# Shell — API Agent Score

> Score: 74/100 (Grade: B) | Domain: shell.com | Rubric: 1.0.0 | Checked: August 20, 2026

Shell scored 74/100 (B), classified "partially-ready".

[View full report](https://www.postman.com/ai/ai-ready-apis/company/shell)
[All organizations](https://www.postman.com/ai/ai-ready-apis/llms.txt)

## Summary

- Overall: 74/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 83/100 (A)
- Developer Experience: 59/100 (D)
- Agent Discovery: 70/100 (B)
- Agent Understanding: 73/100 (B)
- Agent Usability: 85/100 (A)

## Check Results

### API Design

- [warn] Schema coverage & depth — 0/4 (0%) public params are fully typed (no any/**kwargs). Analyzer reports not all methods have a derivable input schema. Investigated: sdk 60%.
- [pass] Security & governance hygiene — Code is formatter-clean with zero linter errors and zero style warnings. Investigated: sdk 100%, wellknown 0%.
- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%, docs 0%.
- [skip] Machine-readable, versioned contract — No surface produced evidence for this capability in this run.
- [skip] Auth declared & discoverable — No surface produced evidence for this capability in this run.

### Developer Experience

- [pass] Quickstart present — Quickstart at https://developer.shell.com/docs/welcome-shell-developer-portal includes a runnable first-call code sample. Investigated: docs 100%.
- [pass] Description completeness — 5/5 operations carry a description. Investigated: sdk 100%.
- [fail] Self-service developer portal — The signup page is sales-gated (contact-sales / request-access language detected), so an agent can't self-serve. Investigated: docs 0%.
- [fail] Code samples in docs — No code samples detected across 3 sampled docs pages, so a coding agent gets no ready-to-use examples. Investigated: docs 0%.
- [skip] Changelog published — No surface produced evidence for this capability in this run.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (moudey/shell, 723 snippets). Investigated: docs 100%, sdk 67%, cli 0%.
- [warn] Docs reachable, not hard auth-gated — Server ignores Accept: text/markdown header (0/1 pages return markdown). Investigated: docs 75%.
- [pass] Crawlable / AEO — robots.txt lets all monitored AI crawlers reach the docs paths. Investigated: wellknown 100%.
- [fail] llms.txt present, valid & comprehensive — No llms.txt found at any candidate location (https://developer.shell.com/llms.txt, https://developer.shell.com/docs/llms.txt). Investigated: docs 0%, sdk 0%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — Single base error "ShellException" with 3 subclasses. Investigated: sdk 100%.
- [warn] Agent-navigable, token-efficient docs — No pages support .md URLs (0/1 tested). Investigated: docs 79%.
- [warn] Operation purpose clarity — Read/write classification is mostly ambiguous: only 0/5 operations classified. Investigated: sdk 50%.
- [warn] Agent instructions file (AGENTS.md) — No agents.md or skill.md context file found (nice-to-have for agent operation). Investigated: sdk 50%, wellknown 0%.
- [fail] Docs structured data — No JSON-LD or OpenGraph/meta tags found across 2 assessed pages (2 JS-rendered), so answer engines have nothing to cite. Investigated: docs 0%.
- [skip] Description consistency across surfaces — Only 1 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [pass] Idempotency documented — Built-in retry machinery is present (grep-derived). Investigated: sdk 100%.
- [warn] Sandbox separation — No test-mode flag or sandbox environment is exposed. Investigated: sdk 50%.
- [pass] Runnable collection with test scripts — README is present and includes a runnable quickstart. Investigated: sdk 100%, platform 0%.
- [skip] Rate-limit signaling — No surface produced evidence for this capability in this run.
- [skip] Pagination documented & consistent — No surface produced evidence for this capability in this run.

## Executive Summary

Shell's API Design and Agent Usability are strong foundations, but two areas are holding back the partner program: partners and their AI agents cannot discover or self-serve the API without a sales conversation, and the documentation surface lacks the machine-readable signals modern answer engines and coding agents depend on. Prioritize opening a self-serve onboarding path with working code examples first, then layer in the discovery and structured-data signals that let agents find and cite your APIs without human intervention.