A Claude SQL skills generator built from promoted Postgres queries

One agent file per role, exported to Claude Code and Codex

Each CHION.md is one role’s worth of saved SQL: finance, ops, growth. One role compiles per export, and the files you keep become your team’s SQL knowledge base. Same database, scoped knowledge per role. Each file is the agent that role owns, routing to the queries your team saved and reviewed; the library compounds as your team works.

Chion's SQL Skills Generator creates a CHION.md file: your portable Postgres SQL skills library. It auto-generates a SQL Analytics Agent file (the .md suffix follows the CLAUDE.md / AGENTS.md / SKILL.md convention). The bundle ships CHION.md, CONNECT.md, and a skills/ folder holding one SKILL.md per role. CHION.md holds the seven Layer 1 rules in full; each SKILL.md inlines them as a seven-line quick reference. Rename CHION.md to CLAUDE.md or AGENTS.md if that is what your agent reads.

CHION.md is a SQL Analytics Agent file for your database: a portable, version-controlled instruction file an AI reads before doing any work. The difference vs. hand-written agent files: yours is auto-written from your real analytics conversations, fully editable, and re-exportable on every refresh. Every saved query teaches it; every PII column closes off; every business rule is cited back to the row that proved it.

The export ships as one folder you point your agent at: CHION.md at the root + a skills/ folder beneath it (an _INDEX.md catalog that groups roles by department, then one folder per role holding its SKILL.md and saved scripts/). Sister-paired roles within each department cover complementary axes (recognized vs. forecast, between-warehouse vs. inside-warehouse, acquisition vs. in-product) so cross-axis questions resolve without the agent inventing a join.

One compile per role, in three model passes. The slot-filling pass runs at temperature 0, so the same evidence produces the same file structure.

A real Northwind Logistics agent file. Each Layer 2 evidence line cites [src=…] back to the row that proved it; anything the compiler could not source is emitted marked _inferred, flag for review_.

Key facts. Frontmatter contract: 11 fields. Framework version: 7. Layer 2: 11–13 density-gated slots, each evidence line [src=…]-cited to its source row. Three model passes per role, with the slot-filling pass at temperature 0. Fully editable; export as CHION.md / CLAUDE.md / AGENTS.md / SKILL.md.

---
artifact_type: domain_sql_sme_prompt
artifact_version: 2.5.0
framework_version: 7
archetype: logistics_supply_chain
chosen_primitives: [pre_aggregate_grain, snapshot_latest,
                    ratio_reconstruction, period_over_period_lag]
refreshed_at: 2026-04-30T18:22:11Z
---

# Analyst Persona
You are Northwind Logistics' supply-chain analyst. Your day is
shipments, lanes, carriers, and SLA breaches. You reason in
on-time-delivery rates and cost-per-mile. You refuse avg_of_ratios;
you reconstruct ratios from numerator + denominator at lane-grain.

# Curated SQL Rule Pack
### snapshot_latest
  use-when: balance-style metrics (inventory_on_hand)
  sql-shape: SELECT … ORDER BY ts DESC LIMIT 1 per entity
  guards: never SUM across snapshots

### ratio_reconstruction
  use-when: on_time_rate, fill_rate, defect_rate
  guards: SUM(numerator) / NULLIF(SUM(denominator),0)

# Layer 2 — Domain Profile
## 2.1 Questions You Compute
- on_time_rate = SUM(delivered_on_time) / NULLIF(SUM(shipments),0)
  [src=column_profiles:shipments.delivered_on_time, kpi_metrics:otd]
- avg_cost_per_mile = SUM(total_cost) / NULLIF(SUM(miles),0)
  [src=metric_concepts:cpm_lane]

## 2.6 Stop Signals
- never SUM(inventory_on_hand) across days
  [src=donts:snapshot_sum, decision_record:wh_audit_2026q1]
- never AVG(rates) — reconstruct from numerator + denominator
  [src=donts:avg_of_ratios, decision_record:metric_audit_2026q1]

Department is the top-level axis; role is the brain. Each department contains two sister-paired roles: finance (finance-analyst ↔ fp-and-a-analyst), operations (ops-supply-chain ↔ warehouse-operations), growth (growth-marketing ↔ product-analytics). Saved queries land under the role that owns the data shape; cross-axis questions route to both sister roles.

Each role's scripts/ folder mirrors every saved query under that role as a {README.md, query.sql} pair the agent wraps as a CTE rather than rewriting. For how Claude Code discovers and loads one of these files, read how to build a Claude Code SQL skill. The tree below shows the layout after activation. The export arrives with skills/ un-dotted; one move or symlink puts it under .claude/skills/ where Claude Code looks.

chion-skills-workspace/
├── CHION.md                                      ← root agent file (canonical)
├── README.md
├── LICENSE
└── .claude/skills/
    ├── _INDEX.md                                 ← workspace catalog · vocabulary · routing
    │
    ├── finance/                                  ← department · 2 sister-paired roles
    │   ├── _INDEX.md                             ← department catalog · sister-pair logic
    │   ├── finance-analyst/                      ← recognized revenue · ARR/MRR · margin
    │   │   ├── SKILL.md                          ← role brain · rule pack · scripts index
    │   │   └── scripts/
    │   │       ├── arr-by-segment/{README.md, query.sql}
    │   │       ├── mrr-trend-12mo/{README.md, query.sql}
    │   │       └── …
    │   └── fp-and-a-analyst/                     ← forecast · variance · runway · burn
    │       ├── SKILL.md
    │       └── scripts/…
    │
    ├── operations/                               (between-warehouse + inside-warehouse)
    │   ├── _INDEX.md
    │   ├── ops-supply-chain/{SKILL.md, scripts/}
    │   └── warehouse-operations/{SKILL.md, scripts/}
    │
    └── growth/                                   (acquisition + in-product)
        ├── _INDEX.md
        ├── growth-marketing/{SKILL.md, scripts/}
        └── product-analytics/{SKILL.md, scripts/}

A typical SKILL.md frontmatter: name + description drive native AI-tool skill discovery; trigger-keywords + department/role drive the CHION.md cascade:

---
name: finance-analyst
description: |
  The default analyst role for the finance department.
  Owns recognized-revenue P&L, segment-margin reconstruction,
  ARR/MRR roll-ups, and renewal recognition.
must-read: [_INDEX.md, ../_INDEX.md]
trigger-keywords: [revenue, recognized revenue, ARR, MRR,
                   GAAP, gross margin, segment margin, renewal]
department: finance
role: finance-analyst
archetype: saas_finance
chosen_primitives: [pre_aggregate_grain,
                    period_over_period_lag,
                    ratio_reconstruction]
status: verified
---

Bottom of every SKILL.md carries a fixed Scripts Index: trigger phrases mapped to saved scripts/ folders. No LLM judgment between trigger match and SQL execution.

Promoted queries  →  3 model passes per role  →  one role per export today

Six role archetypes in the compiler:
                 ┌─ finance-analyst, fp-and-a-analyst
                 ├─ ops-supply-chain, warehouse-operations
                 └─ growth-marketing, product-analytics

Max plan economics. ~20 credits per role compile · 750 credits/month on Max → up to ~37 compiles, one role per export today, each carrying 10+ promoted queries. Re-compile any role anytime; supersedes the prior version cleanly.

Indexable, navigable, version-controlled. Diff your agent file across releases the same way you diff code.