本文へ移動
cccskills
無料GitHub で公開

data-charts-tako

Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more

gooseworks-ai/goose-skills
インストール方法を見る

含まれるファイル（2）

  • SKILL.md9.3 KB
  • skill.meta.json279 B

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Tako Knowledge Search & Visualization

Setup

Read your credentials from ~/.gooseworks/credentials.json:

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login

All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"

Search for data with natural language and get interactive charts, AI-generated insights, and embeddable knowledge cards. Covers finance, economics, demographics, sports, politics, climate, and health from sources like S&P Global, World Bank, and more.

When to Use

  • User asks a data question ("What's NVIDIA's revenue?", "US GDP growth?")
  • User wants to compare metrics ("Tesla vs Ford market cap")
  • User needs a chart or visualization for a report
  • User wants to turn their own data into a chart
  • User asks for insights or analysis on a data trend

Usage

Search for Data

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/knowledge_search","body":{"inputs":{"text":"NVIDIA vs AMD revenue since 2018"}}}'

With search effort and source options:

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/knowledge_search","body":{"inputs":{"text":"US inflation rate 2020-2025","search_effort":"deep"},"source_indexes":["tako","web"]}}'

With dark mode chart images:

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/knowledge_search","body":{"inputs":{"text":"Bitcoin price history"},"output_settings":{"knowledge_card_settings":{"image_dark_mode":true}}}}'

Get Chart Insights

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/beta/chart_insights","query":{"card_id":"sXQPVnixcDUf2Iw35Via"}}'

Visualize Your Own Data

Provide data as CSV strings. Tako picks the best chart type automatically.

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/beta/visualize"}'
Q1 2024,100
Q2 2024,150
Q3 2024,220
Q4 2024,310"], "query": "Show quarterly revenue as a bar chart"}'

Request a specific chart type:

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/beta/visualize"}'
US,500
EU,300
Asia,250"], "query": "Sales by region", "viz_component_type": "pie"}'

Create a Custom Chart

Build charts from scratch with full control over components and layout.

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/thin_viz/create/","body":{"components":[{"component_type":"header","config":{"title":"Sales by Region"}},{"component_type":"categorical_bar","config":{"datasets":[{"label":"Revenue (M)","data":[{"x":"US","y":500},{"x":"EU","y":300},{"x":"Asia","y":250}]}]}}],"title":"Sales by Region","source":"Internal Data"}}'

List Available Chart Types

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/thin_viz/default_schema/"}'

Get Tako Tool Descriptions

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/tako_tools_description"}'

Parameters

Knowledge Search (POST /v1/knowledge_search)

Body:

  • inputs.text (string, required) - Natural language query (e.g. "Tesla vs Ford market cap")
  • inputs.search_effort (string) - "fast", "medium", "deep", or "auto"
  • source_indexes (array) - Priority order: "tako", "web", "tako_deep_v2". Default: ["tako"]
  • country_code (string) - ISO 3166-1 alpha-2 (e.g. "US", "GB"). Default: "US"
  • locale (string) - e.g. "en-US", "de-DE". Default: "en-US"
  • output_settings (object) - {"knowledge_card_settings": {"image_dark_mode": true}} for dark mode

Chart Insights (GET /v1/beta/chart_insights)

  • card_id (string, required) - Card ID from Knowledge Search or Create Card response

Visualize Datasets (POST /v1/beta/visualize)

Body:

  • csv (array of strings, required) - CSV data with headers in first row. Example: ["name,value Apple,3.7 NVIDIA,3.4"]
  • query (string) - How to visualize (e.g. "Show as a bar chart")
  • viz_component_type (string) - Force chart type: bar, grouped_bar, stacked_bar, timeseries, pie, choropleth, scatter, boxplot, heatmap, waterfall, histogram, table, treemap

Create Card (POST /v1/thin_viz/create/)

Body:

  • components (array, required) - Each needs component_type (header, categorical_bar, pie, scatter, table, choropleth, heatmap, histogram, boxplot, treemap, waterfall, bubble, etc.) and config (type-specific data)
  • title (string) - Card title
  • description (string) - Card description
  • source (string) - Data source attribution for footer

List Default Schemas (GET /v1/thin_viz/default_schema/)

No parameters.

Tool Descriptions (GET /v1/tako_tools_description)

  • index_ids (string) - Comma-separated index IDs to filter

Response

Knowledge Search — data.outputs.knowledge_cards[]

  • card_id - Unique ID (use for Chart Insights or embed URLs)
  • title - Chart title
  • description - Text description of the data and trends
  • card_type - "chart", "table", "company", or "text"
  • webpage_url - Interactive card page on Tako
  • image_url - Static chart image (embed in messages, reports)
  • embed_url - Embeddable iframe URL
  • relevance - "High", "Medium", or "Low"
  • sources - Data sources with name and description
  • visualization_data - Raw chart data points

Chart Insights — data

  • insights - Array of AI-generated observations
  • description - Chart description

Create Card — data

  • card_id, title, webpage_url, image_url, embed_url

Examples

# What's the US unemployment rate?
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/knowledge_search","body":{"inputs":{"text":"US unemployment rate"}}}'

# Compare company revenues
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/knowledge_search","body":{"inputs":{"text":"Apple vs Microsoft vs Google revenue","search_effort":"deep"}}}'

# Get insights on a chart
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/beta/chart_insights","query":{"card_id":"sXQPVnixcDUf2Iw35Via"}}'

# Visualize your own CSV data
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/beta/visualize"}'
North America,500
Europe,300
Asia,250
LatAm,100"], "query": "Show sales by region"}'

# Create a custom bar chart
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"tako","path":"/v1/thin_viz/create/","body":{"components":[{"component_type":"categorical_bar","config":{"datasets":[{"label":"Revenue","data":[{"x":"Q1","y":100},{"x":"Q2","y":200}]}]}}],"title":"Quarterly Revenue"}}'

Tips

  • Knowledge Search is the main endpoint — start here for any data question
  • Use image_url to display charts in Slack, Discord, or other channels
  • embed_url gives an interactive iframe for web pages
  • Call List Default Schemas before Create Card to see available chart types
  • Set search_effort: "deep" for complex multi-metric comparisons
  • Data coverage: stock prices, revenue, GDP, unemployment, population, sports stats, weather, health, and more

Error Handling

  • 400 - Invalid body or missing required fields
  • 401 - Invalid API key
  • 404 - Card not found (Chart Insights) or no results found (Knowledge Search)
  • Empty knowledge_cards array — try rephrasing or using source_indexes: ["tako", "web"]

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

ログインしてレビューを書く

同じリポジトリのスキル

概要と使いどころ

ad-angle-miner

無料

Research supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

ad-campaign-analyzer

無料

Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

ad-lead-quality-analyzer

無料

For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

ad-management-intake

無料

The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

ad-to-landing-page-auditor

無料

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

ads-north-star-strategy

無料

Turn a brand's facts, a campaign brief and the product into a one-minute Meta ad strategy with its reasoning — goal, audience, objective and placements, budget split, how many ads and how different they must be (generate 3x so the user can choose), the test frame, the success metric, and safety rules for the user to accept. Decides what launch-meta-ad-campaign then executes, and re-reads the strategy after a deep check to show which assumption changed. Use it after intake and before any creative is generated or any campaign is built.

日本語の概要は準備中です。原文の説明を表示しています。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

gooseworks-ai のスキルをすべて見る

このスキルの問題を報告する