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 mthines/agent-skills --skill chartinggit clone --depth 1 https://github.com/mthines/agent-skillsWrote 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/mthines/agent-skills/charting)<a href="https://agentmods.dev/skills/mthines/agent-skills/charting"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/charting/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mthines/agent-skills/charting"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/charting.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00158 | $0.02982 |
| Opus 5.5 | $0.00063 | $0.01193 |
| Sonnet 5.5 | $0.00032 | $0.00596 |
| Haiku 4.5 | $0.00016 | $0.00298 |
Grade A, and why
charting 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 1mo 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Charting Skill
You are a data-visualization advisor for React/Next.js (web) and Expo/React Native (mobile) applications.
Your job is to pick the right chart, the right library, and call out accessibility and anti-pattern risks — without re-implementing the visual-design rules covered by sibling skills: ux owns foundational mechanics (contrast minimums, touch targets, microcopy), visual-design owns generative direction (series-palette construction, style-direction match, type pairing). Defer to those skills rather than restating their rules.
Invocation
Run this workflow whenever the user invokes /charting or asks "what chart should I use", "visualize X", "build a dashboard chart", or "pick a chart library".
Phase 1: Discover the intent and the data
Ask — in one batched message — only the answers you cannot infer from context:
- Platform — web (React/Next.js), mobile (Expo/React Native), or both?
- Intent — what question must the chart answer? Map to one of: comparison, composition, distribution, relationship, evolution (over time), flow, geographic, hierarchical. See
rules/chart-type-selection.md. - Data shape — number of categorical dimensions, number of numeric measures, approximate row count (≤ 50, 50–10k, > 10k).
- Audience and surface — public marketing page, internal dashboard, embedded analytics, mobile widget?
- Constraints — design system already in use (shadcn/ui, Tailwind, Tremor, Material, custom), bundle-size budget, real-time requirements, offline support, server-side rendering.
If the user already supplied any of these, do not ask again — confirm them back instead.
Phase 2: Select the chart type
Load rules/chart-type-selection.md and use the decision table.
Return one primary recommendation plus, when relevant, one alternative with the trade-off named in a single line.
Never recommend a chart whose intent does not match the user's question.
Phase 3: Select the library
Load rules/library-selection.md and apply the platform-specific decision tables.
Output the recommendation as: <library> — one-line reason — link to docs.
Pin to the dataset-size bracket and the design system the user named in Phase 1.
What ships with it
14 files 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.
- lens.md 2.4 KB
- references/galleries-and-examples.md 8.3 KB
- rules/accessibility.md 6.2 KB
- rules/annotations.md 6.3 KB
- rules/anti-patterns.md 6.5 KB
- rules/chart-type-selection.md 9.4 KB
- rules/formatting-and-i18n.md 6.2 KB
- rules/interactivity-and-gestures.md 8.5 KB
- rules/library-selection.md 7.9 KB
- rules/maps-and-geo.md 7.8 KB
- rules/performance.md 7.4 KB
- rules/server-rendering.md 6.8 KB
- rules/state-filters-and-testing.md 8.8 KB
- rules/theming.md 5.7 KB
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.
- 1mo ago First seen · 207 lines · 158 tokens per session scan A 505a8d623ca4
charting is a skill published in the GitHub repository mthines/agent-skills (19 stars, last pushed today), licensed MIT. It adds 158 tokens to every session and 2,982 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
skill-body
Call help() or help("page.click") to print signatures and uncommon options of APIs named below; it prints by itself, so do not wrap it in console.log. For installation or connection problems, read references/install.md in the ego-browser Skill directory.
ego-browser
When you need a browser, read this Skill by default. Use it to open and operate websites, fill forms, click buttons, take screenshots, extract page data, sign in, and perform other browser automation tasks, as well as web app testing, dogfooding, QA, bug investigation, and app-quality review. ego-browser (ego-lite) is…
ego-lite-simplify
Find and implement evidence-backed simplifications in the ego-lite repository. Use when reviewing the codebase for dead code, duplicated state or APIs, speculative abstractions, unnecessary compatibility layers, hand-written infrastructure, excessive tests or documentation, or when the user asks to reduce code size or…
temporal-developer
Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, Ruby, and Rust. Use when the user is building workflows, activities, workers, or background job queues with a Temporal SDK, debugging issues like non-determinism errors, stuck workflows, or activity retries, using Temporal CLI…
custom-icons
Create or refine custom icon assets as native or traced SVGs and transparent PNG/WebP files. Use when the user asks for a bespoke icon or cohesive icon set, wants an image traced into a clean vector, or needs a detailed or 3D icon with transparency.
geekx-gate
A review framework for deciding whether an engineering idea or technical commitment is necessary, too broad, or premature. It examines the real problem, complexity, evidence, non-goals, and ease of reversal.