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 agentmods add skills/swaylq/master-skill/outputnpx skills add swaylq/master-skill --skill outputgit clone --depth 1 https://github.com/swaylq/master-skillWrote 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/swaylq/master-skill/output)<a href="https://agentmods.dev/skills/swaylq/master-skill/output"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/output.svg" alt="Measured on agentmods" 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 | $0.04239 | $0.14491 |
| Opus 5 | $0.02119 | $0.07246 |
| Sonnet 5 | $0.00848 | $0.02898 |
| Haiku 4.5 | $0.00424 | $0.01449 |
Grade A, and why
ad-agency-performance-master 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 5d 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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
广告外包公司绩效管理 · Master OS
装上这个 skill, agent 立刻进入「广告外包公司绩效管理」资深人模式 — 用这一行的心智模型 + 决策规则 + 工作流 + 说话方式 给判断。
激活规则
收到与 广告外包公司绩效管理 相关的问题时（关键词：广告公司绩效, 广告外包绩效管理, agency 绩效, 广告公司 KPI, 广告公司 OKR, 创意绩效考核, 广告公司提成制, 乙方绩效, 广告公司人效, 项目利润率考核, billable hours 广告, 工作室制 分成, 创意不可量化 考核, 广告公司薪酬绩效, 营销外包 绩效），先按下方 Agentic Protocol 做功课，再用本 skill 的心智模型 + playbook 给出答复。
如果问题完全跟 广告外包公司绩效管理 无关 — 不激活，正常应答。
Agentic Protocol（先研究，再发言）
核心原则：广告外包公司绩效管理 不靠训练语料硬答。遇到需要事实支撑的问题，先按本节列出的研究维度做功课。
Step 1: 问题分类
| 类型 | 特征 | 行动 |
|---|---|---|
| 需要事实 | 涉及具体工具 / 公司 / 版本 / 现状 / 数字 | → Step 2 研究 |
| 纯框架 | 抽象决策 / 概念辨析 / 入门讲解 | → 直接 Step 3 用心智模型回答 |
| 混合 | 用具体案例讨论抽象问题 | → 先取事实，再用框架分析 |
判断原则：如果回答质量会因为缺少最新信息显著下降，必须先研究。
Step 2: 按这一行的方式做功课
⚠️ 必须使用工具（WebSearch / WebFetch / agent-reach 等）获取真实信息。
维度 1: 定位/定价与考核口径判定
- 看什么: agency 怎么定价(工时制/项目制/retainer/价值制)、定位与客户结构——决定考核口径。
- 在哪看: Track 04 定价 canon(Enns/Williams) + Track 03 阶段 0。
- 输出: 定价方式 + 对应考核口径(util vs 项目毛利 vs 客户价值)。
维度 2: 人效基线核算（LUBRM）
- 看什么: utilization/realization/项目利润率/人均毛利/AGI per head 现状。
- 在哪看: PSA/工时数据(Track 02) + LUBRM 框架(Track 01 Maister/Track 06)。
- 输出: 人效四件套数值 + 诊断(问题在人还是在定价)。
维度 3: 分岗位指标设计
- 看什么: 各岗可量化性(创意三层/媒介硬指标/AE 客户/BD 销售)。
- 在哪看: Track 03 分岗位 SOP + Track 04 创意可量化三层。
- 输出: 每岗指标(质量软评/效率结果硬指标)+权重，标哪层靠评议。
维度 4: 激励与分配设计
- 看什么: 提成 vs 固定+奖金 vs 项目分成 vs 合伙人；获取分享+熔断是否适用。
- 在哪看: Track 01(华为/稻盛/Williams) + Track 03 阶段 4。
- 输出: 分配机制 + 奖金池核算方式 + 协作/个人平衡 + 创意非物质激励。
维度 5: 考核执行与反绩效主义防坑
- 看什么: PBC/OKR 闭环、校准、强制分布用不用、指标会不会被刷(Goodhart)、是否杀创意。
- 在哪看: Track 03 阶段 5-6 + Track 01(Deming/Muller/索尼)。
- 输出: 考核流程(目标→述职→校准→面谈→应用) + Goodhart 复审点 + 强制分布适用层级。
维度 6: 乙方风险与 AIGC 调优
- 看什么: 甲方不确定性(改稿/账期/比稿)如何纳入+合同前置对冲；AIGC 对工时制的冲击。
- 在哪看: Track 01(Enns/Farmer) + Track 02(计费工时悖论) + Track 03。
- 输出: 甲方风险纳入指标+合同对冲方案 + AIGC 后考核口径调整(转单位价值)。
研究完成后，把事实摘要内部整理（不直接展示给用户），进入 Step 3。用户应该看到的是经过框架处理的判断，不是 raw research dump。
Step 3: 用心智模型 + 决策规则输出回答
What ships with it
9 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.
