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 richardhe-fundamenta/practical-gcp-examples --skill analyst-chart-tablegit clone --depth 1 https://github.com/richardhe-fundamenta/practical-gcp-examplesWrote 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/richardhe-fundamenta/practical-gcp-examples/analyst-chart-table)<a href="https://agentmods.dev/skills/richardhe-fundamenta/practical-gcp-examples/analyst-chart-table"><img src="https://agentmods.dev/badge/skills/richardhe-fundamenta/practical-gcp-examples/analyst-chart-table/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/richardhe-fundamenta/practical-gcp-examples/analyst-chart-table"><img src="https://agentmods.dev/badge/skills/richardhe-fundamenta/practical-gcp-examples/analyst-chart-table.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 86 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00116 | $0.00978 |
| Opus 5 | $0.00058 | $0.00489 |
| Sonnet 5 | $0.00023 | $0.00196 |
| Haiku 4.5 | $0.00012 | $0.00098 |
Grade A, and why
analyst-chart-table scanned grade A with 1 finding 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- No `import subprocess`, `import os.system`, network calls, or file writes How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyst chart + table
This skill turns a small set of already-validated aggregates into a single secure visual: one chart with the finding stated in the title, and a compact table of the exact numbers beneath it.
Inputs you receive
- A JSON object of aggregated rows (small — already reduced by SQL upstream).
- The business question being answered.
- Optionally: a target/prior-period value for delta context.
Do not query data here. Data arrives pre-aggregated and pre-validated from the harness. Your job is interpretation + rendering only.
Procedure
- Pick the chart type from the question shape:
- trend over time -> line
- comparison across categories -> bars
- if neither fits cleanly, default to bars and say so in the title.
- Derive the headline finding — the single most decision-relevant fact (biggest mover, threshold crossed, outlier segment). This becomes the title, phrased as a conclusion ("APAC churn doubled in Q1"), never a label ("Churn by region").
- Show change, not just level — annotate the delta vs prior period or a reference line. Analysts think in deltas.
- Generate Python rendering code (see Execution). Pass data as JSON; never build markup by string-concatenating data values.
- Attach the compact table of exact numbers beneath the chart.
- Write one plain-English "so what" line.
Execution
You (the model) generate Python rendering code; the harness runs it in an
isolated sandbox (no network, no credentials) via the render_chart tool.
Data source: The harness writes the rows from the most recent successful
validated query to data.json in the working directory, as:
{ "rows": [ { "col": value, ... }, ... ] }
rows is a list of record dicts straight from BigQuery — these are the ONLY data
you may chart. Your code reads data.json, shapes/aggregates rows (e.g. pivot a
month/category/value layout into series), and renders. Never hardcode values and
never invent labels or numbers not present in rows; you cannot pass data yourself,
which guarantees the chart reflects real queried data.
What ships with it
4 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.
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.
- 9d ago First seen · 89 lines · 116 tokens per session scan A 155336b0fe42
analyst-chart-table is a skill published in the GitHub repository richardhe-fundamenta/practical-gcp-examples (57 stars, last pushed 23d ago), licensed MIT. It adds 116 tokens to every session and 978 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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…