宽高都是有限正数、且在 160–1600 × 120–1200 内 (注意:baseSize是基准不是上限——flint 会按类别数/分面数把它放大,实测420×260在多序列下会长到657×514。渲染端卡的是放大后的尺寸,所以类别特别多时要么减少类别、 要么用canvasSize给一个硬上限,它是真会生效的钳制)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 108 lines · 197 tokens per session scan A c6ce218fdc7c
flint-chart-author is a skill published in the GitHub repository jin-bo/agentao (100 stars, last pushed today), licensed MIT. It adds 197 tokens to every session and 2,061 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…