Agent-skills manifest with sha256 integrity
Publish `/.well-known/agent-skills/index.json` with a digest for each skill so agents can verify they fetched the right instructions before they act on them.
Why this can grow a startup
Capability discovery gets more useful when the client can trust the file it just loaded. The manifest digest is a small detail with a big effect: it helps agents verify content integrity, reduces confusion around stale mirrors, and makes the discovery layer feel like infrastructure instead of an undocumented convenience page.
Company example
Mintlify's recommended agent-skills endpoint uses the 0.2.0 discovery schema and includes a `sha256` digest for every listed skill file.
Source and metric
Source: Mintlify Docs · Browse Mintlify Docs tactics
The agent-skills 0.2.0 manifest includes a sha256 digest for each skill file
Source discovered: May 27, 2026
When to use it
Use this when AI Search, Documentation, Integrations is relevant to agent enablement, integration hygiene, brand trust and you can run a bounded test with a free budget.
When not to use it
Do not use it as a substitute for customer evidence, a clear owner, or a measurable stop condition. Local platform rules and market behavior still need checking.
Founder checklist
- Read Mintlify Docs and identify what is directly supported.
- Choose one channel context: AI Search, Documentation, Integrations.
- Define the test around The agent-skills 0.2.0 manifest includes a sha256 digest for each skill file.
- Set an owner, evidence window, and stop condition before launch.
Explore the context
Apply this with an operator
Turn isolated search tactics into a crawlable visibility system tied to demand and proof.