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 create-chartgit 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/create-chart)<a href="https://agentmods.dev/skills/amplitude/mcp-marketplace/create-chart"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/create-chart/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/create-chart"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/create-chart.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 | $0.00043 | $0.02597 |
| Opus 5 | $0.00022 | $0.01299 |
| Sonnet 5 | $0.00009 | $0.00519 |
| Haiku 4.5 | $0.00004 | $0.00260 |
Grade A, and why
create-chart 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 4d 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Amplitude Chart
Create charts from natural language by discovering events, building chart definitions, and verifying results.
Planning First (Critical)
Before any tool calls, decompose the request:
1. Identify chart components:
- Chart type and metric (what's being measured)
- Time range (default: Last 30 Days if not specified)
- Primary event (the action being counted)
- Segment conditions (user filters/groups)
- Filters, groupings, breakdowns
- Funnel steps (if conversion analysis)
2. Plan event searches:
- ONE search per distinct event concept
- Never combine multiple concepts in one search
- Example: "purchase" and "signup" need separate searches
3. Plan parallel tool calls:
- Get context, search events, find cohorts can run together
- Wait for results before building definition
Event Discovery (Critical: Discovery First)
IMPORTANT: Cast a wide net before narrowing down
When the user's request is ambiguous or could map to multiple events:
- Search BROADLY first to discover relevant options
- Review relevant results - look for related events, custom events, meta events
- Present options to user OR explain your selection rationale
- Try not to assume a single event is the only answer without exploration
Search for events:
Amplitude:search with entity_types=['EVENT', 'CUSTOM_EVENT']
- Search ONE concept at a time
- Use broad search terms first (e.g., "AI" not just "AI chat")
- ✓ Good: "user completes purchase"
- ✗ Bad: "signup or purchase events"
Make informed decisions, then explain:
- Search broadly to discover all options
- Review results and identify the most comprehensive/accurate approach
- Make your best judgment call (prefer aggregated custom events over single events)
- Always explain: "I found X, Y, Z options. I chose [X] because [reason]. This includes/excludes [scope]."
- User can correct if your assumption was wrong
Decision criteria:
- Prefer custom events that aggregate related activity (e.g., "[2026] Activation Metric [AI events only]")
- If no aggregated event exists, choose the primary interaction event
- Consider what "active user" typically means for that product area
- Default to broader scope unless user specifies narrow focus
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.
- 4d ago Changed · -1 lines 9f34f2c51c74
- 9d ago First seen · 320 lines · 43 tokens per session scan A 811876822366
create-chart is a skill published in the GitHub repository amplitude/mcp-marketplace (35 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 2,597 once invoked, about $0.0002 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…