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 imartinstudio/cover-prompt-skills --skill cover-cream-orange-knowledge-poster-with-docsgit clone --depth 1 https://github.com/imartinstudio/cover-prompt-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/imartinstudio/cover-prompt-skills/cover-cream-orange-knowledge-poster-with-docs)<a href="https://agentmods.dev/skills/imartinstudio/cover-prompt-skills/cover-cream-orange-knowledge-poster-with-docs"><img src="https://agentmods.dev/badge/skills/imartinstudio/cover-prompt-skills/cover-cream-orange-knowledge-poster-with-docs/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/imartinstudio/cover-prompt-skills/cover-cream-orange-knowledge-poster-with-docs"><img src="https://agentmods.dev/badge/skills/imartinstudio/cover-prompt-skills/cover-cream-orange-knowledge-poster-with-docs.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 | $0.00123 | $0.02453 |
| Opus 5 | $0.00062 | $0.01226 |
| Sonnet 5 | $0.00025 | $0.00491 |
| Haiku 4.5 | $0.00012 | $0.00245 |
Grade A, and why
cover-cream-orange-knowledge-poster-with-docs 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cream Orange Knowledge Poster With Docs
Use this skill when one article needs both a cover and section-bound inline
visuals in the cream-orange knowledge family. This skill is self-contained. Do
not route runtime work to cover-cream-orange-knowledge-poster,
article-visual-planner, or any illustration skill.
Hard Boundaries
- Accepted article sources: pasted article text, Markdown files, or plain-text files.
- Do not claim DOCX, PDF, remote article, or web scraping support.
- The article source remains read-only.
- If no valid article content is available, ask for pasted text or a Markdown/plain-text path. Do not fall back to cover-only behavior.
- Default output is returned in the conversation. Write a file only when the user explicitly provides an output path.
- An output path applies only to that requested path; do not overwrite or modify any other file.
Output Type
Use the explicit --out-type parameter to decide what to output.
--out-type template: output the invocation template only.--out-type brief: output the article visual brief set only.--out-type prompt: output final image prompts for every planned asset.--out-type all: output the brief set first, then the prompts.- Omitted
--out-type: default tobrief.
Treat 直接生成, 出图, 生成封面和配图, and 开始生图 as direct image
generation only when the user explicitly asks for images.
Template Output
For template-only mode, output exactly this structure and fill every field:
使用 $cover-cream-orange-knowledge-poster-with-docs 生成一套文章封面+正文配图方案
文章来源:{article_source}
输出类型:{out_type}
封面用途:{cover_use_case}
正文配图用途:{inline_use_case}
正文配图数量:{inline_count}
语言:{language}
封面画幅比例:{cover_ratio}
正文主画幅比例:{inline_ratio}
信息结构主线:{information_structure}
已有图片处理:{image_handling}
补充背景:{context}
禁用元素:{forbidden_elements}
Required Inputs
Extract or infer:
- Article source: required.
- Topic / article thesis: required.
- Cover use case: X article cover, WeChat cover, blog header, tutorial cover, technical knowledge poster, PPT title visual.
- Inline use case: architecture explainer, workflow diagram, comparison panel, decision logic visual, feedback-loop inline image.
- Inline count: this is a hard constraint. If
正文配图数量is omitted, use3. If it is explicitly supplied, accept only an integer from1to5. Validate this before producing any template, brief, prompt, or image. An explicit0, negative number, non-integer, or value above5must fail with a clear request to use an integer from1to5; never clamp, round, expand, truncate, omit, or route to the base cover skill or cover-only behavior. - Language: Chinese, English, or mixed Chinese-English.
- Information structure: stage progression, before/after comparison, system architecture, feedback loop, maturity ladder, decision framework, bounded vs unbounded contrast.
- Cover ratio and inline ratio: optional; infer from use case when omitted.
- Extra context: optional.
- Forbidden elements: optional.
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.
- 12d ago First seen · 304 lines · 123 tokens per session scan A 3586c1dd6236
cover-cream-orange-knowledge-poster-with-docs is a skill published in the GitHub repository imartinstudio/cover-prompt-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 2,453 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…