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 renky1025/agent-skills --skill mckinsey-covergit clone --depth 1 https://github.com/renky1025/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/renky1025/agent-skills/mckinsey-cover)<a href="https://agentmods.dev/skills/renky1025/agent-skills/mckinsey-cover"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/mckinsey-cover/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/renky1025/agent-skills/mckinsey-cover"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/mckinsey-cover.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 | $0.00000 | $0.01793 |
| Opus 5.5 | $0.00000 | $0.00717 |
| Sonnet 5.5 | $0.00000 | $0.00359 |
| Haiku 4.5 | $0.00000 | $0.00179 |
Grade A, and why
mckinsey-cover 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 1mo 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mckinsey-cover: 麦肯锡风格封面图片生成
基于 Adrian Punk 原创「麦肯锡风格提示词」，生成具有顶级咨询公司视觉质感的高级封面或信息图。
Purpose
把一句主题词转换为一张可直接交付的咨询风格视觉作品。技能本身不设计画面，而是把用户输入 准确映射到一套经过验证的固定提示词模版上，再由图片生成工具出图。价值在于路由正确、 占位符填对、不做多余改写。
When to Use
- 用户要求生成封面图，且风格指向咨询/研报/专业商务质感。
- 用户明确说「麦肯锡风格」「咨询风」「高级感封面」「商业报告封面」「PPT 封面」。
- 用户需要信息图，且强调结构清晰、克制、非自媒体风格：咨询分析页、方法论图、流程图、矩阵图。
- 触发词：麦肯锡封面、咨询风封面、研报封面、商业信息图、mckinsey cover、consulting cover。
When NOT to Use
- 用户要的是摄影质感、写实、产品图或情感化视觉 -> 交给
image-design。 - 用户要的是信息卡片（内容型、多模块、带主题配色）-> 交给
infocard。 - 用户要的是工程化规格出图、透明底素材、UI 原型、角色一致性 -> 交给
spec-image。 - 用户只想要提示词文本本身、明确表示不出图 -> 把
references/prompt-template.md的填充结果 直接交给用户，不要调用出图工具。
Workflow
- 解析输入：提取必填主题词；映射
--usage到用途描述；对其余参数取默认值。 主题超过 30 字时标记，让模版中的「长标题自动提炼机制」生效。 - 填充模版：读取
references/prompt-template.md，把七个{{}}占位符替换为实际值。 无值的位置填空字符串，不要删除该行。 - 调用出图工具：把填充后的完整提示词传入，尺寸按下方映射表设置。 调用前先告知用户本次消耗约 5-10 credits。
- 展示结果：用
present_files展示生成的图片，并附一句主题与用途的说明。
Decision Rules
用途映射（--usage -> 提示词中的用途描述）：
--usage |
用途描述 | --usage |
用途描述 | |
|---|---|---|---|---|
cover |
X封面 | infographic |
信息图 | |
ppt |
PPT封面 | consulting |
咨询分析页 | |
report |
商业报告封面 | methodology |
方法论图 | |
portfolio |
作品集封面 | flowchart |
流程图 | |
wechat |
公众号封面 | matrix |
矩阵图 |
封面类与信息图类走模版中两条不同的处理逻辑（封面信息密度低、信息图允许 3-6 个模块）， 不要混用。
尺寸映射（--ratio -> 出图尺寸）：
--ratio |
尺寸 | --ratio |
尺寸 | |
|---|---|---|---|---|
5:2 |
1536x614 | 3:4 |
1152x1536 | |
16:9 |
1536x864 | 1:1 |
1024x1024 | |
4:5 |
1024x1280 |
其余分流：
- 用户未指定
--usage-> 默认cover。 - 主题词缺失 -> 向用户追问主题，不要自行编造。
- 出图工具报提示词超长 -> 按
references/prompt-template.md的「长度裁剪」顺序降级， 并告知用户裁掉了哪些章节。 - 生成结果不符合咨询质感（出现卡通、霓虹、握手图标等）-> 直接重试一次，
并在提示词中强化
{{禁用元素}}。
Constraints
- 提示词原文不得改写。除
{{}}占位符外，references/prompt-template.md中的文字 一律原样提交。长度限制、禁止元素清单和末尾指令都是刻意设计的，不是冗余。 - 末尾指令必须原样保留：
请根据用户输入用途，直接生成最终画面。不要输出分析过程，不要输出解释文字。 - 出图前必须披露 credit 消耗（约 5-10 credits/次）。
- 不得把主题词拆散或替换成同义词；品牌名、人名、术语保持用户输入的原始写法。
- 生成结果不唯一，重试属于正常流程，不要为此反复向用户确认。
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.
- 1mo ago Changed · -621 lines · -115 tokens per session 2be15b27f765
- 2mo ago First seen · 734 lines · 115 tokens per session scan A d7d4d4b7ec83
mckinsey-cover is a skill published in the GitHub repository renky1025/agent-skills (11 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,793 tokens. 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.
mckinsey-cover compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mckinsey-coverrenky1025/agent-skills | Skill | 11 | 28d ago | MIT | A | 0 | Claude Code |
| ui-ux-pro-maxDuanZGit/D-Hub | Skill | 0 | yesterday | MIT | A | 114 | Claude Code |
| create-xilehui-brand-posterCatmint103/xilehui-brand-agent | Skill | 3 | 23d ago | none | A | 169 | Codex |
| xilehui-header-footer-templateCatmint103/xilehui-brand-agent | Skill | 3 | 23d ago | none | A | 95 | Codex |
| SwiftUIonmyway133/claude-code-plugins | Skill | 5 | 10mo ago | MIT | A | 16 | Claude Code |
| Frontend Designonmyway133/claude-code-plugins | Skill | 5 | 10mo ago | MIT | A | 19 | Claude Code |
| design-taste-frontendDuanZGit/D-Hub | Skill | 0 | yesterday | MIT | A | 61 | Claude Code |