- cli/decision/evidence.sh 3.7 KB runs code
- cli/decision/topic-1.sh 4.4 KB runs code
- cli/decision/topic-3.sh 4.4 KB runs code
- cli/decision/topic-4.sh 3.2 KB runs code
- cli/decision/topic-5.sh 3.2 KB runs code
- cli/lib/common.sh 1.8 KB runs code
- cli/protocol/agentic.sh 4.7 KB runs code
- cli/README.md 1.6 KB
- meta.json 5.4 KB
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.
- 5d ago First seen · 333 lines · 4,239 tokens per session scan A e66fd2d05cf2
ad-agency-performance-master is a skill published in the GitHub repository swaylq/master-skill (127 stars, last pushed 7d ago), licensed MIT. It adds 4,239 tokens to every session and 14,491 once invoked, about $0.0212 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
pitchcraft
Structured persuasion for tech leads, PMs, and founders—not activity logs. Five scenarios (kickoff, status update, wrap-up, investor pitch, solution selling) on one 5-part framework (Hook→Context→Proposal→Evidence→Ask). AI prompts for missing materials and audience context; pre-submit checklist. Claude Code plugin…
all-deploy
Deploys any web app, API, or agent to the internet with a strict pre-deploy audit and a preview → health-check → prod flow. Detects Next, Vite, Astro, Remix, Nuxt, SvelteKit, FastAPI, Flask, Express, MCP server, Claude Agent SDK script, Python worker, Dockerized, and static projects; routes to Vercel, Railway…
watch-anything
看懂视频与富媒体：X 推文（含推文视频）/ YouTube / B站 / 无字幕视频链接 → 字幕优先或本地/云端语音转写 → 中文卡片解读（卡片：摘要 3 句 + 要点 3-6 条 + 金句中英对照；全稿：讲述脉络按原片结构走完 + 关键案例 + 结构图）→ 基于材料的多轮问答。触发：用户丢 X/YouTube/B站/视频链接并说"解读/看懂/讲了啥/转写一下/值得看吗/这视频说了什么"，或明确说"watch-anything"。read-anything 的姊妹：read 管读文字，watch 管看视频/富媒体。.
read-anything
即时分析：任意链接（网页/博客/YouTube/B站/小宇宙播客/X）或本地录音（会议录音/语音备忘录）→ 抓取或本地转写 → 中文结构化解读（精读稿/快扫/访谈拆解/会议纪要/论文拆解/选题素材六种模板+自定义）→ 基于材料的多轮问答。触发：用户丢链接/音频文件/粘贴纪要并说"分析/解读/精读/这是什么/讲了啥/值得看吗/提选题"，或明确说"即时分析"。.
context-graph-compressor
Compress any conversation into a portable JSON context graph for handoff to a new chat or LLM. Trigger on: "compress this chat", "save context", "new chat", "hand off", "transfer context", "too many tokens", "start fresh", "export conversation", "context graph", "continue in new session". Also trigger proactively when…
wiki
LLM 维护的持久化 Markdown 知识库 —— 既可用作个人知识库（/wiki/）， 也可用于给开源项目做架构 wiki（ -wiki/）。 触发场景：用户说 "wiki"、"/wiki"、"添加到wiki"、"ingest"、"wiki lint"、 "wiki add"、"wiki query"、"wiki status"、"添加到知识库"、"导入这篇文章"、 "收藏这个"、"记到wiki里"、"建一个 wiki"、"给 X 做架构 wiki"。.