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 Wang-Cankun/cankun-skills --skill cankun-blog-previewgit clone --depth 1 https://github.com/Wang-Cankun/cankun-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/wang-cankun/cankun-skills/cankun-blog-preview)<a href="https://agentmods.dev/skills/wang-cankun/cankun-skills/cankun-blog-preview"><img src="https://agentmods.dev/badge/skills/wang-cankun/cankun-skills/cankun-blog-preview/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/wang-cankun/cankun-skills/cankun-blog-preview"><img src="https://agentmods.dev/badge/skills/wang-cankun/cankun-skills/cankun-blog-preview.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 | $0.00122 | $0.01378 |
| Opus 5 | $0.00061 | $0.00689 |
| Sonnet 5 | $0.00024 | $0.00276 |
| Haiku 4.5 | $0.00012 | $0.00138 |
Grade A, and why
cankun-blog-preview 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate one Cankun blog preview
Treat one article slug, including its English and Chinese MDX pair, as the complete transaction. Never turn a single-article request into an archive-wide regeneration.
Preflight
- Confirm the workspace is
cankun-blogand contains:content/files/content/preview-image-prompts.mdpublic/images/scripts/optimize-previews.ts
- Resolve exactly one target slug. If the user did not name it, select it only when exactly one English MDX article lacks preview metadata; otherwise ask which article.
- Inspect
git statusand preserve unrelated changes. - Check whether the target already has a preview PNG or WebP. Overwrite it only when the user explicitly asked to refresh, replace, remake, or restyle it; otherwise report the existing asset and stop.
- Remember that
bun run previewsscans everypublic/images/**/*-preview.png. Check for unrelated stale sources before running it; stop and report a scope conflict if the command would regenerate another article's WebP.
Read the sources of truth
Read the target English article fully. Read its Chinese pair when present so the alternative text can be localized accurately.
Read these repository-owned sources rather than copying their contents into this skill:
content/preview-image-prompts.md— current series contract and per-article prompts.public/images/shape-of-not-knowing/known-unknowns-preview.png— visual style anchor.scripts/optimize-previews.ts— the only publication resize and WebP compression implementation.
Define one visual metaphor
Infer the image from the article's argument, not its title alone. Reduce it to one subject, one action or tension, and one spacious setting. Avoid collages and stacks of symbols.
When no metaphor is clearly strongest, present at most three concrete candidates and ask the user to choose before generating.
Add or update only the target article's block in content/preview-image-prompts.md. Preserve the existing prompt structure. Require all of the following:
What ships with it
1 file 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.
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 · 129 lines · 122 tokens per session scan A 5004c6dec1e5
cankun-blog-preview is a skill published in the GitHub repository Wang-Cankun/cankun-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 122 tokens to every session and 1,378 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
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…
create-video-seedance-2-fal
Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills…
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
render-cosmic-mythology-voiceover
Assemble a cosmic-mythology-voiceover reel from a config — a warm spoken voiceover carries the whole narrative while N curated cosmic stills are weighted beat-synced across the delivered VO duration (cutdur = VOdur times weight over the weight sum, so emotional beats hold longer), Ken-Burns-zoomed per still (scale 2x…