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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.7 KB |
| references/api.md | markdown | 4.4 KB |
| references/data-model.md | markdown | 4.7 KB |
| references/publishing.md | markdown | 2.7 KB |
| references/trust.md | markdown | 3.3 KB |
references/publishing.md
View on GitHub# Publishing
## Step 1 — Create the Manifest
Minimum viable `ai-catalog.json`:
```json
{
"specVersion": "1.0",
"host": { "displayName": "My AI Tools" },
"entries": [
{
"identifier": "urn:air:example.com:server:my-tool",
"displayName": "My Tool",
"type": "application/mcp-server-card+json",
"url": "https://api.example.com/mcp/my-tool.json",
"capabilities": ["MyTool"],
"description": "One-line description of what the tool does.",
"representativeQueries": [
"natural language query that matches this tool",
"another example query"
]
}
]
}
```
Key rules:
- `identifier` — `urn:air:<your-domain>:<namespace>:<name>`; `<your-domain>` must be an FQDN you control
- `representativeQueries` — 2–5 examples; directly fed into semantic vector embeddings used for search ranking
- `url` XOR `data` — exactly one per entry
## Step 2 — Host the Manifest
Upload to:
```
https://<your-domain>/.well-known/ai-catalog.json
```
Required HTTP response headers:
| Header | Value |
|--------|-------|
| `Content-Type` | `application/json` |
| `Access-Control-Allow-Origin` | `*` (required for crawlers) |
| Protocol | HTTPS only |
## Step 3 — Alternate Discovery Mechanisms (Optional)
### Well-Known URI (primary)
```
https://example.com/.well-known/ai-catalog.json
```
### Agentmap in robots.txt
```
Agentmap: https://example.com/catalog.json
```
### HTML Link Tag
```html
<link rel="ai-catalog" href="https://example.com/catalog.json">
```
### DNS — Static Catalog (TXT)
For when `.well-known` hosting is not possible (e.g., static S3 bucket or GitHub Pages):
| Name | Type | Value |
|------|------|-------|
| `_catalog._agents.example.com` | `TXT` | `url=https://bucket.s3.amazonaws.com/ai-catalog.json` |
### DNS — Dynamic Registry (SRV)
Points to a live `POST /search` endpoint:
| Name | Type | Port | Target |
|------|------|------|--------|
| `_search._agents.example.com` | `SRV` | `443` | `search.example.com` |
## Registry Ingestion
Registries index catalogs via:
| Pipeline | Required |
|----------|----------|
| Web crawl of `ai-catalog.json` | Yes — all ARD implementations |
| Git repo scanning | Optional |
| npm / OCI registry scanning | Optional |
Publishing makes resources _potentially_ discoverable; each registry decides independently what it indexes.
## Enterprise vs. Public Publishing
| Scenario | Typical approach |
|----------|----------------|
| Public internet | Host at `.well-known`; rely on public crawlers |
| Enterprise internal | Register directly with internal registry; open-web crawling often not used |
| Vendor catalog | Vendor feed to customer registries; ARD manifest still useful for interop |
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: 472k | 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: 198k | 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: 198k | 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: 198k | Updated | Claude CodeCodex | Verified | Install |