AC ai-readiness
Generates a complete set of AI readiness files for any website from a single command. Invoke this skill whenever the user types `/ai-readiness [url]`, asks to "create AI readiness files for [site]", "make my site AI-ready", "generate llms.txt for [url]", "build AI files for [domain]", or any variation of wanting to optimize a website for AI systems (ChatGPT, Claude, Gemini, Perplexity, etc.). Also trigger when the user asks about AI crawlers, llmstxt.org, ai.txt, RAG indexing of a website, or improving a site's visibility in AI search. The output is a complete folder of 18 production-ready files — dropped into the workspace, ready to deploy to the web root.
Generates a complete set of AI readiness files for any website from a single command.
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "created_by" - note
frontmatter-keyunknown frontmatter key "company"
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 47 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1795 tokens
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 665: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 47 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.