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 TIKAZI/TIKAZ-AI-Skills --skill visual-contentgit clone --depth 1 https://github.com/TIKAZI/TIKAZ-AI-SkillsWrote 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/tikazi/tikaz-ai-skills/visual-content)<a href="https://agentmods.dev/skills/tikazi/tikaz-ai-skills/visual-content"><img src="https://agentmods.dev/badge/skills/tikazi/tikaz-ai-skills/visual-content/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/tikazi/tikaz-ai-skills/visual-content"><img src="https://agentmods.dev/badge/skills/tikazi/tikaz-ai-skills/visual-content.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 | $0.00048 | $0.00458 |
| Opus 5 | $0.00024 | $0.00229 |
| Sonnet 5 | $0.00010 | $0.00092 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
visual-content 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 11d 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.
What it actually says
Visual Content
Designed, integrated, refactored, and continuously maintained by TIKAZ.
Inputs and routing
Accept the content or thesis, audience, publishing surface, required asset, factual sources, accessibility needs, and license boundary. Use one child Skill directly when writing cleanup, one illustration identity, or lawful music discovery is the whole task.
TIKAZ method
- Extract the content thesis, audience, publishing surface, visual jobs, claims, and accessibility needs.
- Use
concise-writing-editoronly when the source is padded or generic; preserve facts and author voice. - Route to exactly one illustrator:
xiaohei-article-illustratororzhuge-logistics-illustrator. - Create a shot card: message, scene/mechanism, composition, labels, character role, palette, forbidden elements, source assets, and license status.
- Review at publishing size for message clarity, text accuracy, character consistency, cropping, hierarchy, and alt text.
- Use
legal-free-musiconly when music is requested; retain license and attribution evidence with the selected file.
Boundary
This suite intentionally excludes 生图-Image2. It defines content and QA workflows without requiring a specific image-generation provider.
Output, fallback, and limits
Return the selected route, shot or editing contract, source and license ledger, accessible text, publishing-size QA, and final asset or explicit creation handoff. If no drawing or generation tool is available, deliver an editable SVG/HTML specification or shot card rather than pretending an image was produced. Never turn uncertain labels or claims into definitive visuals.
Example
Use visual-content to clean this article, choose one illustration route, create a sourced shot card, and verify labels, licenses, alt text, and publishing-size clarity.
Read references/routing.md and references/output-contract.md.
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 283 B
- assets/workflow.svg 4.8 KB
- concise-writing-editor/agents/openai.yaml 322 B
- concise-writing-editor/SKILL.md 1.5 KB
- legal-free-music/agents/openai.yaml 604 B
- legal-free-music/SKILL.md 5.5 KB
- README.md 5.1 KB
- README.zh-CN.md 2.5 KB
- references/output-contract.md 299 B
- references/routing.md 707 B
- xiaohei-article-illustrator/agents/openai.yaml 273 B
- xiaohei-article-illustrator/SKILL.md 2.7 KB
- zhuge-logistics-illustrator/agents/openai.yaml 253 B
- zhuge-logistics-illustrator/SKILL.md 2.6 KB
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.
- 11d ago First seen · 38 lines · 48 tokens per session scan A 77608df97a30
visual-content is a skill published in the GitHub repository TIKAZI/TIKAZ-AI-Skills (6 stars, last pushed 8d ago), licensed MIT. It adds 48 tokens to every session and 458 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
optimize-claude-opus-5-prompts
Clarify, audit, and rewrite rough or existing prompts for Claude Opus 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt, system prompt, or agent harness for Claude Opus 5 (claude-opus-5), including requests phrased as Opus 5 prompt…
optimize-claude-fable-5-prompts
A prompt-editing method for Claude Fable 5, an AI model. It turns rough or existing instructions into clearer prompts while keeping the original goal and important limits.
optimize-gpt-5-6-prompts
A guide for improving prompts written for OpenAI’s GPT-5.6 models, including GPT-5.6 Sol.