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`.

72

Quality

90%

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

78%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-structured, highly actionable CLI usage guide with clear sequencing and good error-handling guidance. Its main weakness is a dangling reference: the body points to REFERENCE.md twice but no such file ships with the skill.

Suggestions

Ship the missing REFERENCE.md (global options, environment variables, exit codes, reference URLs) or remove the two references to it — currently both links are dead ends.

Cut the repeated spec enumeration in the opening paragraph (it already appears in the frontmatter description) and collapse the "When to use" section's trigger-phrase pointer to reduce token redundancy.

Consider moving the rating-band / check-category reference (Step 7, lines 137–142) into REFERENCE.md so the main body stays a lean procedure.

DimensionReasoningScore

Conciseness

Largely efficient and operational — it assumes Claude knows what npm/API keys are and leads with executable commands — but the intro re-enumerates the full spec list already in the description and the "When to use" section re-points to the same triggers, minor redundancy that could be trimmed.

4 / 5

Actionability

Fully executable, copy-paste-ready commands throughout (`npx agent-ready-scanner --version`, `agent-ready scan https://example.com --json | jq '.vercelScore'`, get/list/ask invocations) plus a concrete options table covering the common cases.

5 / 5

Workflow Clarity

Steps 1–7 give a clear, ordered sequence with branching in Step 2 (env var → .env → ask user) and error-recovery feedback (no-wait → capture id → get; quota_exhausted → reset date → dashboard); falls short of 5 only because there is no explicit validate-then-proceed checkpoint, which this read-only scan task does not strictly require.

4 / 5

Progressive Disclosure

Structure is sound and the overview correctly pushes detail (global options, env vars, exit codes, reference URLs) to a one-level-deep REFERENCE.md, but that file does not exist anywhere in the bundle — the referenced path is a dead link, so navigation is actually broken rather than merely having minor gaps.

3 / 5

Total

16

/

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.

This is a strong, exemplar-style description: concrete actions, explicit trigger phrases, both what and when answered, and clear boundary guidance against sibling skills. It closely matches the rubric's good_overall_examples.

DimensionReasoningScore

Specificity

Names multiple concrete subcommands — "scan any public URL for AI agent-readability", "agent-ready get {id}", "agent-ready list", "agent-ready ask {question}" — giving comprehensive coverage of the CLI's actions rather than vague verbs.

5 / 5

Completeness

Explicitly answers both what (scans a public URL against the named specs/manifests) and when ("Activates for ..." trigger phrases plus "Pick this skill when the agent can run shell commands"), matching the 5-anchor pattern.

5 / 5

Trigger Term Quality

Includes natural trigger phrases ("scan this site with the agent-ready CLI", "run agent-ready scan {URL} in the terminal") plus synonyms ("one-command terminal scan with no fetch wiring and no MCP install"), covering how users would actually phrase the request.

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche (one-command terminal scan) and explicitly disambiguates from siblings — "For raw HTTP, use the `agent-ready-api` skill; for MCP-native tool calls, use `agent-ready-mcp`" — minimizing wrong-skill triggers.

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