CtrlK
BlogDocsLog inGet started
Tessl Logo

mlava/agent-ready-cli

Use the Agent Ready (agent-ready.dev) command-line client to scan any public URL for AI agent-readability against the Vercel Agent Readability Spec, the llmstxt.org standard, and agent-protocol manifests (MCP server cards, A2A, agents.json, agent-permissions.json, UCP, x402, NLWeb). Activates for "scan this site with the agent-ready CLI", "run agent-ready scan {URL} in the terminal", "agent-ready get {id}", "agent-ready list", "agent-ready ask {question}", or any time the user wants a one-command terminal scan with no fetch wiring and no MCP install. Pick this skill when the agent can run shell commands. For raw HTTP, use the `agent-ready-api` skill; for MCP-native tool calls, use `agent-ready-mcp`.

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, highly actionable CLI skill body with executable commands and a clear step sequence. The main weakness is a referenced REFERENCE.md that does not exist in the bundle, plus minor verbosity in the anonymous-tier and naming-gotcha passages.

Suggestions

Add the missing REFERENCE.md to the bundle (or remove the reference and inline the few needed exit codes / env vars), since the body currently points to a file that is not present.

Tighten the Step 3 anonymous-tier paragraph and consolidate the repeated npx-vs-command naming caveats into a single note to reduce token overhead.

Add one explicit validation checkpoint (e.g. 'Confirm Node >= 20.10 before proceeding; if `--version` fails, stop and install Node') to push workflow clarity toward the top anchor.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence (no explanation of npm, API keys, or URLs), but a few spots could be tightened — e.g. the long Step 3 paragraph on anonymous-tier behavior and the repeated naming-gotcha caveats. Fits the 'efficient; minor instances that could be trimmed' anchor, not a 5 because of those padded passages.

4 / 5

Actionability

Fully executable, copy-paste-ready commands throughout (npx version check, scan with flag variants, get/list/ask invocations) plus a concrete options table and jq example, covering the common cases — matches the anchor-5 example.

5 / 5

Workflow Clarity

Clear numbered sequence (Steps 1–7) with decision branches (A/B/C for key location) and error-handling notes (quota_exhausted, --no-wait capture). Not a 5 because there are no explicit validate-then-proceed checkpoints, though the non-destructive scan task does not strictly require them.

4 / 5

Progressive Disclosure

Well-structured into labeled sections with a clearly signaled one-level reference ('see [REFERENCE.md](REFERENCE.md)'). Not a 5 — and a real gap — because REFERENCE.md is referenced but is absent from the bundle (no references/ directory or file exists), leaving a dangling pointer.

4 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A dense but information-rich description that nails all four dimensions: concrete actions, natural trigger phrasing, explicit what/when guidance, and clear sibling differentiation. Every clause earns its place rather than padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (scan, get, list, ask) and comprehensively names the target specs (Vercel Agent Readability Spec, llmstxt.org, MCP server cards, A2A, agents.json, UCP, x402, NLWeb), matching the 'multiple specific concrete actions; comprehensive coverage' anchor.

5 / 5

Completeness

Explicitly answers both 'what' (scan any public URL for agent-readability against named specs) and 'when' ('Activates for ...' plus concrete trigger phrases and a 'Pick this skill when the agent can run shell commands' clause), matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Includes natural user phrasings ('scan this site with the agent-ready CLI', 'run agent-ready scan {URL} in the terminal') plus the literal command invocations users would say, giving comprehensive coverage of natural terms.

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche (one-command terminal scan, no fetch wiring, no MCP install) and explicitly differentiates siblings ('For raw HTTP, use the `agent-ready-api` skill; for MCP-native tool calls, use `agent-ready-mcp`'), minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents