Name: agent-readiness-audit
Rating: 70.39999999999999 (1 reviews)
Author: docker

agent-readiness-audit

Audit a documentation site for agent-friendliness: discovery, markdown delivery, crawlability, semantic structure, machine-readable surfaces, and content legibility. Use when asked to assess docs.docker.com or any docs site for AI/agent readiness, produce a scored report, compare with external scanners, or generate a remediation list. Triggers on: "audit docs for agent readiness", "how agent-friendly is docs.docker.com", "score our docs for AI agents", "review llms.txt / markdown / crawlability", "create an agent-readiness remediation plan".

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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-organized, actionable audit workflow that assumes Claude's competence and delegates bulky materials to one-level-deep references. Minor room to tighten rationale clauses and add explicit inline examples for the mechanical fetch-path checks.

Suggestions

Trim inferable rationale clauses (e.g. 'This helps catch stale or misleading discovery surfaces...') to push conciseness toward a clean 5.

Add a short inline example of the key fetch-path checks (e.g. a curl one-liner for Accept: text/markdown) so the most common mechanical checks are copy-paste ready without relying solely on the bundled script.

Add an explicit validate/retry feedback loop for page sampling (e.g. what to do when a sampled URL fails to fetch or returns unexpected content type) to strengthen workflow checkpoints.

Dimension	Reasoning	Score
Conciseness	Largely lean and directive, assuming Claude's knowledge (no padding about what llms.txt or sitemaps are), but contains a few rationale clauses ("This helps catch stale or misleading discovery surfaces...", "This matters for optional checks...") that an intelligent agent could infer, keeping it off a clean 5.	4 / 5
Actionability	Provides concrete copy-paste commands (the baseline-probes.sh invocation with env-var variant) and specific checks (file paths, Accept: text/markdown behavior, .md routes, JSON-LD), but leaves the precise mechanics of several fetch-path checks to the bundled script rather than inline executable examples.	4 / 5
Workflow Clarity	A clear nine-step sequence (scope -> sitewide signals -> sample -> fetch-path checks -> judge structure -> score -> compare scanners -> remediation -> report) with validation rules ("score only what you verified", N/A handling, trust-live-fetch-on-mismatch), but lacks explicit per-step error-recovery feedback loops for the batch page sampling.	4 / 5
Progressive Disclosure	Well-structured overview with clearly signaled one-level-deep references to real files ([references/rubric.md], [references/report-template.md]) and a bundled script; bulky scoring/report templates are appropriately split out rather than inlined.	5 / 5
	Total	17 / 20 Passed

Description

95%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 strong, well-targeted description that clearly states both capability and trigger conditions with natural phrasing. The only minor weakness is that the audited areas are listed as noun phrases rather than discrete verbs.

Dimension	Reasoning	Score
Specificity	Lists several concrete audit dimensions ("discovery, markdown delivery, crawlability, semantic structure, machine-readable surfaces, and content legibility") plus concrete outputs ("produce a scored report, compare with external scanners, or generate a remediation list"), but the audit list is framed as area nouns under a single verb, leaving minor coverage gaps versus a clean 5.	4 / 5
Completeness	Explicitly answers both what (audit a docs site across six named dimensions and produce scored report / scanner comparison / remediation list) and when ("Use when asked to assess docs.docker.com or any docs site..." plus explicit Triggers-on phrases).	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases users would actually say ("audit docs for agent readiness", "how agent-friendly is docs.docker.com", "score our docs for AI agents", "review llms.txt / markdown / crawlability") including the file-format term llms.txt.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (agent/AI-readiness auditing of documentation sites) with distinct, specific triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: docker/docs
Path: .agents/skills/agent-readiness-audit/SKILL.md
Commit: ff96ad1

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.