agent-ready
Implements agent-readiness on public sites and docs from Mintlify Agent Score, AFDocs, Is Agentic, Is It Agent Ready, or url-discovery-bench reports, or from server logs of agents 404ing on guessed URLs. Use when asked to "make this agent-ready", "improve Agent Score", "fix llms.
Install
npx skills add https://github.com/mblode/agent-skills/tree/main/skills/agent-ready
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install mblode-agent-skills@llmmart
git clone https://github.com/mblode/agent-skills.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole mblode/agent-skills collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Agent Ready
Turn a public agent-readiness score, or a log of agents failing to navigate, into shipped, verified HTTP and docs changes.
- IS: ingesting Mintlify Agent Score / AFDocs, Is Agentic, Is It Agent Ready, or url-discovery-bench findings, plus server-side evidence of agent 404s, inspecting the repo, implementing the matching protocols, adding tests, and verifying live responses.
- IS NOT: rewriting docs prose (
ghostwriter), package/CLI/SDK ergonomics (dx-audit), whether an in-product agent can be trusted (ax-audit), search ranking, crawler policy, and Next.jsllms.txt/markdown routes (seo; this skill owns the AFDocs and Is Agentic contract those routes must satisfy), or repo instruction files (agents-md). Do not vendor vercel-labs/is-agentic; that skill retrieves reports. This one implements the product.
Contents
Workflow
Agent-ready progress:
- [ ] Step 1: Ingest the report, the agent 404 log, or run scanners against the public URL
- [ ] Step 2: Inspect the existing codebase before any edit
- [ ] Step 3: Inventory every knowledge surface the origin serves and map each finding to a real one; skip surfaces the product does not offer
- [ ] Step 4: Load the matching reference and implement the map first, then failures, then warnings. For Next.js App Router `llms.txt` and markdown routes, load `seo` (that skill's `nextjs-implementation.md` and `answer-engines.md`) instead of a second recipe.
- [ ] Step 5: Add or update tests for every behavior you change
- [ ] Step 6: Verify every public endpoint and machine-readable file you touched (`scripts/check-surfaces.sh`, then the curl recipes for anything it does not cover)
- [ ] Step 7: Report changes, quoted verification, and remaining product decisions
A pasted scorecard is the spec. If none is present and the user named a public URL, gather one:
pnpm dlx afdocs check <docs-url> --format scorecard --sampling deterministic
pnpm dlx is-agentic <domain> --json
Is It Agent Ready: POST https://isitagentready.com/api/scan with {"url":"<origin>","format":"agent"}. Prefer the user's pasted report over a new scan when both exist.
Server logs are a brief too. Agents fetch server-side and run no JavaScript, so they never appear in client-side analytics; count requests for .md URLs, llms.txt, and recognized AI user agents, and treat a stream of 404s from those agents (fetch, 404, guess a sibling path, retry) as the failing check. references/verification.md has the log queries and the navigation benchmark.
Step 3 covers the whole origin, not only /docs: changelog, release notes, help center, community, and status pages are knowledge agents answer from, and they are usually HTML-only while the docs are ready. Decide per surface whether it gets markdown twins and an index entry; marketing pages do not.
Preserve visual design and existing product behavior. Change discovery, representations, headers, and documented contracts, not the feature set.
Local test suites that cannot reach production are safe to run, fix, and rerun. Do not deploy, change DNS, buy a registry name, or write outside the working tree without authorization.
Done when every in-scope failing check has a code or content change (or an explicit skip with reason), tests cover the new behavior, and Step 6 quotes status, Content-Type, and the relevant headers or body from the environment you actually hit.
Reference files
| File | Read when |
|---|---|
| references/docs-afdocs.md | Mintlify Agent Score, AFDocs, llms.txt, .md URLs, the index link in markdown twins, Accept negotiation, page size, auth gates, non-docs knowledge surfaces |
| references/api-surfaces.md | Any Is Agentic report: essential checks (content without JavaScript, agent-friendly 404s), JSON errors, OpenAPI, versioning, rate limits, function calling, CLI, MCP |
| references/site-discovery.md | Is It Agent Ready: robots, sitemap, Link headers, DNS-AID, well-known catalogs, bot rules |
| references/verification.md | Step 6: check-surfaces.sh, curl recipes, server-log measurement, url-discovery-bench, and what counts as evidence |
Priority
Agents read markdown fine and fail at navigation. In Mintlify's 2026 benchmark (2,400 tasks, 20 docs sites, Claude and Codex) accuracy held at 94 to 99% in every format while failed requests per task went 2.23 on HTML, 1.42 on plain markdown, 0.11 once each markdown page linked llms.txt. Order work accordingly:
- The map:
llms.txton the docs host, a link to it in the first lines of every markdown twin, andLinkheaders that advertise both. Agents request.mdandllms.txtonly when they know they exist. - Failures the product actually has (docs HTML that agents cannot read, HTML error pages on a real API, gated public docs with no alternate path).
