AB programmatic-seo-writer
Use when the user wants to write an SEO article, generate a blog post, create content for a keyword, run the full SEO pipeline, or check available keywords. Triggers include: "write article: [keyword]", "generate SEO content", "show available keywords", "force framework [A/B/C/D]: [keyword]", or simply typing a keyword directly. Executes a fully integrated 5-step pipeline — keyword backlog check → keyword matrix expansion → SERP deep analysis → framework auto-selection → four-block article output (SEO metadata + full article + FAQ Schema + GEO-optimized version). All five steps run as a single continuous workflow; data from each step feeds directly into the next. Designed for English-language SEO + AEO + GEO content production targeting Google search and generative AI engines.
As a process B 67/100 · Nearly there — weak spots: inputs and preconditions, consistency, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
- warning
body-longSKILL.md body ≈ 9434 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (programmatic-seo-writer) differs from the folder (seo-geo-content-engine)
- 40Execution cost. Instruction body is 9434 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 6 branches
- 100Tools and files. No external tools needed
- 100Steps. 77 steps
- 100When it triggers. States when to use and when not to
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
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)
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 787: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 77 items
- +3Output format is stated explicitly
- +4Has examples (16 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.