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 amplitude/mcp-marketplace --skill build-charts-with-typed-paramsgit clone --depth 1 https://github.com/amplitude/mcp-marketplaceWrote 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/amplitude/mcp-marketplace/build-charts-with-typed-params)<a href="https://agentmods.dev/skills/amplitude/mcp-marketplace/build-charts-with-typed-params"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/build-charts-with-typed-params/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/amplitude/mcp-marketplace/build-charts-with-typed-params"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/build-charts-with-typed-params.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 | $0.00079 | $0.03266 |
| Opus 5 | $0.00039 | $0.01633 |
| Sonnet 5 | $0.00016 | $0.00653 |
| Haiku 4.5 | $0.00008 | $0.00327 |
Grade A, and why
build-charts-with-typed-params 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 7d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Charts With Typed Params
Express the chart as typed, UI-shaped parameters and let the server compile it. Do not hand-build raw definition JSON.
Typed chart first
query_amplitude_data takes exactly one of chart or definition.
chart(preferred) — a small model mirroring the chart builder UI. It is compiled server-side by Langley'sCompileChartinto a validated definition, so a successful compile is structurally correct by construction. Compile errors name the offending field and come back with a fix-oriented hint.definition(fallback) — raw definition JSON. Only for chart types the typed model does not cover (composition,revenueLtv) or advanced params with no typed field.
Field names are snake_case; they are validated server-side by Pydantic.
The one thing that goes wrong
The compiler validates structure, not your taxonomy. An event or property name that doesn't exist won't error — it returns a well-formed chart with empty data, which reads like a real answer of "zero".
Resolve names first with the taxonomy search/read capabilities advertised by the connected catalog. Read event, user, or group properties as appropriate and use the exact name and scope returned. Do not invent a property-reader name from server prose or copy parameters from an older schema.
Two workflows
Create: discover names with the current taxonomy capability → build the typed chart → call
query_amplitude_data → render_amplitude_chart with the returned
chartEditId to show it.
Modify or fork a saved chart: search_amp_entities to find the chart id →
get_amplitude_charts with include: 'typed' → edit the returned object →
call query_amplitude_data with that chart and chartId set to the saved
chart id. Passing chartId links the edit to its parent, and the parent's
params fill any gaps the typed model omits. Reading a real chart back as typed
params is also the fastest way to see how this project spells things.
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.
- 7d ago Changed · -4 lines 48a034802229
- 12d ago First seen · 285 lines · 79 tokens per session scan A 9019021ebc1e
build-charts-with-typed-params is a skill published in the GitHub repository amplitude/mcp-marketplace (35 stars, last pushed 4d ago), licensed MIT. It adds 79 tokens to every session and 3,266 once invoked, about $0.0004 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…