Seshat-BI: Skill for Claude Code

.claude/skills/dashboard-design/SKILL.md

dashboard-design is a skill for Claude Code from Kemetra/Seshat-BI. It costs 177 tokens per session (4,194 once invoked), scanned A, original, Apache-2.0.

A gated dashboard-planning tool for Power BI, Microsoft's reporting software. It creates a page layout, list of visuals, and links from each visual to an approved metric definition and ready semantic model.

In plain words
What is it for?
Use it to plan Power BI report pages and show which approved metrics each chart, table, or other visual uses.
Why use it?
It prevents report designs from being based on unapproved or undefined measures.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Kemetra/Seshat-BI's own configuration. It tells Claude Code how to work on Seshat-BI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Seshat-BI configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Kemetra/Seshat-BI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Kemetra/Seshat-BI/main/.claude/skills/dashboard-design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Kemetra/Seshat-BI

Made for: Claude Code.

Wrote 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.

agentmods badge for dashboard-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/kemetra/seshat-bi/dashboard-design/github.svg)](https://agentmods.dev/skills/kemetra/seshat-bi/dashboard-design)
Your own site
<a href="https://agentmods.dev/skills/kemetra/seshat-bi/dashboard-design"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/dashboard-design/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.

agentmods 80×15 button for dashboard-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/kemetra/seshat-bi/dashboard-design"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/dashboard-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 177 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,194 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00177 $0.04194
Opus 5 $0.00088 $0.02097
Sonnet 5 $0.00035 $0.00839
Haiku 4.5 $0.00018 $0.00419

Measured 10d ago against content hash 54816482c6ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dashboard-design 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 10d 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.

.claude/skills/dashboard-design/SKILL.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dashboard-design

Stage 6 of the Tower BI Readiness System, Dashboard Ready (docs/readiness/dashboard-ready.md): a report is designed AGAINST approved metric contracts -- never before them. This skill is the agent VERB that runs that stage. It reads the approved metric contracts (F009) and the governed PBIP model (F010), then authors a layout plan, a visual list, and a visual->contract binding map so every visual traces to a contract that already exists and is approved. It is the agent expression of roadmap hard rule 5 ("no dashboard design before metric contracts") and hard rule 6 ("no Power BI execution before semantic-model readiness").

This verb is the gated, contract-binding design step that the broader powerbi-dashboard-design router (F011A, the visual-design FOUNDATION) hands the "design a dashboard from approved contracts" intent to. The router carries the design vocabulary (four surfaces, tokens, theme, blueprints, QA); this verb enforces the gate and produces the binding map a human signs off.

Scope boundary (read first)

This skill AUTHORS design guidance and STOPS. Authoring is in-scope: a layout plan, a visual list, a visual->contract binding map, and (optionally) a blank PBIR scaffold a human fills -- no side effects, no DB/Desktop connection, the same category as source-mapping authoring mappings/ and retail-build-warehouse authoring warehouse/migrations/*.sql. EXECUTING the design -- generating the PBIR report, publishing to a workspace, calling the Power BI execution adapter (official Power BI MCP / connection; pbi-cli no longer preferred) -- is the deferred, execution-only F016 adapter seam and is OUT of scope here. The skill authors, runs static seshat check on any committed report text, and STOPS.

Hard gate (rule 5) -- verify BEFORE authoring anything

Before authoring ANY design, read the subject area's readiness status and verify semantic_model_ready: pass. "Pass" means BOTH:

Read the full file on GitHub · 304 lines

Changes

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.

  1. 10d ago First seen · 304 lines · 177 tokens per session scan A 54816482c6ce

Subscribe to this mod's changes

dashboard-design is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 177 tokens to every session and 4,194 once invoked, about $0.0009 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 2026-08-31.

Related

Other skills, from other repositories

powerbi-modifying-theme-json

Design, enforce, audit, and validate Power BI report themes. This skill MUST be invoked when a report uses the default or built-in theme, has a minimal custom theme (few or no visualStyles), or has accumulated many visual-level formatting overrides (objects/visualContainerObjects in visual.json); these are signs the…

santoshkanthety/powerbi-agent · 180 tokens

powerbi-report-design

Power BI report design principles, layout guidance, and formatting best practices. Automatically invoke when the user asks about "report layout", "design best practices", "visual hierarchy", "3-30-300 rule", "KPI card design", "page layout", "accessibility in reports", "visual spacing", "report canvas", "card design…

santoshkanthety/powerbi-agent · 90 tokens

powerbi-svg-visuals

SVG generation via DAX measures and extension measures with ImageUrl data category for inline visualizations in PBIR reports. Automatically invoke when the user mentions "SVG visual", "DAX sparkline", "SVG measure", "inline graphics with DAX", "ImageUrl data category", "extension measure", or asks to create any…

santoshkanthety/powerbi-agent · 126 tokens

powerbi-report-theming

Power BI report theming via pbir.tools - color palettes, typography, text classes, theme templates, visual formatting, icons, background images, and conditional formatting rules. Use when the user mentions: theme, theming, color palette, brand colors, fonts, typography, text class, formatting, conditional formatting…

santoshkanthety/powerbi-agent · 93 tokens

powerbi-custom-visuals

Build, package, and embed Power BI custom visuals (.pbiviz) into PBIR reports via the powerbi-visuals SDK. Automatically invoke when the user asks to "create a custom visual", "vibe-code a visual", "build a pbiviz", "scaffold a custom visual project", "import a custom visual into the report", "iterate on visual.ts"…

santoshkanthety/powerbi-agent · 113 tokens

powerbi-report-authoring

General report authoring patterns. Use when the user mentions: report, page, visual, chart, bar chart, line chart, matrix, table, slicer, filter, bookmark, tooltip, drill-through, navigation, layout, canvas, report design, visual formatting, conditional formatting, KPI, card, decomposition tree.

santoshkanthety/powerbi-agent · 70 tokens