Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add dr-robert-li/cowork-wordpress-expert --skill site-specificationgit clone --depth 1 https://github.com/dr-robert-li/cowork-wordpress-expertWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/site-specification)<a href="https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/site-specification"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/site-specification/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/site-specification"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/site-specification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.02533 |
| Opus 5.5 | $0.00014 | $0.01013 |
| Sonnet 5.5 | $0.00007 | $0.00507 |
| Haiku 4.5 | $0.00003 | $0.00253 |
Grade A, and why
site-specification scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
97% identical to site-specification — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site Specification Skill
Extract detailed site specifications from user descriptions to guide theme generation. If the user has provided images, image urls or other documents, analyze them for additional clues about the brand and design preferences - obviously things like an exising logo image can be very informative about the brand's aesthetic, tone, and values, and any written documents can contain explicit statements about the brand identity or design preferences.
Site Spec Schema
A complete site specification uses this JSON structure:
{
"siteBrief": {
"siteName": "Name of the site/business",
"siteType": "Type of site (e.g., e-commerce, portfolio, blog, SaaS, restaurant)",
"primaryGoal": "Main purpose or conversion goal of the site",
"audience": "Target audience description",
"tone": "Voice and tone for the content",
"brandKeywords": "Keywords describing the brand aesthetic and values"
},
"layoutNotes": [
"Each layout requirement as a separate string",
"Sections, features, and visual elements"
],
"typography": {
"primaryFont": "Main font for headings",
"secondaryFont": "Font for body text",
"usage": "How fonts should be applied",
"fontImport": "Google Fonts import URL"
}
}
All fields are optional - only include what can be reasonably inferred from the user's description.
Inference Patterns by Site Type
SaaS / Technology
Infer:
- Primary goal: Drive signups or demo requests
- Audience: Technical decision-makers, developers, or business users
- Tone: Professional, innovative, trustworthy
- Brand keywords: Modern, efficient, powerful, seamless
Typical layout:
- Hero with value proposition and CTA
- Feature grid or comparison
- Social proof (logos, testimonials)
- Pricing section
- FAQ
- Final CTA
Typography tendency:
- Clean geometric sans-serifs
- Strong hierarchy for scanning
- Consider: Satoshi, Plus Jakarta Sans, Outfit
E-commerce / Retail
Infer:
- Primary goal: Drive purchases
- Audience: Consumers with specific interests
- Tone: Varies by brand (luxury vs. casual vs. value)
- Brand keywords: Depends on positioning
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 328 lines · 34 tokens per session scan A 50900bcabaef
site-specification is a skill published in the GitHub repository dr-robert-li/cowork-wordpress-expert (29 stars, last pushed 8mo ago), licensed MIT. It adds 34 tokens to every session and 2,533 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to site-specification, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.