# 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.

- Canonical HTML: https://growth.iangoh.com/growth-ideas/agent-skills-manifest-with-sha256-integrity/
- Source: [mintlify.com](https://www.mintlify.com/docs/ai/skillmd)
- GrowthDex source hub: [Mintlify Docs](/sources/mintlify-docs-mintlify-com/)
- Last checked: 2026-05-27
- Rarity: rare
- Budget: free
- Channels: AI Search, Documentation, Integrations
- Stages: agent enablement, integration hygiene, brand trust, crawlability
- Key metric: The agent-skills 0.2.0 manifest includes a sha256 digest for each skill file

## Why this can grow

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.

## Ian's take

From scaling consumer platforms across MENA and Southeast Asia, my default is to distrust growth work that only looks good in a slide. For SEO and AI search, I care less about clever keyword tricks and more about clarity. A buyer, crawler, or answer engine should quickly understand who this is for, why it works, what proof backs it, and what page deserves to be cited. I would run it small enough to learn quickly, then only scale the parts that real users repeat, save, reply to, or buy from. For this tactic, I would watch one clear growth signal before putting more time or budget behind it.

## Action plan

1. Define one narrow startup segment where agent-skills manifest with sha256 integrity can create a measurable lift.
2. Turn the tactic into one offer, page, campaign, or workflow for the AI Search and Documentation channel.
3. Use the evidence from mintlify.com to set the first version of the message, format, and audience.
4. Launch a small test for 7 to 14 days with one success metric: one measurable growth signal.
5. Review the result, keep the winning message, remove weak variants, and turn the learning into a repeatable growth playbook.

## Source-backed example

Mintlify's recommended agent-skills endpoint uses the 0.2.0 discovery schema and includes a `sha256` digest for every listed skill file.

## Adjacent tactics in the same lane

- [Agent-skills index for multi-workflow products](/growth-ideas/agent-skills-index-for-multi-workflow-products/) - same source, 3 shared channels, 1 shared stage
- [Root skill.md for product capability discovery](/growth-ideas/root-skill-md-for-product-capability-discovery/) - same source, 2 shared channels, 2 shared stages
- [Reverse-proxy forwarding for agent skill paths](/growth-ideas/reverse-proxy-forwarding-for-agent-skill-paths/) - same source, 2 shared channels, 2 shared stages
- [Skill frontmatter with compatibility and tool constraints](/growth-ideas/skill-frontmatter-with-compatibility-and-tool-constraints/) - same source, 2 shared channels, 2 shared stages

## Read GrowthDex essays

Browse the plain-English essay index at [GrowthDex Blog](/blog/).

## Related GrowthDex essays

- [An agent needs a capability page, not just a crawl map](/blog/an-agent-needs-a-capability-page-not-just-a-crawl-map/) - AI Search, brand trust, technical SEO

## Advisory

If you want help turning this into a working growth system, Ian Goh offers advisory at https://iangoh.com/advisory.