- Warnings on those same surfaces (
llms.txtcoverage, buried directives, wrongContent-Type). - Recommended checks that match a surface already in the repo (OpenAPI, MCP, OAuth).
- Emerging extras (commerce protocols, A2A, DNS-AID) only when the product already offers them or the user asked to add them.
A missing MCP card is not a failure on a site that has no MCP server. Do not invent an API, CLI, or payment protocol to chase points.
Output
Group work by check. For each: evidence from the report, files changed, exact markup or schema added, verification quote, skip reason if N/A. When the brief was a 404 log or benchmark, quote failed requests per task before and after.
Finish with remaining items that need a product decision, DNS access, or credentials.
Gotchas
is-agentic.com/scan/<domain>shows the last stored snapshot, which can be months old. Check the snapshot date and press Rescan (or run the CLI) before treating it as the brief, and rescan again to verify.- A
.mdtwin has no navigation: the conversion stripped it with the chrome. Emit thellms.txtlink from the twin route so no page can miss it; a per-page edit drifts. - Markdown twins are a route in one app. When the changelog or blog lives in a separate marketing app on the same origin, it stays HTML-only without anyone deciding that; walk every app, not only the one with the twin route.
- One
llms.txtadvertised three ways (rel="llms-txt"from a proxy,rel="https://llmstxt.org/rel/llms-txt"from framework headers,rel="describedby"from a layout<link>) leaves the scanner reading whichever layer wins on that response. Pick the rel set the scanners probe and emit it from one place. llms.txtthat lists HTML while.mdtwins exist steers agents away from markdown and is scored worse than linking.mdfrom the start.- A directive in
<head>, nav, or past 50% of the HTML body does not count. Put it in the document body, near the top, server-rendered. - A dashboard with no agent traffic proves nothing: agents run no JavaScript, and Search Console and SERP tools count searchers, not agents. Server logs of
.md,llms.txt, and AI user agent requests are the only readership measure; without a log drain the honest number is No data, not a client-side proxy. - Bot protection tuned for crawlers (challenge pages, WAF bot rules, tight rate limits on
text/markdownroutes) blocks the agents you are optimizing for, and they cannot pass a challenge. Exempt the machine-readable routes or serve them from paths the rules do not cover. - Coverage fail vs curated index: regenerate from the sitemap when the site intends parity; if the index is intentional, say so and do not pad it with marketing URLs.
Maintenance only: evals/evals.json is for changing this skill, not for a user task.
Files (agent-skills)
-
evals
-
fixtures
-
markdown-negotiation
-
base
-
content
-
exports.mdx 444 B · in bundle
-
overview.mdx 439 B · in bundle
-
risk-score.mdx 460 B · in bundle
-
-
public
-
docs.css 564 B · in bundle
-
llms.txt 467 B
Loading… -
robots.txt 23 B
Loading…
-
-
src
-
content.mjs 890 B · in bundle
-
render.mjs 1.5 KB · in bundle
-
server.mjs 1.9 KB · in bundle
-
-
test
-
server.test.mjs 1.4 KB · in bundle
-
-
package.json 221 B
Loading…
-
-
fixture.json 28 B
Loading…
-
-
no-api-scorecard
-
base
-
pages
-
guides
-
frost-dates.html 563 B · in bundle
-
sowing-calendar.html 891 B · in bundle
-
-
about.html 399 B · in bundle
-
buy.html 285 B · in bundle
-
index.html 497 B · in bundle
-
-
public
-
almanac.css 457 B · in bundle
-
llms.txt 467 B
Loading… -
robots.txt 45 B
Loading…
-
-
scripts
-
build.mjs 2.2 KB · in bundle
-
-
package.json 149 B
Loading… -
site.config.mjs 170 B · in bundle
-
-
fixture.json 30 B
Loading…
-
-
stale-llms-index
-
base
-
content
-
docs
-
authentication.mdx 420 B · in bundle
-
delivery-receipts.mdx 460 B · in bundle
-
quickstart.mdx 414 B · in bundle
-
quiet-hours.mdx 463 B · in bundle
-
rate-limits.mdx 391 B · in bundle
-
voice-fallback.mdx 331 B · in bundle
-
-
-
scripts
-
build-site.mjs 2.6 KB · in bundle
-
preview.mjs 1.1 KB · in bundle
-
-
static
-
llms.txt 389 B
Loading… -
robots.txt 74 B
Loading…
-
-
package.json 241 B
Loading… -
site.config.mjs 392 B · in bundle
-
-
fixture.json 30 B
Loading…
-
-
twin-index-link
-
base
-
app
-
docs
-
llms.txt
-
route.ts 500 B
Loading…
-
-
-
layout.tsx 874 B · in bundle
-
-
content
-
docs
-
errors.mdx 546 B · in bundle
-
quickstart.mdx 608 B · in bundle
-
webhooks.mdx 698 B · in bundle
-
-
-
lib
-
docs.ts 1.1 KB
Loading…
-
-
next.config.mjs 264 B · in bundle
-
package.json 473 B
Loading… -
tsconfig.json 429 B
Loading…
-
-
fixture.json 29 B
Loading…
-
-
untyped-api-errors
-
base
-
public
-
docs
-
index.html 1 KB · in bundle
-
-
index.html 1 KB · in bundle
-
-
src
-
lib
-
limiter.mjs 487 B · in bundle
-
store.mjs 584 B · in bundle
-
-
routes
-
rates.mjs 692 B · in bundle
-
shipments.mjs 1.5 KB · in bundle
-
-
app.mjs 2.2 KB · in bundle
-
server.mjs 460 B · in bundle
-
-
openapi.json 2.5 KB
Loading… -
package.json 300 B
Loading…
-
-
fixture.json 31 B
Loading…
-
-
-
evals.json 6.6 KB
Loading…
-
-
references
-
api-surfaces.md 6.7 KB
Loading… -
docs-afdocs.md 6.9 KB
Loading… -
site-discovery.md 3.3 KB
Loading… -
verification.md 4.3 KB
Loading…
-
-
scripts
-
check-surfaces.sh 3.7 KB
Loading…
-
-
SKILL.md 8.4 KB
--- name: agent-ready description: Implements agent-readiness on public sites and docs from Mintlify Agent Score, AFDocs, Is Agentic, Is It Agent Ready, or url-discovery-bench reports, or from server logs of agents 404ing on guessed URLs. Use when asked to "make our site agent-ready", "improve Agent Score", "fix llms.txt coverage", "agents keep 404ing on our docs", or when a pasted scorecard is the brief. compatibility: The verification script needs Bash and curl. Scanner commands need Node.js and npm registry access. --- # Agent Ready Turn a public agent-readiness score, or a log of agents failing to navigate, into shipped, verified HTTP and docs changes. - **IS:** ingesting Mintlify Agent Score / AFDocs, [Is Agentic](https://is-agentic.com/), [Is It Agent Ready](https://isitagentready.com/), or [url-discovery-bench](https://github.com/mintlify/url-discovery-bench) findings, plus server-side evidence of agent 404s, inspecting the repo, implementing the matching protocols, adding tests, and verifying live responses. - **IS NOT:** rewriting docs prose (`ghostwriter`), package/CLI/SDK ergonomics (`dx-audit`), whether an in-product agent can be trusted (`ax-audit`), search ranking, crawler policy, and Next.js `llms.txt`/markdown routes (`seo`; this skill owns the AFDocs and Is Agentic contract those routes must satisfy), or repo instruction files (`agents-md`). Do not vendor [vercel-labs/is-agentic](https://github.com/vercel-labs/is-agentic); that skill retrieves reports. This one implements the product. ## Contents - [Workflow](#workflow) - [Reference files](#reference-files) - [Priority](#priority) - [Output](#output) - [Gotchas](#gotchas) ## Workflow ```text Agent-ready progress: - [ ] Step 1: Ingest the report, the agent 404 log, or run scanners against the public URL - [ ] Step 2: Inspect the existing codebase before any edit - [ ] Step 3: Inventory every knowledge surface the origin serves and map each finding to a real one; skip surfaces the product does not offer - [ ] Step 4: Load the matching reference and implement the map first, then failures, then warnings. For Next.js App Router `llms.txt` and markdown routes, load `seo` (that skill's `nextjs-implementation.md` and `answer-engines.md`) instead of a second recipe. - [ ] Step 5: Add or update tests for every behavior you change - [ ] Step 6: Verify every public endpoint and machine-readable file you touched (`scripts/check-surfaces.sh`, then the curl recipes for anything it does not cover) - [ ] Step 7: Report changes, quoted verification, and remaining product decisions ``` A pasted scorecard is the spec. If none is present and the user named a public URL, gather one: ```bash pnpm dlx afdocs check <docs-url> --format scorecard --sampling deterministic pnpm dlx is-agentic <domain> --json ``` Is It Agent Ready: `POST https://isitagentready.com/api/scan` with `{"url":"<origin>","format":"agent"}`. Prefer the user's pasted report over a new scan when both exist. Server logs are a brief too. Agents fetch server-side and run no JavaScript, so they never appear in client-side analytics; count requests for `.md` URLs, `llms.txt`, and recognized AI user agents, and treat a stream of 404s from those agents (fetch, 404, guess a sibling path, retry) as the failing check. `references/verification.md` has the log queries and the navigation benchmark. Step 3 covers the whole origin, not only `/docs`: changelog, release notes, help center, community, and status pages are knowledge agents answer from, and they are usually HTML-only while the docs are ready. Decide per surface whether it gets markdown twins and an index entry; marketing pages do not. Preserve visual design and existing product behavior. Change discovery, representations, headers, and documented contracts, not the feature set. Local test suites that cannot reach production are safe to run, fix, and rerun. Do not deploy, change DNS, buy a registry name, or write outside the working tree without authorization. Done when