is-agentic — Claude Code skill: site audits and setup
The is-agentic Claude Code skill scores how ready a website, domain, or public MCP endpoint is for AI agents. It can fetch a report or help address the issues behind a score.
Apache-2.0 108 installs ★ 344 updated 2026-10-23
npx skills add vercel/vercel-plugin --skill is-agentic -a claude-codeWhat is-agentic does
The skill audits a public URL and returns an agent-readiness score from 0 to 100, with scan evidence and suggested fixes. It can request a score, retrieve a JSON report, or work through the findings.
For a CLI check, it runs npx is-agentic <domain> --json. The command returns a stored report or starts a scan and waits for it to finish. The API reads completed reports only; the MCP endpoint also exposes tools for reports, methodology, and developer documentation. These interfaces are free and require no API key.
Reports belong to an exact URL: example.com/docs and example.com are separate targets. The CLI can return the existing snapshot after a fix; compare scanned_at, since reports refresh on access only when they are older than 6 hours.
What it helps with
- score a public site for AI-agent readiness
- retrieve a domain's stored score as JSON
- identify issues that lower a site's score
- use scan recommendations to address reported issues
Example prompts for the agent
- Check
example.comfor AI-agent readiness and return the JSON report. - Fetch the Is Agentic report for
https://example.com/docs. - Review the findings for
example.comand apply the suggested fixes.
How to install is-agentic
1Skills CLI (Vercel)
npx skills add vercel/vercel-plugin --skill is-agentic -a claude-code2Manually: put the files in place
~/.claude/skills/is-agentic/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/is-agentic/
1Skills CLI (Vercel)
npx skills add vercel/vercel-plugin --skill is-agentic -a codex2Manually: put the files in place
.agents/skills/is-agentic/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add vercel/vercel-plugin --skill is-agentic -a cursor2Manually: put the files in place
.cursor/skills/is-agentic/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install vercel/vercel-plugin skills/is-agentic2Manually: put the files in place
.github/skills/is-agentic/SKILL.md1Skills CLI (Vercel)
npx skills add vercel/vercel-plugin --skill is-agentic -a gemini-cli2Platform CLI
gemini skills install https://github.com/vercel/vercel-plugin --path skills/is-agenticManually: put the files in place
.devin/skills/is-agentic/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add vercel/vercel-plugin --skill is-agentic -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about is-agentic
How do I install is-agentic in Claude Code?
Run npx skills add vercel/vercel-plugin --skill is-agentic -a claude-code. The skill file is placed at ~/.claude/skills/is-agentic/SKILL.md.
What does is-agentic do?
It audits a public URL for AI-agent readiness and returns a score with scan evidence and suggested fixes. The skill can fetch the report or help address its findings.
What URLs can is-agentic scan?
It accepts public HTTP or HTTPS URLs. Paths and query strings are part of the target, so a site root and one of its pages have separate reports.
Source text
SKILL.md · Apache-2.0
---
name: is-agentic
description: Score how ready a website, domain, or public MCP endpoint is for AI agents using Is Agentic, and read or act on the resulting report. Use when asked to check a site's agent readiness, get its Is Agentic score, fetch a scored report as JSON, or fix the issues that lower a site's score.
metadata:
priority: 4
docs:
- "https://is-agentic.com/docs"
- "https://is-agentic.com/llms.txt"
bashPatterns:
- '\bnpx\s+is-agentic\b'
- '\bbunx\s+is-agentic\b'
- '\bskills\s+add\s+vercel-labs/is-agentic\b'
- '\bcurl\s+[^\n]*is-agentic\.com/api\b'
---
# Is Agentic
Is Agentic runs a technical audit of a public URL and publishes a 0 to 100 agent-readiness score with evidence-backed issues and recommended fixes. All interfaces below are public, read-only, and free; none needs an API key.
## Get a score
Default: the official CLI. It returns a stored report immediately, or starts a scan and waits when none exists.
```sh
npx is-agentic <domain> --json
```
Omit `--json` only when a human is reading the terminal output.
When you cannot run commands, use the read-only API instead. It never starts a scan; a 404 means no completed report exists yet.
```
GET https://is-agentic.com/api/v1/report?url=<url-encoded-target>
```
MCP hosts can connect to the Streamable HTTP endpoint `https://is-agentic.com/mcp` and call `is_agentic_get_report`, `is_agentic_get_methodology`, or `is_agentic_get_developer_docs`.
## Read a report
The JSON response is a `PublicScanReport`:
- `score`: 0 to 100, or `null` when the target could not be scored (for example an MCP server that requires authentication). `score_label` explains a null score.
- `score_breakdown.essential` and `.recommended`: each has `earned`, `available`, `passing`, `total`. Essential checks are the ones that matter most; a site can look polished and still fail them.
- `score_breakdown.bonus`: `points` and `positive_signals`. Bonus is additive and never required; do not treat missing bonus signals as defects.
- `issues[]`: each has `id`, `name`, `tier` (`essential` | `recommended` | `bonus`), `result` (`failed` | `partial`), `details` (evidence from the scan), and `recommendation` (the fix).
- `report_url`: the canonical human-readable report. Cite it when reporting a score to a person.
- `scanned_at`: when the audit ran. Reports are immutable snapshots.
## Improve a site's score
1. Fetch the report for the exact target you are improving.
2. Work through `issues` in this order: `essential` failures, `essential` partials, then `recommended`. Ignore `bonus` unless everything else passes.
3. For each issue, `details` says what the scan observed and `recommendation` says what to change. Prefer the recommendation; it was written against the actual evidence.
4. After deploying fixes, get a fresh score and compare `scanned_at` to confirm you are not reading the old snapshot (see gotchas).
## Errors
Failures are RFC 9457 `application/problem+json` with a stable `code` and a `resolution` hint. Act on the code:
- `invalid_url` (400): pass a public HTTP or HTTPS URL.
- `report_not_found` (404): no completed report exists; create one with the CLI, or open `https://is-agentic.com/scan/<target>` to start a scan, then retry after it completes.
- `rate_limit_exceeded` (429): honor `Retry-After` before retrying.
- `report_temporarily_unavailable` (503): retry shortly; do not start a new scan.
## Gotchas
- Reports refresh only when a visit finds them older than 6 hours. Re-running the CLI right after deploying a fix returns the same stored snapshot; check `scanned_at` before drawing conclusions, and use the Rescan control on the report page when a human needs an immediate re-run.
- The API and the CLI differ on missing reports: the API returns 404, the CLI starts a scan and waits. Pick accordingly.
- Targets are exact: `example.com/docs` and `example.com` are separate reports, and a URL with a query string is its own report.
- The rate limit is 120 requests per IP per 60 seconds.
- For token-light reading, content pages and completed reports honor `Accept: text/markdown`.
© vercel · Apache-2.0 · vercel/vercel-plugin