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 endearqb/endearqb-skills --skill 1nfinix-editorial-card-screenshotgit clone --depth 1 https://github.com/endearqb/endearqb-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/endearqb/endearqb-skills/1nfinix-editorial-card-screenshot)<a href="https://agentmods.dev/skills/endearqb/endearqb-skills/1nfinix-editorial-card-screenshot"><img src="https://agentmods.dev/badge/skills/endearqb/endearqb-skills/1nfinix-editorial-card-screenshot/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/endearqb/endearqb-skills/1nfinix-editorial-card-screenshot"><img src="https://agentmods.dev/badge/skills/endearqb/endearqb-skills/1nfinix-editorial-card-screenshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00105 | $0.02698 |
| Opus 5 | $0.00053 | $0.01349 |
| Sonnet 5 | $0.00021 | $0.00540 |
| Haiku 4.5 | $0.00011 | $0.00270 |
Grade A, and why
1nfinix-editorial-card-screenshot 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editorial Card Screenshot
Overview
Turn source text into an editorial-style HTML information card, then capture it as a PNG in a supported ratio. The priority is editorial hierarchy plus stable rendering: no clipped Chinese text, no accidental cropping, and no large dead zones in the lower half.
Default deliverables unless the user asks otherwise:
- One complete HTML file with embedded CSS.
- One PNG screenshot rendered from that HTML.
Workflow
1. Analyze Content Density
Choose layout strategy from the content itself:
- Use "big-character" composition when content is sparse and a single phrase, number, or hook can carry the page.
- Use a two-column or three-column editorial grid when content is dense and needs stronger hierarchy.
- Use oversized numbers, heavy rules, tinted blocks, and pull-quote scale to avoid dead space.
- Do not force dense content into evenly weighted tiles. Build primary blocks, secondary blocks, and lighter supporting blocks.
- Match structure to content type:
- Ranking / recommendation content: allow asymmetric hero + structured list.
- Tutorial / analysis / interpretation content: group into overview, core judgment, interpretation, boundary, and conclusion.
Before compressing content, first change the layout skeleton.
- Ratio changes should primarily change reading path, hierarchy, and module arrangement.
- Do not treat ratio changes as a reason to delete content by default.
- Only compress, group, or summarize when the current ratio cannot hold the content clearly after layout has already been restructured.
2. Apply the Editorial Defaults
Use these defaults unless the user overrides them:
- Import Google Fonts:
<link href="https://fonts.googleapis.com/css2?family=Noto+Serif+SC:wght@700;900&family=Noto+Sans+SC:wght@400;500;700&family=Oswald:wght@500;700&family=Inter:wght@400;600;700&display=swap" rel="stylesheet"> - For Chinese text, always declare local CJK fallbacks before generic serif/sans-serif fallbacks. Prefer:
font-family: "Noto Sans SC", "Noto Sans CJK SC", "Source Han Sans SC", "Microsoft YaHei", "PingFang SC", sans-serif; font-family: "Noto Serif SC", "Noto Serif CJK SC", "Source Han Serif SC", "Songti SC", "STSong", serif; - Keep body text around
18pxto20pxon a 900px-wide composition. - Keep meta/tag text at
13pxminimum. - Use compact spacing: outer padding
40pxto50px, module gaps30pxto40px, line-height1.5to1.6. - Add visual anchors with
4pxto6pxaccent rules, subtle gray planes, and a light noise overlay. - Favor warm-paper backgrounds such as
#f5f3edunless the user specifies another palette. - For Chinese-heavy cards, shorten dense column line lengths and always add
overflow-wrap/word-breakguards. - If the user provides a title, use it as the main headline by default. Expand the layout before rewriting or shortening it.
- Avoid equal-weight boxes on dense cards. At least one module should feel visually heavier than the others.
- Do not hard-code signatures, creator handles, or personal branding unless requested.
What ships with it
6 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.
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 · 219 lines · 105 tokens per session scan A 817433ff0a36
1nfinix-editorial-card-screenshot is a skill published in the GitHub repository endearqb/endearqb-skills (19 stars, last pushed 9d ago), licensed MIT. It adds 105 tokens to every session and 2,698 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".
answer-reviewer-questions
For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions".
evaluate-findings
Critically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply using adversarial verification. Use when the user asks to "evaluate findings", "assess review comments", "triage review feedback", "evaluate review output", or "filter false positives".
create-project-skills
Scans an existing codebase and generates project-specific skills that capture inferred conventions such as naming, file organization, framework usage, data access, error handling, and testing style. Writes into the project's chosen skill directory (e.g., .claude/skills/, .agents/skills/, or a custom path). Use when…
retrospective-audit
Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…