every in-scope failing check has a code or content change (or an explicit skip with reason), tests cover the new behavior, and Step 6 quotes status, `Content-Type`, and the relevant headers or body from the environment you actually hit. ## Reference files | File | Read when | |------|-----------| | [references/docs-afdocs.md](references/docs-afdocs.md) | Mintlify Agent Score, AFDocs, `llms.txt`, `.md` URLs, the index link in markdown twins, Accept negotiation, page size, auth gates, non-docs knowledge surfaces | | [references/api-surfaces.md](references/api-surfaces.md) | Any Is Agentic report: essential checks (content without JavaScript, agent-friendly 404s), JSON errors, OpenAPI, versioning, rate limits, function calling, CLI, MCP | | [references/site-discovery.md](references/site-discovery.md) | Is It Agent Ready: robots, sitemap, Link headers, DNS-AID, well-known catalogs, bot rules | | [references/verification.md](references/verification.md) | Step 6: `check-surfaces.sh`, curl recipes, server-log measurement, url-discovery-bench, and what counts as evidence | ## Priority Agents read markdown fine and fail at navigation. In Mintlify's 2026 benchmark (2,400 tasks, 20 docs sites, Claude and Codex) accuracy held at 94 to 99% in every format while failed requests per task went 2.23 on HTML, 1.42 on plain markdown, 0.11 once each markdown page linked `llms.txt`. Order work accordingly: 1. The map: `llms.txt` on the docs host, a link to it in the first lines of every markdown twin, and `Link` headers that advertise both. Agents request `.md` and `llms.txt` only when they know they exist. 2. Failures the product actually has (docs HTML that agents cannot read, HTML error pages on a real API, gated public docs with no alternate path). 3. Warnings on those same surfaces (`llms.txt` coverage, buried directives, wrong `Content-Type`). 4. Recommended checks that match a surface already in the repo (OpenAPI, MCP, OAuth). 5. Emerging extras (commerce protocols, A2A, DNS-AID) only when the product already offers them or the user asked to add them. A missing MCP card is not a failure on a site that has no MCP server. Do not invent an API, CLI, or payment protocol to chase points. ## Output Group work by check. For each: evidence from the report, files changed, exact markup or schema added, verification quote, skip reason if N/A. When the brief was a 404 log or benchmark, quote failed requests per task before and after. Finish with remaining items that need a product decision, DNS access, or credentials. ## Gotchas - `is-agentic.com/scan/<domain>` shows the last stored snapshot, which can be months old. Check the snapshot date and press Rescan (or run the CLI) before treating it as the brief, and rescan again to verify. - A `.md` twin has no navigation: the conversion stripped it with the chrome. Emit the `llms.txt` link from the twin route so no page can miss it; a per-page edit drifts. - Markdown twins are a route in one app. When the changelog or blog lives in a separate marketing app on the same origin, it stays HTML-only without anyone deciding that; walk every app, not only the one with the twin route. - One `llms.txt` advertised three ways (`rel="llms-txt"` from a proxy, `rel="https://llmstxt.org/rel/llms-txt"` from framework headers, `rel="describedby"` from a layout `<link>`) leaves the scanner reading whichever layer wins on that response. Pick the rel set the scanners probe and emit it from one place. - `llms.txt` that lists HTML while `.md` twins exist steers agents away from markdown and is scored worse than linking `.md` from the start. - A directive in `<head>`, nav, or past 50% of the HTML body does not count. Put it in the document body, near the top, server-rendered. - A dashboard with no agent traffic proves nothing: agents run no JavaScript, and Search Console and SERP tools count searchers, not agents. Server logs of `.md`, `llms.txt`, and AI user agent requests are the only readership measure; without a log drain the honest number is No data, not a client-side proxy. - Bot protection tuned for crawlers (challenge pages, WAF bot rules, tight rate limits on `text/markdown` routes) blocks the agents you are optimizing for, and they cannot pass a challenge. Exempt the machine-readable routes or serve them from paths the rules do not cover. - Coverage fail vs curated index: regenerate from the sitemap when the site intends parity; if the index is intentional, say so and do not pad it with marketing URLs. Maintenance only: `evals/evals.json` is for changing this skill, not for a user task.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.