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 HYYH-code/agent-skills --skill research-cover-generatorgit clone --depth 1 https://github.com/HYYH-code/agent-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/hyyh-code/agent-skills/research-cover-generator)<a href="https://agentmods.dev/skills/hyyh-code/agent-skills/research-cover-generator"><img src="https://agentmods.dev/badge/skills/hyyh-code/agent-skills/research-cover-generator/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/hyyh-code/agent-skills/research-cover-generator"><img src="https://agentmods.dev/badge/skills/hyyh-code/agent-skills/research-cover-generator.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 | $0.00082 | $0.02046 |
| Opus 5 | $0.00041 | $0.01023 |
| Sonnet 5 | $0.00016 | $0.00409 |
| Haiku 4.5 | $0.00008 | $0.00205 |
Grade A, and why
research-cover-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
研究报告风公众号封面生成器 V3
这个 Skill 解决什么问题
把一篇文章压缩成一张 20:9、缩略图可读、让人想点开学习 的公众号封面。
V3 的核心升级：
- 构图与配色由文章语义驱动，不写死模板；
- 同时支持两种渲染路径：
direct_text：模型直接生成带文字封面；overlay_text：模型生成无字底图，再由脚本准确叠字；
- 提供
auto自动决策模式：根据标题长度、文字准确率要求与审美优先级自动选路径； - 默认先追求图像理解质量，再保证文字准确率，而不是用保守底图牺牲观感。
最简调用
/research-cover-generator FDE 到底是什么？一个普通人看得懂的 AI 新岗位入门指南（万字长文）
推荐调用
标题：FDE 到底是什么？一个普通人看得懂的 AI 新岗位入门指南（万字长文）
摘要：解释 FDE 的定义、岗位别名、典型项目、招聘趋势与入门路径。
关键词：AI 落地、工作流、工程交付、新岗位、入门指南
数量：3
模式：auto
文字准确率优先级：high
视觉冲击力优先级：high
三种渲染模式
1) direct_text
适合：
- 模型中文排版能力较强；
- 标题较短；
- 追求“画面与文字一体化”的整体感；
- 更看重观感上限。
执行要求：
- 允许模型直接生成主标题、副标题、角标；
- 标题必须逐字正确；
- 生成后必须核对标题是否与输入一致；
- 若发现错字、漏字、形近替换、乱码，立即重试或转入 overlay_text。
2) overlay_text
适合：
- 标题较长；
- 含英文缩写、括号、副说明；
- 明确要求“一字不差”；
- 批量出图；
- 当前模型中文文字稳定性一般。
执行要求：
- 底图必须无任何文字、字母、水印；
- 底图只负责画面理解与视觉隐喻，不承载任何排版文字；
- 经检查批准后，用脚本准确叠加中文；
- 最终只允许出现一层文字。
3) auto
默认模式。
自动判断规则：
- 长标题 / 高风险文字 / 强准确率要求 → 优先
overlay_text； - 短标题 / 模型带字能力强 / 更重视整体美感 → 优先
direct_text； - 若
direct_text首次输出文字不可靠，则降级为overlay_text。
具体诊断可调用：
python "${CODEBUDDY_SKILL_DIR}/scripts/recommend_strategy.py" \
--title "文章标题" \
--summary "文章摘要" \
--keywords "关键词1,关键词2" \
--render-mode auto
标准工作流
第一步：语义诊断
提取：
- 核心对象
- 读者状态
- 学习承诺
- 核心矛盾
- 主叙事关系
- 可视化关键词
先形成一句内部命题：
用【视觉关系】表现【核心矛盾】，让读者一眼理解【学习承诺】。
第二步：选择构图原型
从构图库中动态选择，不准看见某个主题词就固定套模板。
构图候选至少覆盖这 14 类之一：
- 汇聚归一
- 断层桥接
- 穿墙管道
- 资源开采
- 剖面揭示
- 路径导航
- 模块拼合
- 流程闭环
- 对照分岔
- 增长扩散
- 网络枢纽
- 翻译适配
- 杠杆放大
- 种子生长
当用户要 3 张图时，必须输出三个不同叙事角度，而不是同一画面换色。
第三步：选择配色
从 12 套色板中选择，按文章气质匹配：
sage鼠尾草绿：入门、平静、可理解blue雾霾蓝：系统、工程、API、部署warm暖灰：方法、沉淀、价值转化oat燕麦米：知识型、杂志感、阅读友好teal灰青：逻辑、结构、理性ink墨蓝：严肃、技术、深度lavender灰紫：趋势、未来、观察clay柔陶粉：职业、人物、协作moss苔藓灰绿：组织、长期主义、稳健sand沙金灰：资源、开采、价值沉淀charcoal石墨灰：风险、冲突、批判fog柔雾青白：极简、清洁、轻研究感
第四步：设计标题结构
标题文字可以重组换行，但不得改字、删字或擅自添加结论。
建议拆成：
- 第一层：认知钩子 / 问题句
- 第二层：收益说明 / 内容定位
- 第三层：角标（如“万字长文”“入门指南”“研究版”）
What ships with it
11 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.
- assets/reference-blue-pipeline.png 1417 KB
- assets/reference-sage-gap.png 1403 KB
- assets/reference-warm-mining.png 1968 KB
- examples/sample_requests.md 665 B
- README.md 4.0 KB
- references/composition-library.md 1.8 KB
- references/palette-system.md 1.9 KB
- references/render-modes.md 737 B
- scripts/approve_background.py 1001 B runs code
- scripts/compose_cover.py 5.5 KB runs code
- scripts/recommend_strategy.py 4.1 KB runs code
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.
- 8d ago First seen · 217 lines · 82 tokens per session scan A dbcdf2291b02
research-cover-generator is a skill published in the GitHub repository HYYH-code/agent-skills (3 stars, last pushed 14d ago), licensed MIT. It adds 82 tokens to every session and 2,046 once invoked, about $0.0004 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
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.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.