NetFabric/intelligentium / .agents/skills/agentic-resource-discovery
agentic-resource-discovery
VerifiedOpen specification (ARD v0.9) for publishing, discovering, and verifying AI capabilities (MCP servers, A2A agents, skills, APIs) across federated networks. USE FOR: creating ai-catalog.json manifests; catalog entry schema; URN identifier format (urn:air:<publisher>:<namespace>:<name>); hosting at /.well-known/ai-catalog.json; DNS discovery (TXT/SRV records); Agentmap robots.txt directive; POST /search API; POST /explore API; GET /agents list API; federation modes (auto, referrals, none); trustManifest with SPIFFE/DID/attestations; representativeQueries for semantic search; building ARD registry clients; querying discovery services at runtime. DO NOT USE FOR: implementing MCP server tools (use MCP docs); implementing A2A agent cards (use A2A spec); OAuth/OIDC authentication.
Agentic Resource Discovery (ARD)
ARD v0.9 (Draft) — federated open specification for cataloging, discovering, and verifying agentic resources. Developed by Microsoft, Google, Hugging Face, and others. Apache 2.0.
Core Concepts
| Term | Definition |
|---|---|
| Catalog | Static ai-catalog.json manifest hosted on a domain |
| Registry | Searchable service that crawls & indexes catalogs |
| Entry | Single capability record within a catalog |
| Federation | Registry-to-Registry routing (auto / referrals / none) |
| trustManifest | Cryptographic identity & compliance metadata per entry |
Publish in 3 Steps
- Create
ai-catalog.jsonwith entries → references/data-model.md - Host at
https://<domain>/.well-known/ai-catalog.json(HTTPS,Content-Type: application/json, CORS*) → references/publishing.md - (Optional) Add DNS
TXT/SRVrecords for alternate paths → references/publishing.md
Catalog Entry — Required Fields
| Field | Type | Rule |
|---|---|---|
identifier | String | urn:air:<publisher>:<namespace>:<name>; <publisher> must be FQDN |
displayName | String | Human-readable label |
type | String | IANA media type (see table below) |
url or data | String / Object | Exactly one; mutually exclusive |
Common type Values
| Type | Resource |
|---|---|
application/mcp-server-card+json | MCP server |
application/a2a-agent-card+json | A2A agent |
application/ai-skill+md | Copilot skill |
application/ai-catalog+json | Nested / linked catalog |
application/ai-registry+json | Dynamic registry search endpoint |
ARD API at a Glance
| Endpoint | Required | Use |
|---|---|---|
POST /search | Yes | Semantic search; returns ranked entries + optional referrals |
POST /explore | No | Faceted aggregation (counts by type, publisher, …) |
GET /agents | No | Deterministic paginated listing with filter/orderBy |
Full schemas → references/api.md
Federation Modes (federation field in POST /search)
| Mode | Behavior |
|---|---|
auto | Registry merges upstream results transparently |
referrals | Returns local results + referral registry entries for client-directed follow-up |
none | Scoped to queried registry only |
Reference Files
| File | Load When |
|---|---|
| references/data-model.md | Full catalog schema, URN format, optional fields, nested catalog examples |
| references/api.md | Search / Explore / List request & response JSON schemas |
| references/publishing.md | Hosting, DNS TXT/SRV, Agentmap, robots.txt, HTML link tag |
| references/trust.md | trustManifest object, SPIFFE, DID, attestations, provenance, signatures |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 197k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |