Seshat-BI: Skill for Claude Code

.claude/skills/retail-discover-portfolio/SKILL.md

retail-discover-portfolio is a skill for Claude Code from Kemetra/Seshat-BI. It costs 86 tokens per session (1,371 once invoked), scanned A, original, Apache-2.0.

A guided discovery process for an unfamiliar retail database schema or folder of files. It surveys available tables, helps define the business area and first delivery, then profiles selected tables for later discussion.

In plain words
What is it for?
Use it to inventory a retail data portfolio, choose an initial set of tables, gather value-backed table profiles, and prepare for a business interview.
Why use it?
It gives you an evidence-based starting point before you decide which retail data to onboard. It avoids duplicating the existing per-table profiling process or making premature scale decisions.

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/retail-discover-portfolio/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 retail-discover-portfolio

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kemetra/seshat-bi/retail-discover-portfolio"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/retail-discover-portfolio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,371 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 $0.00086 $0.01371
Opus 5 $0.00043 $0.00685
Sonnet 5 $0.00017 $0.00274
Haiku 4.5 $0.00009 $0.00137

Measured 12d ago against content hash 065d3d002ace, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

retail-discover-portfolio 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 12d 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/retail-discover-portfolio/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

retail-discover-portfolio

Use this skill when the owner has an unfamiliar database schema or file folder and needs a governed route from portfolio discovery to the business interview.

Boundary

This is an agent-conducted flow, not a new state engine or CLI workflow:

portfolio discovery -> domain -> scope -> selected-table onboarding -> interview handoff -> STOP

  • Layer A is the metadata-only portfolio survey in templates/portfolio-survey.md.
  • Layer B is the existing value-backed, per-table Source Ready profile owned by retail-onboard-table.
  • Never create a second profiler or author mappings//source-profile.md here.
  • Never select a scale-out route. Record scale evidence for the existing silver_gold_model_planning boundary to decide later.
  • Read the existing stage contracts and committed artifacts to derive exactly one next action. Create no run-state, projection, or routing file.

The golden reference shapes are:

  • tests/fixtures/portfolio-survey/db-schema/survey.md
  • tests/fixtures/portfolio-survey/file-folder/survey.md

1. Produce the Layer-A survey

For a database schema:

  1. Call seshat.portfolio_enumerate.enumerate_tables(schema). This helper is the only DB table-enumeration path. Do not issue a raw information_schema.tables query, and do not catch raw config, driver, or connection exceptions.
  2. If it returns an error, show only that redacted error. If no metadata is readable, STOP and name the unblock: configure the gitignored .env, install the matching retail DB extra, or grant metadata permission.
  3. For every returned table, read information_schema.columns plus declared PK/FK and catalog-estimate metadata through the same read-only boundary.

For a file folder, list every reachable CSV and Excel file and inspect only format/schema metadata. Do not read source values.

Fill one committed survey from templates/portfolio-survey.md:

  • include every reachable table; never choose a table-count or time cap;
  • include declared types, declared PK/FK metadata, catalog row estimates, and name/type-based date, PII-suspicion, grain, and structural-role hints;
  • label every inference candidate/hint, never a ruling;
  • for unavailable metadata, record [PENDING LIVE PROFILE] or needs_sample, the exact reason, and the enabling step;
  • never measure uniqueness, missingness, date spans, or returns population;
  • never include raw or masked samples, suspected-PII values, credentials, DSNs, or connection strings.

Read the full file on GitHub · 142 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. 12d ago First seen · 142 lines · 86 tokens per session scan A 065d3d002ace

Subscribe to this mod's changes

retail-discover-portfolio is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,371 once invoked, about $0.0004 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.