This page documents the legacy-compatible skills_index.json contract used by custom host integrations and lazy loaders.
For Codex and Claude Code, use AAS Core instead of wiring a host directly to this repository manifest. Core exposes every skill in a verified local catalog through bounded, read-only MCP tools for search, inspection, and agent-owned composition. The raw manifest remains useful for integrations that do not have an AAS Core host adapter.
skills_index.json at repository root.data/skills_index.json must be an exact compatibility mirror of skills_index.json.schemas/skills-index.v1.schema.jsonEach manifest entry includes:
id – skill identifier (same as @skill-id).path – relative skill folder, e.g. skills/brainstorming.category – grouping used by UI/search surfaces.name – display name.description – short purpose/trigger summary.risk – one of repo risk labels.source – source of authority/trust metadata.date_added – ISO date string or null.Additional fields are allowed, and plugin metadata is optional.
Stable integrations must not load every skill instruction file up front.
skills_index.json).@skill-id values from the conversation.SKILL.md lazily.SKILLS_ROOT.This is the main prevention for context truncation and trajectory conversion errors in custom multi-skill hosts. It is not the AAS Core catalog or stack lifecycle contract.
data/ mirror existsdata/skills_index.json remains for downstream compatibility where clients still read from the data/ subtree. The stable contract is that both files contain the same payload.
{
"id": "brainstorming",
"path": "skills/brainstorming",
"category": "planning",
"name": "brainstorming",
"description": "Use before any creative or constructive work.",
"risk": "safe",
"source": "official",
"date_added": "2026-02-27"
}