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 serejaris/kimi-skills --skill audience-adaptergit clone --depth 1 https://github.com/serejaris/kimi-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/serejaris/kimi-skills/audience-adapter)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/audience-adapter"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/audience-adapter/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/serejaris/kimi-skills/audience-adapter"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/audience-adapter.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 | $0.00112 | $0.02788 |
| Opus 5 | $0.00056 | $0.01394 |
| Sonnet 5 | $0.00022 | $0.00558 |
| Haiku 4.5 | $0.00011 | $0.00279 |
Grade A, and why
audience-adapter 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 11d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stakeholder-comms
根据受众角色自动调整沟通内容的粒度、语言和侧重点。支持 CEO、VP、技术负责人、运营四类典型受众，覆盖向上汇报和跨部门沟通场景。
使用流程
第一步：收集原始信息
向用户询问以下内容：
- 沟通主题：要汇报/同步什么事（项目进展、问题升级、方案决策、成果汇报等）
- 原始素材：用户掌握的所有细节（可以是散乱笔记、技术文档、数据报告、聊天记录等任何形式）
- 目标受众：这份内容要给谁看（CEO / VP / 技术负责人 / 运营 / 其他角色——若受众不在上述四类中，让用户说明该角色的职能和关注点，然后参考最接近的受众策略进行适配调整）
- 沟通目的：信息同步、争取资源、请求决策、风险预警、成果展示
- 输出形式：邮件、会议口头汇报要点、Slack/飞书消息、PPT 大纲、正式文档
如果用户已在初始请求中明确部分信息，可跳过对应的确认。
第二步：确定受众画像与调整策略
根据目标受众，自动应用以下调整策略：
受众调整策略
CEO / 创始人
关注点：战略影响、商业价值、关键决策点、风险与机会
粒度调整：
- 最高层抽象，只保留结论和决策项
- 整个汇报控制在 1 页或 3 分钟口头时间内
- 删除所有技术实现细节和过程描述
- 数据只保留最关键的 1-3 个指标
语言风格：
- 用商业语言而非技术术语
- "我们完成了微服务架构迁移" → "系统稳定性提升 40%，支撑下季度 3 倍流量增长"
- "数据库查询优化" → "用户体验提升，页面加载快了 2 秒"
- 避免缩写和行业黑话，除非确认 CEO 熟悉
结构模板：
# [主题] — 一句话结论
## 核心结论
用 1-2 句话总结最重要的信息和建议的行动。
## 关键数据
- 指标1：数值 + 变化趋势（↑/↓ X%）
- 指标2：数值 + 与目标的差距
## 需要您的决策/了解（按需）
- 决策项1：选项 A vs 选项 B，推荐 X，原因一句话
- 决策项2：...
## 风险提示（如有）
- 风险描述 → 影响范围 → 应对方案
VP / 部门负责人
关注点：部门目标达成、资源分配、跨团队依赖、里程碑进度、团队健康度
粒度调整：
- 中高层抽象，保留关键过程节点和决策背景
- 可展开到具体项目或工作流级别，但不到代码/操作级别
- 数据包含趋势和对比（环比、与目标对比）
- 资源和人力相关信息要具体
语言风格：
- 可使用部门内通用的专业术语
- 强调目标对齐和资源效率
- "API 重构完成了 70%" → "核心接口改造完成 70%，剩余部分需后端增加 1 人周，预计下周四交付"
- 问题描述要附带影响评估和资源需求
结构模板：
# [主题] 进展同步
## 整体状态
一段话概括当前状态、是否按计划推进、主要成果。
## 里程碑进展
| 里程碑 | 状态 | 进度 | 预计完成 | 备注 |
|---|---|---|---|---|
| 里程碑1 | 进行中 | 70% | MM-DD | 按计划 |
| 里程碑2 | 延期 | 40% | MM-DD | 原因简述 |
## 关键成果
- 成果1：量化描述 + 业务影响
- 成果2：...
## 问题与需要的支持
- **问题1**：描述 → 对目标的影响 → 需要的资源/决策
- **问题2**：...
## 跨团队依赖
- 依赖方 → 事项 → 当前状态 → 期望时间
## 下阶段计划
按优先级列出 3-5 项重点工作及预期产出。
技术负责人 / 架构师
关注点：技术方案、架构影响、性能指标、技术债务、实现风险
粒度调整：
- 中低层抽象，可以包含技术方案对比和架构决策
- 需要给出具体的技术指标（QPS、延迟、错误率等）
- 可以讨论实现路径，但不需要逐行代码级别
- 技术风险要有具体的评估和缓解方案
语言风格：
- 可以自由使用技术术语和缩写
- 直接给结论和推荐方案，用数据支撑
- "建议用 Redis 做缓存" → "建议引入 Redis 缓存热点查询，预计 P99 延迟从 800ms 降到 200ms，需要 2 天开发 + 1 天压测"
- 方案对比要有明确的 trade-off 分析
结构模板：
# [主题] 技术同步
## 概要
一句话说明技术变更的目的和当前状态。
## 技术方案 / 变更内容
描述做了什么、为什么这么做。如果涉及方案选型，给出选项对比：
| 维度 | 方案 A | 方案 B |
|---|---|---|
| 性能 | ... | ... |
| 复杂度 | ... | ... |
| 风险 | ... | ... |
推荐方案：X，理由：...
## 关键指标
- 指标1（如 QPS）：变更前 → 变更后
- 指标2（如 P99 延迟）：变更前 → 变更后
## 影响范围
- 受影响的服务/模块
- 是否需要数据迁移
- 是否有 breaking change
## 风险与缓解
- 风险1 → 缓解措施
- 风险2 → 缓解措施
## 排期与依赖
- 预计工时：X 人天
- 前置依赖：...
- 计划上线时间：MM-DD
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.
- 11d ago First seen · 294 lines · 112 tokens per session scan A 47f9c57bfb49
audience-adapter is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 2,788 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
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
offensive-bluetooth-classic
Bluetooth Classic (BR/EDR) attack methodology — device discovery, service enumeration via SDP, LMP/L2CAP layer attacks, legacy PIN cracking (BlueBorne / KNOB), Bluetooth file-transfer abuse (BlueSnarfing legacy), unauthenticated profile abuse (HSP, HFP, OPP), and modern relevance against older industrial / automotive…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
design-md-validator
Validate DESIGN.md files against the official Google specification using the @google/design.md CLI linter. Works with local files. Use when the user wants to lint a DESIGN.md, check spec compliance, find broken token references, verify WCAG contrast ratios, diff two versions, export tokens to Tailwind or DTCG format…
agent-ready-oauth-protected-resource
Sub-skill de agent-ready-cloudflare: Implement OAuth Protected Resource Metadata.