Artifacts
Artifact builder
Create validated charts, tables, and custom visuals with a clear source basis and runtime fit.
What this skill teaches
The artifact runtime matches the requested interaction and data shape.
Every complex artifact passes Prism validation before it is saved.
Saved artifacts include a concise description of what they show, their source basis, and why they matter.
Workflow
- 1
Inspect visualization capabilities when the correct Prism runtime is unclear.
- 2
Use prepare_chart_table_artifact for raw delimited text, Markdown tables, or JSON rows. Use plan_visualization_artifact for richer custom output.
- 3
For live market visuals, list supported metrics and resolve bindings before generating the artifact.
- 4
Render and inspect React or HTML output in the agent's own environment when possible, then validate the exact artifact payload.
- 5
Save with create_artifact to a Project or article draft, and insert it at a stable draft marker when placement matters.
Tool routing
Choose a native, React, or HTML runtime before generating the final payload.
Normalize raw row or table data into a Prism chart or table spec.
Use supported server-hydrated bindings for live market data.
Validate first, then save the final inspected artifact.
Safety boundaries
- Prism does not run Python as a live browser runtime. Convert isolated Python output into a supported finished artifact.
- HTML must remain self-contained and local-only, with no external scripts, styles, images, fetches, forms, iframes, workers, storage, or navigation APIs.
- Do not claim Prism rendered a preview through MCP. Report only previews the agent actually inspected.
SKILL.md source
Public Markdown you can inspect, copy, download, or adapt.
---
name: prism-artifact-builder
description: "Use when an AI client needs to plan, validate, and save Prism charts, tables, metric cards, Markdown, React, or self-contained HTML artifacts."
---
# Artifact builder
Create validated charts, tables, and custom visuals with a clear source basis and runtime fit.
## Before you start
Copy this guidance into ChatGPT, Claude, Codex, Grok, or another client that accepts custom instructions. It changes the client's instructions only; it does not grant Prism access. Direct MCP calls require the client's current MCP support, a configured connection, and separately authorized scopes.
Scopes this workflow may need:
- `knowledge:read`
- `library:write`
- `drafts:write`
The installed skill does not grant these permissions. Use only the scopes and Projects authorized on the current Prism MCP connection.
## Workflow
1. Inspect visualization capabilities when the correct Prism runtime is unclear.
2. Use prepare_chart_table_artifact for raw delimited text, Markdown tables, or JSON rows. Use plan_visualization_artifact for richer custom output.
3. For live market visuals, list supported metrics and resolve bindings before generating the artifact.
4. Render and inspect React or HTML output in the agent's own environment when possible, then validate the exact artifact payload.
5. Save with create_artifact to a Project or article draft, and insert it at a stable draft marker when placement matters.
## Tool routing
- `get_visualization_artifact_capabilities`, `plan_visualization_artifact`: Choose a native, React, or HTML runtime before generating the final payload.
- `prepare_chart_table_artifact`: Normalize raw row or table data into a Prism chart or table spec.
- `list_market_data_metrics`, `resolve_market_data_bindings`: Use supported server-hydrated bindings for live market data.
- `validate_visualization_artifact`, `create_artifact`: Validate first, then save the final inspected artifact.
## Expected result
- The artifact runtime matches the requested interaction and data shape.
- Every complex artifact passes Prism validation before it is saved.
- Saved artifacts include a concise description of what they show, their source basis, and why they matter.
## Boundaries
- A skill does not grant Prism access. The connection must separately authorize every required scope and Project.
- Call only tools verified callable by the current AI host. Use discover_prism_actions for granular actions. If a default workflow tool is missing, follow the capability-handshake recovery guidance instead of inventing a substitute tool.
- Read before writing. Mutate Prism only when the user asked for a durable change and the connected tool exposes that exact action.
- Keep retrieved evidence separate from analysis. Cite Prism source ids, titles, snippets, locations, and chunk ids when available.
- Prism does not run Python as a live browser runtime. Convert isolated Python output into a supported finished artifact.
- HTML must remain self-contained and local-only, with no external scripts, styles, images, fetches, forms, iframes, workers, storage, or navigation APIs.
- Do not claim Prism rendered a preview through MCP. Report only previews the agent actually inspected.